LADRC control parameter determination method based on Bayesian optimization algorithm

Abstract

The invention provides a method for determining LADRC control parameters based on a Bayesian optimization algorithm, and relates to the technical field of industrial control, and the method comprises the steps: based on a transfer function of a PID controller, building an equivalent function relation between PID control parameters KP, KI and KD and a parameter set formed by the parameters of LADRC control; a Bayesian optimization algorithm is adopted, the values of PID control parameters KP, KI and KD are determined, KP is proportional gain, KI is integral time, and KD is differential time; according to the equivalent function relation and the values of the parameters KP, KI and KD of PID control, the values of all the parameters of LADRC control are determined respectively, the complexity of LADRC control parameter adjustment can be reduced, efficiency can be improved, and a powerful parameter adjustment strategy is provided for wide application of the LADRC controller.

Description

Technical Field

[0001] This application generally relates to the field of industrial control technology. More specifically, this application relates to a method, system, medium, and device for determining LADRC control parameters based on the Bayesian optimization algorithm. Background Art

[0002] Linear Active Disturbance Rejection Controller (LADRC) is a control method with less dependence on the model and has good application prospects in the field of industrial control. However, due to the existence of a large number of undetermined parameters and the complex parameter adjustment process, the trial-and-error cost in industrial application scenarios is relatively high, which limits its industrial applicability. The current adjustment schemes mainly include the artificial bee colony algorithm, chaotic quantum particle swarm optimization algorithm, etc. However, it is still difficult to specify the search range and initial value for each parameter during the adjustment process, and expanding the search space without selection will significantly increase the time required for adjustment. Therefore, finding an effective method to reduce the complexity of LADRC control parameter adjustment and improve efficiency is crucial for the industrial control process. Summary of the Invention

[0003] In order to solve at least one or more of the above-mentioned technical problems, this application proposes a method, system, medium, and device for determining LADRC control parameters based on the Bayesian optimization algorithm in multiple aspects.

[0004] In the first aspect, the method for determining LADRC control parameters provided by this application includes the following steps: Based on the transfer function of the PID controller, establish the equivalent function relationship between the parameters K P , K I and K D of the PID control and the parameter set formed by each parameter of the LADRC control; Use the Bayesian optimization algorithm to determine the values of the parameters K P , K I and K D of the PID control, where K P is the proportional gain, K I is the integral time, and K D is the derivative time; According to the equivalent function relationship and the values of the parameters K P , K I and K D of the PID control, determine the values of each parameter of the LADRC control respectively.

[0005] In some examples, the method further includes: According to the structural form of the transfer function of the PID controller, the parameters K P , K I and K D of the PID control and the equivalent function relationship between the parameter sets formed by the parameters of the LADRC control are established respectively.

[0006] In some examples, the method further includes: According to the values of the parameters K P , K I and K D of the PID control and the equivalent function relationship, the parameters of the LADRC control are determined respectively, where are the observer bandwidth, the controller bandwidth and the control domain respectively.

[0007] In some examples, the equivalent function relationship is:

[0008] where is the observer parameter of the LADRC control, l 1 ,l 2 is the controller parameter of the LADRC control, , .

[0009] In some examples, the method further includes: According to the formula , the final value of the parameter is determined.

[0010] In some examples, the method further includes: According to the formula , the final value of the parameter b 0 is determined, where the value of the parameter is the final value.

[0011] In a second aspect, the control method based on the LADRC controller provided in this application includes the following steps: Obtain the values of each parameter by using the determination method disclosed in the first aspect; Use the values of each parameter as the parameter values of the LADRC control to obtain an LADRC controller with parameter values assigned; Use the LADRC controller with parameter values assigned to perform control.

[0012] In a third aspect, the determination system of the LADRC control parameters based on the Bayesian optimization algorithm provided in this application includes: The module is configured to establish the PID control parameters K based on the transfer function of the PID controller. P , K I and K D The equivalent functional relationship between the value of and the parameter set formed by each parameter controlled by LADRC; The first determination module is configured to use a Bayesian optimization algorithm to determine the parameter K of the PID control P , K I and K D The value of K P is the proportional gain, K I is the integration time, K D is the differential time; The second determination module is configured to determine the equivalent function relationship and the parameter K of the PID control. P , K I and K D The values of determine the values of each parameter controlled by LADRC.

[0013] In a fourth aspect, the present application provides a computer-readable storage medium, which includes program instructions. When the program instructions are executed by a processor, the method described in the first aspect is implemented.

[0014] In a fifth aspect, the present application provides an electronic device, comprising: Processor; and A memory storing computer instructions, which, when executed by the processor, enables the electronic device to execute the method described in the first aspect.

[0015] By using the method, system, medium and device for determining LADRC control parameters based on the Bayesian optimization algorithm provided above, the debugging workload is based on the Bayesian optimization algorithm and by constructing the PID control parameter K P , K I and K D The parameters of LADRC control are obtained by the equivalent functional relationship between the parameter sets formed by the various parameters of LADRC control, which can reduce the complexity of LADRC control parameter adjustment and improve efficiency, and provide a powerful parameter adjustment strategy for the wide application of LADRC controller. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easy to understand. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 Shows the system structure block diagram corresponding to LADRC control; Figure 2 Shows the structural schematic diagram of the LADRC controller equivalent to the PID controller structure; Figure 3 Shows the exemplary flowchart of the method for determining the LADRC control parameters based on the Bayesian optimization algorithm in some embodiments of the present application; Figure 4 Shows the comparison schematic diagram of the control effects of PID control and LADRC control when the transfer function is G1; Figure 5 Shows the comparison schematic diagram of the control effects of PID control and LADRC control when the transfer function is G2; Figure 6 Shows the comparison schematic diagram of the control effects of PID control and LADRC control when the transfer function is G3; Figure 7 Shows the comparison schematic diagram of the control effects of PID control and LADRC control when the transfer function is G4; Figure 8 Shows the comparison schematic diagram of the actual temperature change in the temperature chamber and the temperature change predicted by the transfer function of the heating system in the application scenario of the temperature control platform; Figure 9 Shows the comparison schematic diagram of the results of the set-point disturbance test of PID control and LADRC control in the application scenario of the temperature control platform; Figure 10 Shows the exemplary structure block diagram of the electronic device in some embodiments of the present application. Detailed implementation manners

[0017] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0018] It should be understood that the terms "including" and "comprising" used in the specification of the present application indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0019] It should also be understood that the terms used in the specification of this application are merely for the purpose of describing specific embodiments and are not intended to limit this application. As used in the specification of this application, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms. It should be further understood that the term "and / or" used in the specification of this application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0020] As used in the specification of this application, the term "if" can be interpreted as "when", "once", "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if it is determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once it is determined" or "in response to determining" or "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]" depending on the context.

[0021] The specific embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0022] Embodiment 1 The LADRC controller can be applied to many actual systems, including single-input single-output, multi-input multi-output systems, non-linear, time-varying systems, and model-uncertain systems. For the convenience of analysis, it is assumed that the controlled object is a type of system that can be described by a transfer function: (1) In Equation (1), y(s) and u(s) are the Laplace transforms of the output quantity and the input quantity respectively, and p represents the model parameter. G p is the control object, which can be a wide range of systems such as a high-order model, a model with delay, a non-minimum phase model, or a distributed parameter model.

[0023] In Figure 1 , based on the concept of the state observer, the influence of the disturbance on the output of the controlled object is extended to include new state variables. A dedicated feedback mechanism establishes an observer ESO that can monitor these extended states, effectively solving the disturbance observation challenge in the active disturbance rejection control technology and serving as a key component of the entire LADRC system. The observer ESO operates independently of the model generating the disturbance. By observing the output of the object, the observed values of the first derivative and the second derivative, the ESO can effectively eliminate the dynamic characteristics and external disturbances in the system, improving the performance and robustness of the closed-loop system and being applicable to the control and optimization of complex dynamic systems. r is the set value, u is the control quantity, y is the output value, d is the control quantity disturbance, and the form of the ESO (observer) is: (2) In Equation (2), are the observer parameters. The control law is expressed as: (3) In Equation (3), are the controller parameters. If the controlled object Gp is approximated as: (4) In Equation (4), f is the extended state, which includes y and its derivatives of each order, u and its derivatives of each order, as well as the information of all internal and external disturbances of the system. Its form may be unknown. At this time, due to the observation effect of the observer ESO, can be obtained. Under the action of Equation (3), . On this basis, the LADRC controller can convert any control system into two integral series links.

[0024] Example 2 In Figure 2 , according to the structure of the PID controller, the structure of the LADRC controller is equivalently converted into the corresponding feedback compensator C(s) and the pre-filter C 1 （s） . Among them, P(s) is the controlled object, and the transfer function of the PID controller is: (5) In Equation (5), , s is the complex frequency domain variable.

[0025] By equivalently converting the PID controller into a feedback compensator, the LADRC control parameters can be converted into PID controller parameters. Among them, the transfer function of the feedback compensator is: (6) Example 3 As Figure 3 shown, the method for determining the LADRC control parameters based on the Bayesian optimization algorithm provided by the embodiment of the present application includes the following steps: At step S101, based on the transfer function of the PID controller, the equivalent function relationships between the parameters K P , K I and K D of the PID control and the parameter sets formed by the respective parameters of the LADRC control are established.

[0026] In some examples, step S101 specifically includes: According to the structural form of the transfer function of the PID controller, the parameters K of the PID control are respectively establishedP , K I and K D and the parameters controlled by LADRC to form an equivalent functional relationship between the parameter sets. Among them, .

[0027] Specifically, the derivation process of this equivalent functional relationship is as follows: (7) At step S102, the Bayesian optimization algorithm is adopted to determine the parameters K P , K I and K D of PID control. Among them, K P is the proportional gain, K I is the integral time, and K D is the derivative time.

[0028] Specifically, the core idea of the Bayesian optimization algorithm is to use the probabilistic surrogate model and the acquisition function to find the optimal solution. The advantage of this algorithm is that it can effectively and accurately locate the best hyperparameters in a shorter time by using the previous evaluation results. Initially, the posterior probability distribution of the first n points is calculated using Gaussian process regression, so as to infer the expected mean value and variance of each hyperparameter at each point. The mean value represents the expected final impact of this point, and the higher the mean value, the better the effect; while the variance reflects the uncertainty around this effect, and a larger variance indicates greater uncertainty. It should be noted that it is not recommended to only select the point with the highest mean value, because this may lead to falling into a local optimal solution; some points with higher variance may have the potential for the global optimum. Therefore, selecting points with high mean values is called exploitation, while selecting points with high variance for sampling is called exploration. To balance between exploitation and exploration, an acquisition function is introduced. The choice of the acquisition function is crucial for the efficiency and accuracy of the algorithm, especially for solving complex hyperparameter optimization problems. Therefore, in practice, the choice of the acquisition function needs to be carefully considered to improve the performance of the algorithm. The specific process of the Bayesian optimization algorithm is as follows: Step 1, initialization phase, randomly select several groups of parameters from the parameter set for model training to obtain the corresponding model evaluation metrics; Step 2, use a surrogate function (such as a Gaussian function) to fit the parameters and the corresponding model evaluation metrics; Step 3, use the acquisition function to select the best parameters; Step 4, input the best parameters into the model to obtain new model evaluation metrics, and return to Step 2 for iteration.

[0029] At step S103, according to the equivalent functional relationship and the parameters K of PID controlP , K I and K D , respectively determine the values of the respective parameters of the LADRC control.

[0030] In some examples, step S103 specifically includes: According to the parameters K P , K I and K D of the PID control and the equivalent function relationship, respectively determine the parameters of the LADRC control, where are the observer bandwidth, the controller bandwidth, and the control domain, respectively.

[0031] In some examples, as can be obtained from Equation (7), the equivalent function relationship is: (8) where, since K P , K I and K D are known, the value of can be obtained through Equation (8), is the observer parameter of the LADRC control, l 1 ,l 2 is the controller parameter of the LADRC control, , .

[0032] In some examples, since the parameter obtained from Equation (8) is too small to be used as a reference, the final value of the parameter is determined through Equation .

[0033] In some examples, according to Equation , the final value of the parameter b 0 is determined, where the value of the parameter is its final value.

[0034] Example 4 To evaluate the effectiveness of the method for determining the LADRC control parameters proposed in this application, several typical transfer functions were selected for simulation on the MATLAB / Simulink platform. A PID controller and an LADRC controller for various typical systems were constructed on the Simulink platform, and the obtained simulation results were evaluated using the integral time absolute error (ITAE) index. Among them: (9) In Equation (9), t is time, and e(t) is the temperature deviation value.

[0035] The model consists of two parts: a PID controller and an LADRC controller, both of which are continuous. When dealing with the same step signal and disturbance signal, the two controllers can be applied simultaneously, and their results can be compared through graphical representation. For PID control, its parameters are obtained through the Bayesian optimization algorithm, which can search for the parameter combination that achieves the optimal control effect. The parameters of LADRC control are obtained according to the determination method proposed in this application. The comparison data of the two control methods are shown in Table 1.

[0036] Table 1

[0037] In Figure 4 , under the action of the PID controller, the disturbance process shows an overshoot phenomenon. The overshoot is about 5%, the adjustment time is about 12 s, and the ITAE index is 5.784×10 -1 ; when using LADRC for disturbance rejection control, it shows better stability. The overshoot is about 0.8%, the adjustment time is 14 s, and the ITAE index is 1.616×10 -1 , and the number of oscillations is 0. However, there is still room for improvement in terms of rapidity, the steady-state time is long, and the rise time also needs to be optimized.

[0038] From Figure 5 it can be seen that for the object of the non-minimum phase system, under the action of the PID controller, the overshoot is about 16%, the adjustment time is about 22 s, and the ITAE index is 5.721×10 -1 ; under the action of the ADRC controller, the overshoot is about 5%, the adjustment time is about 22 s, and the ITAE index is 4.571×10 -1 . The control effect of the LADRC controller is slightly better than that of the PID controller, reducing the overshoot of the system and making the adjustment process more stable.

[0039] From Figure 6 it can be seen that under the action of the PID controller, the overshoot is about 17%, the adjustment time is about 30 s, and the ITAE index is 1.161. Under the action of the ADRC controller, the overshoot is about 15%, the adjustment time is about 22 s, and the ITAE index is 4.188×10 -1 . The adjustment process of the LADRC controller is stable, with a faster steady-state response speed, and the control effect is better than PID control.

[0040] From Figure 7It can be seen that under the action of the PID controller, the overshoot is about 8%, the adjustment time is about 20 s, and the ITAE index is 1.35; under the action of the LADRC controller, the overshoot is about 0.5%, the adjustment time is about 18 s, and the ITAE index is 8.738×10 -1 . The control effect of the LADRC controller is better than that of the PID control, the overshoot is reduced, and the control process is stable.

[0041] According to the above experimental results, it shows that the method for determining the LADRC control parameters proposed in this application is feasible, which can ensure the stability of the adjustment process, and has good control effect and anti-interference ability.

[0042] Example 5 Taking the temperature control platform based on the programmable logic controller (PLC) as the application scenario, the transfer function of the heating system can be simplified to a first-order lag system, and its transfer function is as follows: (10) The model mainly identifies the parameter , imports the temperature change curve into the System Identification model in the MATLAB toolbox, and the fitting similarity is 96.33%. The identification result is as Figure 8 shown, and the transfer function is: (11) Import this transfer function into the Bayesian optimization algorithm, and the initial parameters of the PID controller are determined to be K P =191.132, K I =38.79, K D =9.865. According to the parameter determination steps proposed in this application, the parameter values of the LADRC control are 23.595, 7.865, and 0.5695 respectively.

[0043] The set value of the temperature control platform working condition parameter is set to 50 °C at the 5 s moment, and a temperature set-point disturbance test is carried out with two groups of parameters. The comparison of the response curves is shown in Figure 9 .

[0044] From Figure 9 the results of the set-point disturbance test shown in the set-point disturbance test, it can be seen that for this temperature control platform under the action of the LADRC control, the adjustment time is about 80 s, the overshoot is about 2.3%, and the ITAE index is about 1.625×10 -1 . For this temperature control platform under the action of the PID control, the adjustment time is about 95 s, the overshoot is about 1.6%, and the ITAE index is about 2.583×10 -1, it is not difficult to find that the adjustment time of the LADRC control is better than that of the PID controller. It enters the steady state after 70 s, and the steady-state error is very small. According to the determination method proposed in this application, the effectiveness of the method for obtaining the LADRC control parameters is verified.

[0045] The above experimental results prove the effectiveness of the LADRC control in terms of robustness, adaptability, and anti-interference. It is a promising advanced control technology with a wide range of applications. The method for determining the LADRC parameters based on the Bayesian optimization algorithm proposed in this application establishes an equivalent form relationship between the PID parameters and the LADRC parameters to calculate the LADRC parameters. Experiments prove that the method provided in this application can ensure the effectiveness of system parameter transplantation, reduce the debugging workload, reduce the complexity of adjusting the LADRC control parameters, improve the efficiency, and provide a powerful parameter adjustment strategy for the wide application of the LADRC controller.

[0046] On the other hand, the embodiment of this application also provides an electronic device. Refer to Figure 10 , Figure 10 is an exemplary structural block diagram of an electronic device according to an embodiment of this application. As Figure 10 shown, the electronic device includes a processor and a memory. Computer instructions are stored in the memory, and when the processor runs the computer instructions, it executes the method provided in this application.

[0047] Specifically, the processor 601 may include a central processing unit (CPU) or a graphics processing unit (GPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. The memory 602 may include a memory for data or instructions. For example, the memory 602 may be at least one of the following: a hard disk drive (HDD), a read-only memory (ROM), a random access memory (RAM), a floppy disk drive, a flash memory, an optical disc, a magneto-optical disc, a magnetic tape, a universal serial bus (USB) drive, or other physical / tangible memory storage devices. Also, the memory 602 includes a removable or non-removable (or fixed) medium. Again, the memory 602 may be inside or outside the integrated gateway disaster recovery device. The memory 602 may be a non-volatile solid-state memory. In other words, generally, the memory 602 includes a tangible (non-transitory) computer-readable storage medium (such as a memory device) encoded with executable instructions, and when the executable instructions stored therein are executed by the processor 601 (such as by one or more processors), the method in the embodiments of this application can be implemented.

[0048] In one example, Figure 10 the illustrated electronic device may further include a communication interface 603 and a bus 610. Among them, the processor 601, the memory 602, and the communication interface 603 are connected through the bus 610 to complete communication with each other. The communication interface 603 is mainly used to implement communication between various modules, devices, units, and / or devices in the electronic device. The bus 610 includes hardware, software, or both, and can couple the components of the online data flow charging device to each other. For example, the bus may include at least one of the following: Accelerated Graphics Port (AGP) or other graphics buses, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), HyperTransport (HT) interconnect, Industry Standard Architecture (ISA) bus, InfiniBand interconnect, Low Pin Count (LPC) bus, Memory bus, MicroChannel Architecture (MCA) bus, Peripheral Component Interconnect (PCI) bus, PCI-Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local (VLB) bus, or other suitable buses. The bus 610 may include one or more buses. Although the embodiments of the present application describe or illustrate specific buses, the embodiments of the present application may consider any suitable bus or interconnection method.

[0049] On the other hand, the embodiments of the present application also provide a computer-readable storage medium, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the foregoing method is implemented. The computer-readable storage medium is, for example, a classic computer-readable storage medium, such as a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device.

[0050] On the other hand, the embodiments of the present application also provide a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor, the method provided by the embodiments of the present application is implemented. The computer program product is, for example, a software installation package, a plug-in compatible with the relevant software system, etc.

[0051] The flowcharts and / or block diagrams of the methods and systems of the embodiments of the present application have been described above by way of example, and the relevant aspects have been described. It should be understood that each block or combination of blocks in the flowchart and / or block diagram can be implemented by computer program instructions, or by dedicated hardware that performs the specified functions or actions, or by a combination of dedicated hardware and computer instructions. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a functional card, etc.; when implemented in software, it is a program or code segment used to perform the required tasks. The program or code segment can be stored in a memory, or transmitted via a data signal carried in a carrier wave on a transmission medium or a communication link. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0052] Although the present application has shown and described multiple embodiments, it is obvious to those skilled in the art that such embodiments are provided only by way of example. Those skilled in the art can think of many changes, alterations, and alternative ways without departing from the idea and spirit of the present application. It should be understood that various alternative solutions to the embodiments of the present application described in the present application can be adopted in the process of practicing the present application.

Claims

1. A method for determining the control parameters of LADRC based on the Bayesian optimization algorithm, characterized in that, including: Based on the transfer function of the PID controller, the parameters K of the PID control are established respectively. P , K I and K D The equivalent functional relationship between the parameter set formed by each parameter controlled by LADRC; Use the Bayesian optimization algorithm to determine the parameters \(K_p\), \(K_i\), and \(K_d\) of the PID control, where \(K_p\) is the proportional gain, \(K_i\) is the integral time, and \(K_d\) is the derivative time; P \(K_p\), I \(K_i\), D and \(K_d\) P \(K_p\) I \(K_i\) D \(K_d\); According to the values of the equivalent function relationship and the parameters \(K_{p}\), \(K_{i}\), and \(K_{d}\) of the PID control, the values of the respective parameters of the LADRC control are determined respectively. P \(_{p}\), I \(_{i}\), D and \(K_{d}\) of the PID control, the values of the respective parameters of the LADRC control are determined respectively.

2. The determination method according to claim 1, wherein The method further includes: According to the structural form of the transfer function of the PID controller, the parameters K P 、K I and K D of the PID control and the equivalent functional relationship between the parameter set formed by the parameters of the LADRC control are established respectively.

3. The determination method according to claim 2, characterized in that, The method further includes: According to the values of the parameters \(K_{p}\), \(K_{i}\), and \(K_{d}\) of the PID control and the equivalent function relationship, respectively determine the values of the parameters \(b_{0}\), \(b_{1}\), and \(b_{2}\) of the LADRC control, where \(b_{0}\), \(b_{1}\), and \(b_{2}\) are the observer bandwidth, the controller bandwidth, and the control domain, respectively. P ,\(K_{i}\) I and \(K_{d}\) D respectively determine the values of the parameters of the LADRC control according to the values and the equivalent function relationship, where the values of are the observer bandwidth, the controller bandwidth, and the control domain, respectively.

4. The determination method according to claim 3, characterized in that The equivalent functional relationship is: Among them, are the observer parameters of LADRC control, l 1 ,l 2 are the controller parameters of LADRC control, , .

5. The determination method according to claim 3, wherein: According to the formula , determine the final value of the parameter .

6. The determination method according to claim 5, wherein: According to the formula , determine the final value of parameter b 0, where the value of parameter is the final value.

7. A control method based on an LADRC controller, characterized in that, including: Obtaining the values of each parameter by using the determination method described in any one of claims 1-5; Taking the values of each parameter as the parameter values of LADRC control to obtain an LADRC controller with parameter values assigned; Performing control by using the LADRC controller with parameter values assigned.

8. A system for determining the control parameters of LADRC based on the Bayesian optimization algorithm, characterized in that, including: A building module, configured to respectively establish an equivalent functional relationship between the values of parameters K P , K I and K D of PID control and a parameter set formed by respective parameters of LADRC control; The first determination module is configured to determine the parameters \(K_p\), \(K_i\), and \(K_d\) of the PID control by using the Bayesian optimization algorithm, where \(K_p\) is the proportional gain, \(K_i\) is the integral time, and \(K_d\) is the derivative time. P \(p\) I \(i\) D \(d\) P is the proportional gain, \(K\) I \(_i\) D is the integral time, \(K\) A second determination module, configured to determine the values of the respective parameters of the LADRC control according to the equivalent function relationship and the values of the parameters K P , K I , and K D of the PID control.

9. A computer-readable storage medium, characterized in that, Containing program instructions, when the program instructions are executed by a processor, enabling the implementation of the method described in any one of claims 1-8.

10. An electronic device, characterized in that, including: a processor; and a memory storing computer instructions, when the computer instructions are run by the processor, enabling the electronic device to execute the method described in any one of claims 1-8.

Images