Complex system parameter determination method, device and equipment

Abstract

The invention provides a complex system parameter determination method, device and equipment, and relates to the technical field of data processing, and the method can set a gravity line of vine growth by fusing expert experience on the basis of a swarm intelligence algorithm, can reduce the iteration time when iteration is carried out according to the gravity line, and improves the iteration efficiency. And the algorithm for simulating the vine growth can be widely explored in a global range, and can go deep into a local area to carry out fine search, so that falling into a local optimal solution can be avoided, and the probability of finding a global optimal solution is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device and equipment for determining parameters of a complex system. Background Art

[0002] Before large, complex systems are put into operation, their key parameters must be set. Currently, traditional methods rely primarily on manual optimization by experienced engineers. Engineers first draw on expert experience to determine possible initial values ​​for the parameters. Then, they perform extensive manual operations to continuously optimize the parameters within a simulation system. Finally, the optimized parameters are embedded into the system for operational use. However, this approach suffers from high training costs, a time-consuming and labor-intensive optimization process, and inconsistent optimization results.

[0003] To address these issues, researchers have introduced swarm intelligence algorithms. However, in these complex systems, traditional swarm intelligence algorithms, such as genetic algorithms (GAs), whale optimization algorithms (WOA), and gray wolf optimization algorithms (GWO), suffer from slow convergence, susceptibility to local optimality, and inability to integrate expert experience. Summary of the Invention

[0004] The present application provides a method, device and equipment for determining parameters of a complex system, which can improve the speed of parameter optimization based on the integration of expert experience.

[0005] This application provides a method for determining parameters of a complex system, including: Obtaining parameters to be optimized and fitness functions corresponding to the parameters to be optimized, wherein the parameters to be optimized are parameters of a complex system; Initializing the vines in the vine population, determining initial values ​​of parameters to be optimized, and determining the initial values ​​of the parameters to be optimized as initial iterative values ​​of the optimal position; Determine a gravity line in the solution space of the parameter to be optimized based on expert experience, where the gravity line is a line connecting the position of the parameter to be optimized in the solution space determined based on expert experience and the midpoint of the solution space; Iteration is performed according to the gravity line, the initial iteration value of the optimal position, and the fitness function, and the iteration is completed when the iteration stop condition is met to obtain the target optimal position, and the target optimal position is determined as the target value of the parameter to be optimized.

[0006] In one embodiment of the present application, initializing vines in a vine population includes: Initialize the chaotic map for each vine in the vine population.

[0007] In one embodiment of the present application, iterating according to the gravity line, the initial iteration value of the optimal position, and the fitness function includes: Determining a first number of vines and a second number of vines in a current iteration based on a current iteration number, a total number of iterations, and a number of vines; wherein the first number of vines is the number of vines to be explored in the vine population, and the second number of vines is the number of vines to be developed in the vine population; Based on the fitness function and the optimal position, determining an updated position of the exploration vines; the exploration vines are the first number of vines in the vine population; Determining an update position of a development vine, wherein the development vine is the second last vine number of vines in the vine population; Based on the renewal position of the exploratory vines, the renewal position of the development vines, and the gravity line, the renewal position of each vine in the vine population after it droops is determined; The optimal position is updated based on the original position of the vine, the updated position of the exploratory vine, the updated position of the development vine, and the updated position after the vine droops.

[0008] In one embodiment of the present application, determining the first number of vines and the second number of vines in the current iteration process based on the current iteration number, the total number of iterations, and the number of vines includes: determining a first iteration factor based on the total number of iterations and the current iteration number; determining the first number of vines based on the first iteration factor; Based on the number of vines and the first number of vines, the second number of vines is determined.

[0009] In one embodiment of the present application, determining an updated position of the vine to be explored based on the fitness function and the optimal position includes: determining a second iteration factor based on the total number of iterations and the current iteration number; Determining a first position of the vine to be explored based on the second iteration factor, the current iteration position, and the previous iteration position; Determining a first value based on the fitness function and a current iteration position, and determining a second value based on the fitness function and the first position; When the first value is greater than or equal to the second value, determining an updated position of the exploration vine according to the optimal position, the random matrix, and the current iteration position; When the first value is less than the second value, the first position is determined as the updated position of the exploration vine.

[0010] In one embodiment of the present application, determining the update location of the development vine includes: determining a control parameter according to the first iteration factor; When the control parameter is greater than a first preset value, developing a leaf line based on the optimal position and the current iterative position to obtain an updated position of the developed vine; When the control parameter is less than or equal to the first preset value, a heart-shaped line development is performed based on the optimal position and the current iterative position to obtain an updated position of the developed vine.

[0011] In one embodiment of the present application, updating the optimal position based on the original position of the vine, the updated position of the explored vine, the updated position of the developed vine, and the updated position of the vine after it droops includes: Determining an iterative update position based on the original position of the vine, the updated position of the exploratory vine, the updated position of the development vine, and the updated position of the vine after it droops; Determine the competition center position based on the iteratively updated position of each vine; The optimal position is updated according to the competition center position and the optimal position of the current iteration.

[0012] In one embodiment of the present application, the iteration stopping condition includes that the current iteration number reaches the total number of iterations.

[0013] To achieve the above-mentioned and other related purposes, the present application provides a complex system parameter determination device, comprising: A data acquisition module is used to obtain parameters to be optimized and fitness functions corresponding to the parameters to be optimized, wherein the parameters to be optimized are parameters of a complex system; An initialization module, configured to initialize the vines in the vine population, determine initial values ​​of parameters to be optimized, and determine the initial values ​​of the parameters to be optimized as initial iterative values ​​of the optimal position; A gravity line determination module is used to determine a gravity line in the solution space of the parameter to be optimized based on expert experience, where the gravity line is a line connecting the position of the parameter to be optimized in the solution space determined based on expert experience and the midpoint of the solution space; The iteration module is used to iterate according to the gravity line, the initial iteration value of the optimal position, and the fitness function, complete the iteration when the iteration stop condition is met, obtain the target optimal position, and determine the target optimal position as the target value of the parameter to be optimized.

[0014] To achieve the above-mentioned and other related purposes, the present application further provides an electronic device, comprising: one or more processors; a memory for storing program code executable by the processor; The processor is configured to execute the program code to implement the above-mentioned complex system parameter determination method.

[0015] As described above, the method, device, and apparatus for determining complex system parameters provided by this application have the following beneficial effects: The present application discloses a method for determining parameters of a complex system. This method integrates expert experience to set the gravity line for vine growth based on a swarm intelligence algorithm. This method can reduce iteration time when iterating according to the gravity line. The algorithm for simulating vine growth can explore widely on a global scale, while also conducting in-depth searches in local areas, helping to avoid falling into local optimal solutions and increasing the probability of finding a global optimal solution.

[0016] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are incorporated into and constitute a part of the specification, illustrating embodiments consistent with the present application and, together with the specification, serving to explain the principles of the present application. It is obvious that the drawings described below are merely some embodiments of the present application, and a person of ordinary skill in the art can derive other drawings based on these drawings without inventive effort. In the drawings: Figure 1 is a flow chart of a method for determining parameters of a complex system shown in an exemplary embodiment of the present application; Figure 2 is a flow chart of a method for determining parameters of a complex system shown in another exemplary embodiment of the present application; Figure 3 It is a structural block diagram of a complex system parameter determination device shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0018] The following will describe the embodiments of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand the other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for the purpose of illustrating the present application and are not intended to limit the scope of protection of the present application.

[0019] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. Therefore, the illustrations only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0020] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0021] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of a method for determining parameters of a complex system according to an exemplary embodiment of the present application. Figure 1 It can be seen that the complex system parameter determination method may include: Step S110: Obtain the parameters to be optimized and the fitness function corresponding to the parameters to be optimized.

[0022] Among them, the parameters to be optimized are parameters of the complex system.

[0023] In one embodiment of the present application, before a large complex system is put into use, important parameters thereof need to be set. The parameter to be optimized may be an important parameter in the complex system. The fitness function corresponding to the parameter to be optimized may be designed by a designer based on the complex system.

[0024] For example, when the complex system is a compression spring, the goal of compression spring design is to minimize its mass under certain constraints. The mass of the compression spring is also the parameter to be optimized, which includes four inequality constraints: minimum deflection, shear stress, oscillation frequency, and outer diameter limit. The spring wire diameter is , average diameter of spring coil , and the number of effective coils of the spring 3 decision variables, the fitness function includes: ; The constraints that need to be met include: ; ; ; ; Among them, the boundary conditions of each decision variable are .

[0025] For example, when the complex system is a gear system, the goal is to minimize the gear ratio, which is the parameter to be optimized. The gear ratio is defined as the ratio of the output shaft angular velocity to the input shaft angular velocity. 、 、 、 If is determined as a decision variable, the fitness function includes: ; in, .

[0026] For example, if the complex system is a reinforced concrete beam, assume that the span of the reinforced concrete beam is 30 ft and it bears a live load of 2000 lbf and a dead load of 1000 lbf, including the weight of the beam. The compressive strength of the concrete is 5 ksi and the yield stress of the steel is 50 ksi. The cost of concrete is $0.02 / in2 / linearft and the cost of steel is $1.0 / in2 / linearft. $0.02 / in2 / linearft means that the unit cost per square inch per linear foot is $0.02. To minimize the total cost of the structure, determine the area of ​​the steel reinforcement. , beam width and the depth of the beam The three decision variables are the depth-to-width ratio of the beam, which is limited to be less than or equal to 4, and the total cost of the reinforced concrete beam as the parameter to be optimized. The fitness function includes: ; The constraints that need to be met include: ; ; in, .

[0027] It should be noted that, in the above embodiment, represents the fitness function, represents any value of the parameter to be optimized, 、 、 、 They represent the decision variables of the parameters to be optimized. 、 、 、 Represents the constraints respectively. When any constraint is not satisfied, the fitness function Will be set to a very large value.

[0028] It should be noted that the complex system parameter determination method provided in the embodiment of the present application can be implemented by devices such as a server or a server cluster.

[0029] Step S120 , initializing the vines in the vine population, determining initial values ​​of the parameters to be optimized, and determining the initial values ​​of the parameters to be optimized as initial iterative values ​​of the optimal position.

[0030] In one embodiment of the present application, a chaotic mapping can be initialized for each vine in a vine population to determine the initial value of the parameter to be optimized. This chaotic mapping initialization allows each vine's initial position to be distributed around the solution space. The number of vines in the vine population and the total number of iterations, pre-set by the designer, can be obtained; these two metrics can be used to balance optimization time and accuracy. The position of each vine in the vine population represents the possible values ​​of the parameter to be optimized.

[0031] For example, chaos mapping initialization can be performed three times on each vine individual in the vine population.

[0032] (1) (2) in, is the position matrix of the vine population, is the number of vines, It is The location of the vines, It is The first vine decision variables, is the number of decision variables. It is The lower bound of the decision variable, It is The upper bound of the decision variables, and To set the solution space, Indicates the initialization of the chaotic map.

[0033] Step S130 : determining a gravity line in the solution space of the parameter to be optimized based on expert experience, wherein the gravity line is a line connecting the position of the parameter to be optimized in the solution space determined based on expert experience and the midpoint of the solution space.

[0034] In one embodiment of the present application, a gravity line can be determined in the solution space of the parameter to be optimized based on expert experience. The gravity line is a line connecting the position of the parameter to be optimized in the solution space determined based on expert experience and the midpoint of the solution space.

[0035] In a possible implementation, the center point of the solution space may be obtained, an expert experience point may be determined based on expert experience, and a line connecting the center point and the expert experience point may be determined as a gravity line.

[0036] For example, the position of a vine can include three decision variables, x, y, and z. The solution space is [0, 1]. The expert experience point determined by expert experience can be (0.5, 0.5, 1), and the center point of the solution space can be (0.5, 0.5, 0.5). The line connecting the midpoint of the solution space and the expert experience point can be determined as the gravity line. The solution space can be determined by the value range of each decision variable of the parameter to be optimized.

[0037] Step S140 , iterating according to the gravity line, the initial iteration value of the optimal position, and the fitness function, completing the iteration when the iteration stop condition is met, obtaining the target optimal position, and determining the target optimal position as the target value of the parameter to be optimized.

[0038] In one embodiment, the process of iterating according to the gravity line, the initial iteration value of the optimal position, and the fitness function in step S140 may include steps S141 to S145.

[0039] Step S141, based on the current iteration number, the total number of iterations, and the number of vines, determine the first number of vines and the second number of vines in the current iteration process.

[0040] Among them, the first vine number is the number of vines being explored in the vine population, and the second vine number is the number of vines being developed in the vine population.

[0041] In one embodiment of the present application, determining the first number of vines and the second number of vines in the current iteration process based on the current iteration number, the total number of iterations, and the number of vines may include: determining a first iteration factor based on the total number of iterations and the current iteration number; determining the first number of vines based on the first iteration factor; determining the second number of vines based on the number of vines and the first number of vines.

[0042] Exemplarily, the process of determining the first number of vines and the second number of vines in the current iteration may include: (3) (4) in, is the number of first vines, is the second vine number, is the rounding function, is the first iteration factor, is the total number of iterations, is the current iteration number.

[0043] Step S142: Determine the updated position of the exploration vine based on the fitness function and the optimal position; the exploration vines are the first number of vines in the vine population.

[0044] In one embodiment of the present application, determining an updated position of the explored vine based on a fitness function and an optimal position may include: determining a second iteration factor based on the total number of iterations and a current iteration number; determining a first position of the explored vine based on the second iteration factor, the current iteration position, and the previous iteration position; determining a first value based on the fitness function and the current iteration position, and determining a second value based on the fitness function and the first position; determining an updated position of the explored vine based on the optimal position, the random matrix, and the current iteration position when the first value is greater than or equal to the second value; and determining the first position as the updated position of the explored vine when the first value is less than the second value.

[0045] For example, the process of determining the updated position of the vines can characterize the behavior of climbing the host tree, that is, the algorithm exploration phase, the front of the vine population Each vine will perform this behavior, which can include: The vine continues to grow along the direction of growth: (5) (6) Indicates the The vine is iterating The position when , which is also the current iteration position; For the The vine is iterating The position at the time of , which is also the position of the previous iteration; Indicates the The vine is iterating The new position after continued growth along the growth direction is the first position; is the second iteration factor, is a matrix of random numbers between 0 and 1.

[0046] It should be noted that during the first iteration, the "Current Iteration Position" is the position of each individual vine after initialization. After each iteration, this position changes to the updated position. During the second iteration, the "Current Iteration Position" is the updated position of each vine after the first iteration.

[0047] The vines search for new host trees. If it is not better, the vine will perform a random search behavior called Levy Flight to find a new host tree: (7) in, Indicates the optimal position; Indicates that in iteration After searching for a new host tree The new position of the vine, that is, the updated position of the exploration vine; represents the fitness function; is a matrix of random numbers generated by Lévy's flight.

[0048] Step S143: determining the update position of the developed vine.

[0049] Among them, the developed vines are the second largest number of vines in the vine population.

[0050] In one embodiment of the present application, determining the updated position of the development vine may include: determining a control parameter based on a first iteration factor; when the control parameter is greater than a first preset value, performing leaf-shaped line development based on the optimal position and the current iteration position to obtain the updated position of the development vine; when the control parameter is less than or equal to the first preset value, performing heart-shaped line development based on the optimal position and the current iteration position to obtain the updated position of the development vine.

[0051] For example, determining the renewal position of the developing vines can characterize the leaf growth behavior, that is, in the algorithm development stage, the vine population is later A vine will do this: Set the control parameters to control the growth of two leaf forms, including leaf shape and heart shape: (8) in, is a random number between 0 and 1. is the control parameter.

[0052] when When the leaf line is developed and optimized, development is performed at a position with a certain distance from the optimal position to prevent the algorithm from quickly falling into the local optimum.

[0053] when When performing cardioid line development optimization, deep development is performed near the optimal position: (9) (10) (11) (12) (13) (14) (15) in, In iteration After the middle leaves grow The new location of the vine is also the new location of the developed vine; is a matrix of random numbers generated by normal distribution; is the polar coordinate function of the leaf shape; is the cardioid polar function; is the first random angle; is the second random angle; is the third random angle; is the fourth random angle.

[0054] Step S144, based on the updated position of the explored vines, the updated position of the developed vines, and the gravity line, the updated position of each vine in the vine population after drooping is determined.

[0055] Exemplarily, the process of determining the regeneration position of each vine in the vine population after drooping may include: Gravity drooping behavior, which is the stage of integrating expert experience. In S2.3, the gravity line is set through expert experience, and the vine will droop towards the gravity line during growth.

[0056] (16) (17) in, Represents iteration Middle The new position of the vine after it droops, that is, the updated position of the vine after it droops; Indicates the location after the behavior of clinging to the host tree or the behavior of leaf growth; For iteration On the middle gravity line The random decision changes the same position.

[0057] Step S145 , updating the optimal position based on the original position of the vine, the updated position of the explored vine, the updated position of the developed vine, and the updated position of the vine after it droops.

[0058] In one embodiment of the present application, updating the optimal position based on the original position of the vine, the updated position of the explored vine, the updated position of the developed vine, and the updated position of the vine after drooping may include: determining the iterative update position based on the original position of the vine, the updated position of the explored vine, the updated position of the developed vine, and the updated position after drooping of the vine; determining the competition center position based on the iterative update position of each vine; and updating the optimal position based on the competition center position and the optimal position of the current iteration.

[0059] Exemplarily, the process of updating the optimal position may include: Group behavior, namely the position update, group competition and optimal value update stages.

[0060] 1) Position update behavior. The original vine position, the position after clinging to the host tree or leaf growth, and the position after gravity drooping are compared using the fitness function to update the vine position: (18) in, is the iterative update position. After determining the iterative update position, you can Updated to The vine is iterating The current iteration position at the time. That is, the iteration update position determined by the previous iteration update can be determined as the current iteration position corresponding to the current iteration, .

[0061] 2) Group competition behavior. Vine populations will continuously gather towards the center to compete for the best position. Three random vine individuals are selected from the population to simulate this behavior: (19) in, For random Iterative update position of the vine. Competition for central location.

[0062] 3) Compare the optimal value with the competitive center position and update the optimal position: (20) For example, see Figure 2 , which is a flowchart of a method for determining complex system parameters shown in another exemplary embodiment of the present application.

[0063] Figure 3 FIG. 1 is a block diagram of a complex system parameter determination device shown in an exemplary embodiment of the present application. Figure 3 As shown, the exemplary complex system parameter determination device 300 includes: The data acquisition module 310 is used to obtain parameters to be optimized and fitness functions corresponding to the parameters to be optimized, where the parameters to be optimized are parameters of a complex system; Initialization module 320, for initializing the vines in the vine population, determining initial values ​​of the parameters to be optimized, and determining the initial values ​​of the parameters to be optimized as initial iterative values ​​of the optimal position; A gravity line determination module 330 is used to determine a gravity line in the solution space of the parameter to be optimized based on expert experience. The gravity line is a line connecting the position of the parameter to be optimized in the solution space determined based on expert experience and the midpoint of the solution space. The iteration module 340 is used to iterate according to the gravity line, the initial iteration value of the optimal position, and the fitness function, complete the iteration when the iteration stop condition is met, obtain the target optimal position, and determine the target optimal position as the target value of the parameter to be optimized.

[0064] It should be noted that the complex system parameter determination device provided in the above embodiment and the complex system parameter determination method provided in the above embodiment are based on the same concept, and the specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here. In actual applications, the complex system parameter determination device provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the system into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0065] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, which, when executed by one or more processors, enables the electronic device to implement the complex system parameter determination method provided in the above-mentioned embodiments.

[0066] Another aspect of the present application provides a computer-readable storage medium having a computer program stored thereon. When executed by a computer processor, the computer program causes the computer to perform the complex system parameter determination method provided in each of the above embodiments. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist independently and not be incorporated into the electronic device.

[0067] Another aspect of the present application provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the complex system parameter determination method provided in each of the above embodiments.

[0068] In the embodiments of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance. Throughout the specification and claims, the terms "including" and "comprising" are open-ended terms and should be interpreted as "including but not limited to."

[0069] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, any equivalent modifications or alterations accomplished by a person of ordinary skill in the art without departing from the spirit and technical concepts disclosed in this application shall be covered by the claims of this application.

Claims

1. A method for determining parameters of a complex system, characterized in that: include: Obtaining parameters to be optimized and fitness functions corresponding to the parameters to be optimized, wherein the parameters to be optimized are parameters of a complex system; Initializing the vines in the vine population, determining the initial values ​​of the parameters to be optimized, and determining the initial values ​​of the parameters to be optimized as the initial iteration values ​​of the optimal position; Determine a gravity line in the solution space of the parameter to be optimized based on expert experience, wherein the gravity line is a line connecting the position of the parameter to be optimized in the solution space determined based on expert experience and the middle point of the solution space; Iteration is performed according to the gravity line, the initial iteration value of the optimal position, and the fitness function, and the iteration is completed when the iteration stop condition is met to obtain the target optimal position, and the target optimal position is determined as the target value of the parameter to be optimized.

2. The method for determining complex system parameters according to claim 1, characterized in that: Initialize the vines in the vine population, including: Initialize the chaotic map for each vine in the vine population.

3. The method for determining complex system parameters according to claim 1, characterized in that: Iterating according to the gravity line, the initial iteration value of the optimal position, and the fitness function, including: Determine a first vine number and a second vine number in a current iteration process based on a current iteration number, a total number of iterations, and a number of vines; the first vine number is the number of vines to be explored in the vine population, and the second vine number is the number of vines to be developed in the vine population; Based on the fitness function and the optimal position, determining an update position of the exploration vines; the exploration vines are the first number of vines in the vine population; Determining an update position of a development vine, wherein the development vine is a vine having a second number of vines in the vine population; Based on the renewal position of the exploration vine, the renewal position of the development vine, and the gravity line, the renewal position of each vine in the vine population after drooping is determined; The optimal position is updated based on the original position of the vine, the updated position of the explored vine, the updated position of the developed vine, and the updated position after the vine droops.

4. The method for determining complex system parameters according to claim 3, characterized in that: Based on the current iteration number, the total number of iterations, and the number of vines, determining the first number of vines and the second number of vines in the current iteration process includes: determining a first iteration factor based on the total number of iterations and the current number of iterations; determining the first number of vines based on the first iteration factor; Based on the number of vines and the first number of vines, the second number of vines is determined.

5. The complex system parameter determination method according to claim 3, characterized in that: Based on the fitness function and the optimal position, determining an updated position of the explored vine includes: determining a second iteration factor based on the total number of iterations and the current number of iterations; Determine a first position of the vine to be explored based on the second iteration factor, the current iteration position, and the previous iteration position; Determine a first value based on the fitness function and a current iteration position, and determine a second value based on the fitness function and the first position; When the first value is greater than or equal to the second value, determining an updated position of the exploration vine according to the optimal position, the random matrix, and the current iteration position; When the first value is less than the second value, the first position is determined as the updated position of the exploration vine.

6. The method for determining parameters of a complex system according to claim 4, characterized in that: Identify new locations for developing vines, including: Determining a control parameter according to the first iteration factor; When the control parameter is greater than a first preset value, developing a leaf shape line based on the optimal position and the current iteration position to obtain an updated position of the developed vine; When the control parameter is less than or equal to the first preset value, a heart-shaped line development is performed based on the optimal position and the current iteration position to obtain an updated position of the developed vine.

7. The method for determining parameters of a complex system according to claim 3, characterized in that: Based on the original position of the vine, the updated position of the vine after exploration, the updated position of the vine after development, and the updated position after the vine droops, the optimal position is updated, including: Determining an iterative update position based on an original position of the vine, an updated position of the exploratory vine, an updated position of the exploitative vine, and an updated position after the vine droops; Determine the competition center position based on the iteratively updated position of each vine; The optimal position is updated according to the competition center position and the optimal position of the current iteration.

8. The complex system parameter determination method according to claim 1, characterized in that: The iteration stopping condition includes that the current iteration number reaches the total number of iterations.

9. A complex system parameter determination device, characterized in that: include: A data acquisition module, used to acquire parameters to be optimized and fitness functions corresponding to the parameters to be optimized, wherein the parameters to be optimized are parameters of a complex system; An initialization module, used to initialize the vines in the vine population, determine the initial values ​​of the parameters to be optimized, and determine the initial values ​​of the parameters to be optimized as the initial iteration values ​​of the optimal position; A gravity line determination module, used to determine a gravity line in the solution space of the parameter to be optimized based on expert experience, wherein the gravity line is a line connecting the position of the parameter to be optimized in the solution space determined based on expert experience and the middle point of the solution space; The iteration module is used to iterate according to the gravity line, the initial iteration value of the optimal position, and the fitness function, complete the iteration when the iteration stop condition is met, obtain the target optimal position, and determine the target optimal position as the target value of the parameter to be optimized.

10. An electronic device, characterized in that: The electronic device comprises: one or more processors; a memory for storing program code executable by the processor; The processor is configured to execute the program code to implement the complex system parameter determination method according to any one of claims 1 to 8.

Images