A UAV pitch control method and system based on fuzzy immune control optimized PID

Abstract

The present invention discloses a fuzzy immune control optimized PID unmanned aerial vehicle pitch control method and system, which relates to the field of unmanned aerial vehicle control. The analysis method comprises the following steps: decoupling and linearly simplifying the unmanned aerial vehicle motion equation to obtain a longitudinal motion mathematical model; initializing parameters of a PID controller according to the response requirements and performance indicators of the system; building a unmanned aerial vehicle PID control system; establishing a fuzzy control module and performing fuzzy reasoning adjustment; initializing immune algorithm parameters and determining the optimization termination condition of the immune algorithm to obtain an initial unmanned aerial vehicle PID control system; optimizing the initial unmanned aerial vehicle PID control system; connecting the optimized unmanned aerial vehicle PID control system to a controlled object and running them; optimizing and adjusting the fuzzy control module and immune algorithm parameters according to real-time operation effects. The present invention can achieve the purpose of adaptively adjusting PID parameters, adapt to different flight environments and mission requirements, and improve the flight performance and mission execution efficiency of the unmanned aerial vehicle.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle (UAV) control, and in particular to a UAV pitch control method and system based on fuzzy immune control and PID optimization. Background Art

[0002] The primary functions of a fixed-wing drone's pitch control system are to maintain a stable flight attitude, control altitude, adjust attitude, and optimize flight performance. These capabilities enable drones to perform missions efficiently and stably in a variety of applications. Due to the well-developed PID control theory, PID control systems offer strong stability and practicality, making them widely used in drone control systems and crucial for precise control operations.

[0003] With the rapid development of drone technology, drone applications are expanding, placing higher demands on their flight performance and control precision. Fixed-wing drones, a common type of drone, have a pitch control system whose performance directly impacts their overall performance. Traditional controllers exhibit limitations in drone pitch control, such as sensitivity to parameter adjustments and weak interference immunity. Furthermore, drones must adapt to various uncertainties during flight, including complex and volatile aerial environments, changes in their own state, and adjustments to their mission. These factors complicate the design of drone flight control systems and place higher demands on them. This requires control systems to be adaptable and robust, capable of rapidly responding to changing environments and mission requirements to ensure flight safety and mission success.

[0004] Fuzzy algorithms are computational methods based on fuzzy logic principles, used to address uncertainty and ambiguity. They use fuzzy sets, fuzzy rules, and fuzzy reasoning to model and process fuzzy information for decision-making, control, or optimization tasks. Immune algorithms are computational methods based on the principles of the immune system. By simulating the immune system's evolutionary, selective, and adaptive capabilities, they are used to solve optimization, search, and pattern recognition problems.

[0005] Therefore, there is an urgent need for a UAV pitch control method and system based on fuzzy immune control optimized PID to meet the high requirements of UAV control systems. Summary of the Invention

[0006] To solve the above problems, this application provides a UAV pitch control method and system based on fuzzy immune control optimized PID, with the goal of improving adaptability and robustness, aiming to be able to quickly respond to changing environments and mission requirements, so as to ensure the flight safety of the UAV and the completion of the mission.

[0007] In this application, a method for controlling the pitch of a UAV using fuzzy immune control and PID optimization is provided, comprising the following steps:

[0008] S1. Decoupling and linearly simplifying the UAV motion equation to obtain a longitudinal motion mathematical model, which is a PID control object;

[0009] S2. Initialize the parameters of the PID controller according to the system response requirements and performance indicators;

[0010] S3. Build a UAV PID control system, establish a fuzzy control module and perform fuzzy reasoning adjustment. The fuzzy control module includes a fuzzy set and fuzzy rules. The fuzzy control module uses the error amount of the UAV PID control system and the error change rate of the UAV PID control system as input data, and uses the parameter adjustment amount of the UAV PID controller as output data;

[0011] S4. Initialize the immune algorithm parameters and determine the optimization termination condition of the immune algorithm to obtain the initial UAV PID control system;

[0012] S5. Optimize the initial UAV PID control system to obtain an optimized UAV PID control system, connect the optimized UAV PID control system to the controlled object and run them;

[0013] S6. Optimize and adjust the fuzzy control module and immune algorithm parameters according to the real-time operation results.

[0014] Preferably, in S1, the UAV motion equation is decoupled and linearly simplified to obtain the specific content of the longitudinal motion mathematical model as follows:

[0015] Establish the UAV motion equation to obtain the mathematical motion model, and decouple the mathematical motion model to obtain the longitudinal sub-model;

[0016] The longitudinal sub-model is linearized according to the small perturbation principle to obtain a decoupled model;

[0017] According to the short-period motion characteristics of the UAV in the longitudinal direction, the degrees of freedom in the decoupling model are simplified to obtain a short-period decoupling model.

[0018] Preferably, the expression for building the UAV PID control system is:

[0019]

[0020] Among them, k p is the proportional coefficient, T i is the integration time constant, T d is the differential time constant, s is the Laplace operator, and G(s) is the transfer function.

[0021] Among them, the expression of the short-period decoupling model is:

[0022]

[0023] Among them, V is the velocity along the x-axis of the body, α is the angle of attack, q is the pitch angular velocity, δ e is the elevator deflection increment, is the force caused by the change in angular velocity at the angle of attack, is the torque caused by the change of angular velocity at the angle of attack, Z α is the force caused by the change of angle of attack, M α is the moment caused by the change of angle of attack, Z δe is the force caused by the incremental deflection of the elevator, M δe is the moment caused by the incremental elevator deflection.

[0024] Preferably, the specific content of the fuzzy reasoning adjustment is:

[0025] Obtain the precise value of the controlled quantity of the UAV PID control system to obtain the collected quantity, and compare the collected quantity with the given quantity to obtain the error signal E;

[0026] The digital quantity of the error signal E is fuzzified to obtain a fuzzy quantity;

[0027] There is a preset rule for the correspondence between fuzzy quantity and fuzzy language. The corresponding fuzzy language represents the fuzzy quantity to obtain a subset e of the fuzzy language set.

[0028] Combining fuzzy control rules with fuzzy reasoning rules, fuzzy decision making is achieved;

[0029] Combining the fuzzy decision with the subset e, we get the fuzzy control quantity u;

[0030] The expression of fuzzy control quantity u is:

[0031] u=e*R;

[0032] Among them, R is a fuzzy relationship;

[0033] Repeatedly collect the precise values of the controlled quantities of the UAV PID control system and repeatedly perform fuzzy reasoning and adjustment processing.

[0034] Preferably, in S4, the immune algorithm is used to calculate the proportional coefficient k p Make adjustments.

[0035] The present application also provides a fuzzy immune control optimized PID unmanned aerial vehicle pitch control system, including: a data preprocessing module: decoupling and linearly simplifying the UAV motion equation to obtain a longitudinal motion mathematical model, the longitudinal motion mathematical model is the PID control object, and the PID controller is initialized according to the system response requirements and performance indicators;

[0036] Model construction module: Build a UAV PID control system, establish a fuzzy control module and perform fuzzy reasoning adjustment. The fuzzy control module includes fuzzy sets and fuzzy rules. The fuzzy control module uses the error amount of the UAV PID control system and the error change rate of the UAV PID control system as input data, and the parameter adjustment amount of the UAV PID controller as output data. It initializes the immune algorithm parameters and determines the optimization termination condition of the immune algorithm to obtain the initial UAV PID control system.

[0037] Model optimization module: Optimize the initial UAV PID control system to obtain the optimized UAV PID control system, connect the optimized UAV PID control system to the controlled object and run it, and optimize and adjust the fuzzy control module and immune algorithm parameters according to the real-time operation results.

[0038] To sum up, the UAV pitch control method and system of the present invention with fuzzy immune control optimized PID, compared with the traditional PID control method, obtains the transfer function by linearly simplifying the longitudinal motion model of the UAV, introduces fuzzy control and immune feedback algorithm, and integrates the two with PID control, so that the UAV pitch control system can adaptively adjust the PID parameters to adapt to different flight environments and mission requirements. Due to the use of fuzzy immune control algorithm, the system has strong anti-interference ability and robustness. The implementation of the UAV pitch control system mentioned in this application can improve the flight performance of the UAV and the efficiency of executing tasks.

[0039] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a method step diagram of a UAV pitch control method using fuzzy immune control optimized PID according to the present invention;

[0041] Figure 2 This is a control flow chart of a UAV pitch control system based on fuzzy immune control and PID optimization according to the present invention;

[0042] Figure 3 This is a fuzzy immune control principle diagram of a UAV pitch control method based on fuzzy immune control optimized PID in the present invention.

[0043] Figure 4This is a flow chart of the immune control algorithm of the UAV pitch control method using fuzzy immune control optimized PID in the present invention;

[0044] Figure 5 This is a step response simulation result diagram of a UAV pitch control method based on fuzzy immune control optimized PID in the present invention. DETAILED DESCRIPTION

[0045] The technical solutions of the present invention are further described below through the accompanying drawings and embodiments. It should be noted that unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions and values described in these embodiments do not limit the scope of this application.

[0046] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present disclosure, its application, or uses.

[0047] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, they should be considered part of the specification.

[0048] In all examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0049] Unless otherwise defined, technical or scientific terms used in the present invention shall have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs.

[0050] To control the pitch motion of a drone, a mathematical model of its pitch motion is first required. To better understand the drone's motion trends and design a simple and effective control system, the drone's motion model is approximately linearized. The following assumptions are made: First, the aircraft's aerodynamic shape is symmetrical, and its mass is evenly distributed. Furthermore, the aircraft is assumed to be in stable horizontal flight, with the sideslip and roll angles very close to zero. These assumptions allow the aircraft's mathematical model to be decoupled into a longitudinal submodel. Next, the decoupled longitudinal submodel is linearized using the small perturbation principle. This allows the nonlinear system to be approximately converted to a linear one, making controller design easier. For the pitch angle controller design of the longitudinal submodel, the elevator is used as the input. By controlling the elevator angle, the aircraft's pitch attitude is adjusted. This design approach simplifies the control system structure and provides effective pitch angle control.

[0051] like Figure 1As shown, a fuzzy immune control optimized PID UAV pitch control method is provided, comprising the following steps: S1, decoupling and linearly simplifying the UAV motion equation to obtain a longitudinal motion mathematical model, which is a PID control object.

[0052] Furthermore, in S1, the UAV motion equation is decoupled and linearly simplified to obtain the specific content of the longitudinal motion mathematical model as follows: the UAV motion equation is established to obtain the mathematical motion model, and the mathematical motion model is decoupled to obtain the longitudinal sub-model.

[0053] The decoupled longitudinal model is as follows:

[0054] Where: X = [Vαθq] T is the state quantity, V is the velocity along the x-axis of the body, α is the angle of attack, θ is the pitch angle, and q is the pitch angular velocity.

[0055] U=δ e , U is the input, δ e is the elevator deflection increment.

[0056] The matrices E, A, and B are obtained by Taylor series expansion of the nonlinear formula and retaining the first-order terms.

[0057]

[0058] The longitudinal sub-model is linearized according to the small perturbation principle to obtain the decoupled model.

[0059] Except for the hover state, in general, due to is much smaller than V, so the Jacobian matrix E is always non-singular and can be written in standard form:

[0060]

[0061] During the initial phase of an aircraft's longitudinal motion, when subjected to a disturbance or input, short-period motion primarily occurs, with a very rapid transition. During this brief initial phase, the changes in flight speed and pitch angle are relatively small, i.e., the increment ΔV = Δθ = 0. This simplifies the original four-degree-of-freedom longitudinal motion equations (speed, angle of attack, pitch angle, and pitch rate) to only two degrees of freedom (angle of attack and pitch rate).

[0062] According to the short-period motion characteristics of the UAV in the longitudinal direction, the degrees of freedom in the decoupling model are simplified to obtain a short-period decoupling model.

[0063] Furthermore, the expression of the short-period decoupling model is,

[0064]

[0065] Among them, V is the velocity along the x-axis of the body, α is the angle of attack, q is the pitch angular velocity, δ e is the elevator deflection increment, is the force caused by the change in angular velocity at the angle of attack, is the torque caused by the change of angular velocity at the angle of attack, Z α is the force caused by the change of angle of attack, M α is the moment caused by the change of angle of attack, Z δe is the force caused by the incremental deflection of the elevator, M δe is the moment caused by the incremental elevator deflection.

[0066] In the pitch attitude control loop, the servo transfer function is represented by the inertial link, and the longitudinal model of the UAV is represented by δ e As input, q is expressed as a transfer function.

[0067] S2. Initialize the parameters of the PID controller according to the system's response requirements and performance indicators.

[0068] S3. Use MATLAB to build a conventional fixed-wing UAV pitch control system, namely the UAV PID control system.

[0069] A fuzzy control module is established and fuzzy reasoning adjustment is performed. The fuzzy control module includes a fuzzy set and fuzzy rules. The fuzzy control module takes the error amount of the drone PID control system and the error change rate of the drone PID control system as input data, and takes the parameter adjustment amount of the drone PID controller as output data.

[0070] A simple block diagram of a fixed-wing drone using a PID controller is shown below: Figure 2 As shown in Figure 1, PID control is a classic control theory that helps achieve the desired control effect for the controlled object. In traditional analog control systems, PID control has been widely adopted and has become an indispensable control strategy. Using a PID controller, the deviation percentage can be adjusted and the deviation integral can be introduced, significantly improving the system's stability and anti-interference capabilities. Furthermore, the use of differential branches not only effectively suppresses the system's inertial delay but also significantly improves system stability, thereby significantly enhancing the performance and quality of the entire control system.

[0071] Furthermore, the expression for building the UAV PID control system is:

[0072] Among them, k p is the proportional coefficient, T i is the integration time constant, T dis the differential time constant, s is the Laplace operator, and G(s) is the transfer function.

[0073] The basic structure of fuzzy control is the fuzzy control module, such as Figure 3 By writing the corresponding program, the fuzzy control module can adjust the parameters to achieve the desired effect.

[0074] Furthermore, the specific content of the fuzzy reasoning adjustment is to obtain the precise value of the controlled quantity of the UAV PID control system to obtain the collected quantity, and compare the collected quantity with the given quantity to obtain the error signal E.

[0075] The digital quantity of the error signal E is fuzzified to obtain a fuzzy quantity.

[0076] There are preset rules for the correspondence between fuzzy quantities and fuzzy languages, and the corresponding fuzzy languages are used to express the fuzzy quantities to obtain a subset e of the fuzzy language set.

[0077] Combining fuzzy control rules and fuzzy reasoning rules, fuzzy decision making is obtained.

[0078] Combining the fuzzy decision with the subset e, we get the fuzzy control quantity u.

[0079] The expression of the fuzzy control quantity u is u=e*R.

[0080] Among them, R is a fuzzy relationship.

[0081] Repeatedly collect the precise values of the controlled quantities of the UAV PID control system and repeatedly perform fuzzy reasoning and adjustment processing.

[0082] S4. Initialize the immune algorithm parameters and determine the optimization termination conditions of the immune algorithm to obtain the initial UAV PID control system.

[0083] The immune control algorithm is a method modeled after the biological immune system, used to eliminate foreign viruses. During this process, T lymphocytes transmit antigens to B lymphocytes, enabling information exchange. B cells, in turn, restore the body's health by producing antibodies and phagocytizing the antigens. This immune response is a complex and dynamic biological reaction. During this information exchange process, a complex state of mutual regulation and feedback is established between T and B cells. If either cell changes or becomes abnormal, the relationship between them needs to be adjusted. When a large amount of antigen is present in the body, promoter T cells undergo orderly cell division and reproduction, stimulating B cell proliferation and further antibody production. As the amount of antigen decreases, suppressor T cells begin to multiply, inhibiting B cell production and thus preventing energy consumption.

[0084] like Figure 4 As shown, the immune process algorithm.

[0085] Assume that the number of antigens in the kth generation is ε(k), and the number of promoting T cells is T H (k), the number of suppressor T cells is T s (k), the stimulation received by B cells is S(k).

[0086] Among them, T H (k)=k1ε(k).

[0087] T S (k) = k2f(ΔS(k))ε(k).

[0088] S(k)=T H (k)-T S (k).

[0089] Wherein, k1 is the excitation factor, k2 is the inhibition factor, and f(ΔS(k)) is a nonlinear function representing the degree of inhibition.

[0090] If the number of antigens ε(k) is regarded as the system deviation e(k), and the stimulation of B cells S(k) is regarded as the output of the system, the relationship between the system output and the proportional parameter can be obtained.

[0091] The relational expression is: S(k)=K(1-ηf(ΔS(k)))e(k).

[0092] Where η = k2 / k1 is the stabilizing effect of the control, and K = k1 is the reaction speed of the control.

[0093] In the field of immune controllers, designing nonlinear functions f(·) is a very challenging task, but fuzzy control theory can be used to approximate various linear or nonlinear functions to achieve higher control accuracy. By identifying the fuzzy relationship between input variables and output variables, the membership function f(·) and fuzzy control rules corresponding to the fuzzified input variables can be queried during operation to adjust parameters and the proportional coefficient of the immune PID controller in a timely manner, thereby achieving better control effects. The fuzzy controller is used to realize the integration time constant K I and the differential time constant K D The adaptive online tuning is realized, thus realizing the fuzzy immune adaptive PID control.

[0094] Furthermore, in S4, the immune algorithm is used to calculate the proportional coefficient k p Make adjustments.

[0095] S5. Optimize the initial UAV PID control system to obtain an optimized UAV PID control system, connect the optimized UAV PID control system to the controlled object and run them.

[0096] S6. Optimize and adjust the fuzzy control module and immune algorithm parameters according to the real-time operation results.

[0097] In this application, a fuzzy immune control optimized PID UAV pitch control system is also provided, including a data preprocessing module: decoupling and linearly simplifying the UAV motion equation to obtain a longitudinal motion mathematical model, the longitudinal motion mathematical model is the PID control object, and the PID controller parameters are initialized according to the system response requirements and performance indicators.

[0098] Model construction module: build a UAV PID control system, establish a fuzzy control module and perform fuzzy reasoning adjustment. The fuzzy control module includes fuzzy sets and fuzzy rules. The fuzzy control module takes the error amount of the UAV PID control system and the error change rate of the UAV PID control system as input data, and the parameter adjustment amount of the UAV PID controller as output data. It initializes the immune algorithm parameters and determines the optimization termination conditions of the immune algorithm to obtain the initial UAV PID control system.

[0099] Model optimization module: Optimize the initial UAV PID control system to obtain the optimized UAV PID control system, connect the optimized UAV PID control system to the controlled object and run it, and optimize and adjust the fuzzy control module and immune algorithm parameters according to the real-time operation results.

[0100] Table 1 Transient response performance index table

[0101] <![CDATA[Rise time t r / s]]> Peak time tp / s Adjustment time ts / s Overshoot σ% ZN method tuning 1.6578 7.3230 2.5995 0.74％ Fuzzy Immunity Method 0.7886 3.5710 1.3147 0.19％

[0102] Combined with Table 1 and Figure 5 As shown in the figure, the step signal response curves of the traditional ZN method and the fuzzy immune method clearly show that when the desired pitch angle of 1° is input, the parameters obtained by optimizing the PID using the fuzzy immune algorithm are better than those obtained by tuning using the ZN method, with faster response speed, shorter rise time and smaller steady-state error.

[0103] To sum up, the UAV pitch control method and system of the present invention with fuzzy immune control optimized PID, compared with the traditional PID control method, obtains the transfer function by linearly simplifying the longitudinal motion model of the UAV, introduces fuzzy control and immune feedback algorithm, and integrates the two with PID control, so that the UAV pitch control system can adaptively adjust the PID parameters to adapt to different flight environments and mission requirements. Due to the use of fuzzy immune control algorithm, the system has strong anti-interference ability and robustness. The implementation of the UAV pitch control system mentioned in this application can improve the flight performance of the UAV and the efficiency of executing tasks.

[0104] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solutions of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A UAV pitch control method based on fuzzy immune control optimized PID, characterized in that: The following steps are involved: S1. Decoupling and linearly simplifying the UAV motion equation to obtain a longitudinal motion mathematical model, which is a PID control object; S2. Initialize the parameters of the PID controller according to the system response requirements and performance indicators; S3. Build a UAV PID control system, establish a fuzzy control module and perform fuzzy reasoning adjustment. The fuzzy control module includes a fuzzy set and fuzzy rules. The fuzzy control module uses the error amount of the UAV PID control system and the error change rate of the UAV PID control system as input data, and uses the parameter adjustment amount of the UAV PID controller as output data; S4. Initialize the immune algorithm parameters and determine the optimization termination condition of the immune algorithm to obtain the initial UAV PID control system; S5. Optimize the initial UAV PID control system to obtain an optimized UAV PID control system, connect the optimized UAV PID control system to the controlled object and run them; S6. Optimize and adjust the fuzzy control module and immune algorithm parameters according to the real-time operation results; The specific content of the fuzzy reasoning adjustment is: Obtain the precise value of the controlled quantity of the UAV PID control system to obtain the collected quantity, and compare the collected quantity with the given quantity to obtain the error signal E; The digital quantity of the error signal E is fuzzified to obtain a fuzzy quantity; There is a preset rule for the correspondence between fuzzy quantity and fuzzy language. The corresponding fuzzy language represents the fuzzy quantity to obtain a subset e of the fuzzy language set. Combining fuzzy control rules with fuzzy reasoning rules, fuzzy decision making is achieved; Combining the fuzzy decision with the subset e, we get the fuzzy control quantity u; The expression of fuzzy control quantity u is: u=e*R; Among them, R is a fuzzy relationship; Repeatedly collect the precise values of the controlled quantities of the UAV PID control system and repeatedly perform fuzzy reasoning and adjustment processing.

2. The UAV pitch control method based on fuzzy immune control optimized PID according to claim 1 is characterized in that: In S1, the UAV motion equations are decoupled and linearly simplified to obtain the specific contents of the longitudinal motion mathematical model as follows: Establish the UAV motion equation to obtain the mathematical motion model, and decouple the mathematical motion model to obtain the longitudinal sub-model; The longitudinal sub-model is linearized according to the small perturbation principle to obtain a decoupled model; According to the short-period motion characteristics of the UAV in the longitudinal direction, the degrees of freedom in the decoupling model are simplified to obtain a short-period decoupling model.

3. The UAV pitch control method based on fuzzy immune control optimized PID according to claim 1 is characterized in that: The expression for building a drone PID control system is: Among them, k p is the proportional coefficient, T i is the integration time constant, T d is the differential time constant, s is the Laplace operator, and G(s) is the transfer function.

4. The UAV pitch control method based on fuzzy immune control optimized PID according to claim 2 is characterized in that: The expression of the short-period decoupling model is: Among them, V is the velocity along the x-axis of the body, α is the angle of attack, q is the pitch angular velocity, δ e is the elevator deflection increment, is the force caused by the change in angular velocity at the angle of attack, is the torque caused by the change of angular velocity at the angle of attack, Z α is the force caused by the change of angle of attack, M α is the moment caused by the change of angle of attack, Z δe is the force caused by the incremental deflection of the elevator, M δe is the moment caused by the incremental elevator deflection.

5. The UAV pitch control method based on fuzzy immune control optimized PID according to claim 3 is characterized in that: In S4, the immune algorithm is used to calculate the proportional coefficient k p Make adjustments.

6. A UAV pitch control system based on fuzzy immune control optimized PID, characterized by: include: Data preprocessing module: Decouples and linearly simplifies the UAV motion equation to obtain a longitudinal motion mathematical model. The longitudinal motion mathematical model is the PID control object. The PID controller parameters are initialized according to the system response requirements and performance indicators. Model construction module: Build a UAV PID control system, establish a fuzzy control module and perform fuzzy reasoning adjustment. The fuzzy control module includes fuzzy sets and fuzzy rules. The fuzzy control module uses the error amount of the UAV PID control system and the error change rate of the UAV PID control system as input data, and the parameter adjustment amount of the UAV PID controller as output data. It initializes the immune algorithm parameters and determines the optimization termination condition of the immune algorithm to obtain the initial UAV PID control system. The specific content of the fuzzy reasoning adjustment is: Obtain the precise value of the controlled quantity of the UAV PID control system to obtain the collected quantity, and compare the collected quantity with the given quantity to obtain the error signal E; The digital quantity of the error signal E is fuzzified to obtain a fuzzy quantity; There is a preset rule for the correspondence between fuzzy quantity and fuzzy language. The corresponding fuzzy language represents the fuzzy quantity to obtain a subset e of the fuzzy language set. Combining fuzzy control rules with fuzzy reasoning rules, fuzzy decision making is achieved; Combining the fuzzy decision with the subset e, we get the fuzzy control quantity u; The expression of fuzzy control quantity u is: u=e*R; Among them, R is a fuzzy relationship; Repeatedly collect the precise values of the controlled variables of the UAV PID control system and repeatedly perform fuzzy reasoning and adjustment processing; Model optimization module: Optimize the initial UAV PID control system to obtain the optimized UAV PID control system, connect the optimized UAV PID control system to the controlled object and run it, and optimize and adjust the fuzzy control module and immune algorithm parameters according to the real-time operation results.

Images