Rigidity parameter optimization method and device of vibration isolator

Abstract

The invention provides a rigidity parameter optimization method and device for a vibration isolator, and the method comprises the steps: obtaining data used for representing the working state of a vibrating screen and vibration isolation performance data to form a sample set, and determining an optimization target and a constraint condition; evaluating factor weights of the candidate factors by adopting a Relief algorithm, and determining an optimization factor set according to the factor weights; the candidate factors comprise at least two of rubber hardness, rubber diameter, rubber rod height, rubber pre-pressing amount and initial angle of the vibration isolator; determining an optimization factor combination meeting an optimization target in the optimization factor set by adopting a particle swarm optimization algorithm; and verifying the optimization factor combination and outputting a target parameter. According to the method, the Relief algorithm is utilized to perform importance evaluation and screening on the candidate factors, and the particle swarm optimization algorithm is combined to search the optimal combination in the optimization factor set, so that the technical effect of efficiently determining the optimal solution of the stiffness parameter of the vibration isolator in a complex parameter space is achieved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of vibration control and isolation, and particularly relates to a stiffness parameter optimization method and device of an isolator. BACKGROUND

[0002] The vibrating screen is a large-scale device commonly used in the mining, coal, metallurgy and other industries. The large-scale device will generate strong excitation vibration during operation. If not properly controlled, it will cause noise pollution, structural damage, and vibration transmission to the surrounding plant, which will also cause secondary damage. Therefore, an isolator, commonly a rubber isolator, is installed on the device. The rubber isolator can absorb and block a part of vibration energy through deformation, thereby reducing the transmission of vibration.

[0003] At present, the stiffness parameter of the isolator determines the damping effect in engineering. The main factors affecting the stiffness include the hardness, diameter, height of the rubber, the pre-pressing amount during installation, the initial installation angle and the like. The traditional method is to adjust one by one to approach an acceptable effect, but the following problems exist: due to the non-linear and coupling characteristics, it is difficult to obtain the real "optimal combination" by relying on experience or single variable test. Even if some optimization methods (such as the conventional gradient method) are used, due to the non-linear and multi-peak problems, it is easy to be stuck in a "local optimal solution" rather than the best solution as a whole. SUMMARY

[0004] The application provides a stiffness parameter optimization method and device of an isolator, to at least solve the problems of complex multi-factor coupling, dependence on experience selection, insufficient optimization result precision and easy falling into local optimum in the existing stiffness parameter optimization process of the isolator.

[0005] According to one aspect of the application, a stiffness parameter optimization method of an isolator is provided, comprising: obtaining a sample set formed by vibration screen working state data and isolation performance data, determining an optimization target and a constraint condition; using a Relief algorithm to evaluate the factor weight of the candidate factors, and determining an optimization factor set according to the factor weight; the candidate factors include at least two of the rubber hardness, rubber diameter, rubber rod height, rubber pre-pressing amount and initial angle of the isolator; using a particle swarm optimization algorithm to determine an optimization factor combination meeting the optimization target in the optimization factor set; verifying the optimization factor combination and outputting a target parameter.

[0006] In an embodiment, the importance evaluation of the candidate factors using the Relief algorithm comprises: selecting similar data by comparing the similarity of the samples in the sample set; The factor weight is determined according to the candidate factors and the similar data.

[0007] In an embodiment, the optimization factor set is determined according to the factor weight, including: The optimization factor set is obtained by screening the factor weight according to a preset weight threshold value. The candidate factor that does not reach the threshold value is not included in the optimization factor set.

[0008] In an embodiment, the particle swarm optimization algorithm is used to determine the optimization factor combination that meets the optimization target in the optimization factor set, including: In the initialization process of the particle swarm optimization algorithm, the parameter value in the optimization factor set is encoded by the particle; The initialization process is generated by a random method and an experience combination method within the range defined by the constraint condition, and the boundary bounce or truncation processing is used for the out-of-bound particle.

[0009] According to another aspect of the present application, a stiffness parameter optimization device of an isolator is also provided, including: An optimization target and constraint determination unit is configured to obtain a sample set formed by vibration screen working state data and isolator performance data, and determine an optimization target and a constraint condition; A weight determination unit is configured to evaluate the factor weight of the candidate factor by using a Relief algorithm, and determine an optimization factor set according to the factor weight; the candidate factor includes at least two of rubber hardness, rubber diameter, rubber rod height, rubber pre-pressing amount, and initial angle of the isolator; A particle swarm optimization unit is configured to determine an optimization factor combination that meets the optimization target in the optimization factor set by using a particle swarm optimization algorithm; An output unit is configured to verify the optimization factor combination and output a target parameter.

[0010] In an embodiment, the weight determination unit includes: A similarity comparison module is configured to select similar data by performing similarity comparison on the samples in the sample set; A factor weight module is configured to accumulate the importance of the candidate factors according to the similar data to obtain the factor weight.

[0011] In an embodiment, the weight determination unit further includes: A screening module is configured to screen the factor weight according to a preset weight threshold value to obtain the optimization factor set; A rejection module is configured to reject the candidate factor that does not reach the threshold value from the optimization factor set.

[0012] In an embodiment, the particle swarm optimization unit includes: The initialization module is configured to use particle coding to take values of parameters in the optimization factor set during initialization of the particle swarm optimization algorithm. The out-of-bound processing module is configured to generate particles in the initialization process in a random manner and an empirical combination manner within the range defined by the constraint condition, and to use boundary rebound or truncation processing for particles out of the range.

[0013] The application uses the Relief algorithm to evaluate and screen candidate factors, and combines the particle swarm optimization algorithm to search for an optimal combination in the optimization factor set, thereby achieving the technical effect of efficiently determining an optimal solution of the stiffness parameters of the vibration isolator in a complex parameter space, and significantly improving the scientificity of vibration isolation design and the vibration reduction effect, reducing the test cost and improving the design efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0015] Figure 1 A flowchart of a stiffness parameter optimization method of a vibration isolator is provided in the present application.

[0016] Figure 2 A flowchart of a method of evaluating the importance of candidate factors by using the Relief algorithm in the embodiments of the present application is provided.

[0017] Figure 3 A flowchart of a method of determining an optimization factor set according to the factor weight in the embodiments of the present application is provided.

[0018] Figure 4 A flowchart of a method of determining an optimal factor combination satisfying the optimization target in the optimization factor set by using the particle swarm optimization algorithm in the embodiments of the present application is provided.

[0019] Figure 5 A result schematic diagram of characterizing the weight of each candidate feature by using the Relief method in the present application is provided.

[0020] Figure 6 A schematic diagram of the PSO algorithm in the embodiments of the present application is provided.

[0021] Figure 7 The PSO algorithm gradually converges to an optimal parameter combination close to the global optimum in the embodiments of the present application.

[0022] Figure 8 A schematic diagram of an electronic device physical structure in the embodiments of the present application is provided. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort fall within the protection scope of the present application.

[0024] At present, in engineering, the "stiffness parameter" of a vibration isolator determines the damping effect, and the main factors affecting the stiffness include the hardness, diameter, height of rubber, pre-pressing amount during installation, initial installation angle and the like. The traditional way is to adjust one by one to approach an acceptable effect, but the following problems exist: such nonlinear and coupled characteristics make it difficult to obtain a real "optimal combination" simply by experience or single-variable test. Even if some optimization methods (such as the conventional gradient method) are used, due to the nonlinearity and multi-peak value of the problem, it is easy to be stuck in a "local optimal solution", rather than the best solution as a whole.

[0025] In order to solve the above problems, the present application provides a stiffness parameter optimization method for a vibration isolator, as shown in Figure 1 The method comprises the following steps: S101: obtaining a sample set formed by vibration screen working state data and vibration isolation performance data, and determining an optimization target and a constraint condition; By collecting data (such as vibration acceleration, frequency response) of the running state of the vibration screen under different working conditions and the performance (such as transmissibility, stiffness response) of the vibration isolator, a sample set for describing the relationship between input and output is formed; at the same time, according to the actual application needs, the optimization target (for example, reducing the system amplitude, improving the vibration isolation efficiency or reducing the deviation) and the constraint condition (for example, the material physical property range, the geometric size range, the installation condition) are determined.

[0026] S102: evaluating the factor weight of the candidate factors by using the Relief algorithm, and determining the optimization factor set according to the factor weight; the candidate factors include at least two of the rubber hardness, the rubber diameter, the rubber rod height, the rubber pre-pressing amount and the initial angle of the vibration isolator; The candidate factors (including the rubber hardness, the rubber diameter, the rubber rod height, the rubber pre-pressing amount and the initial angle of the vibration isolator) are input into the Relief algorithm, the importance of each factor is evaluated, the factor weight is calculated, and the weight size reflects the influence degree of the factor on the vibration isolation performance.

[0027] S103: determining the optimization factor combination meeting the optimization target in the optimization factor set by using the particle swarm optimization algorithm; According to the factor weight, a parameter with higher importance is selected to form an optimization factor set to avoid irrelevant factors interfering with the optimization process. In the optimization factor set, a particle swarm optimization algorithm is used for global search and iterative updating to obtain an optimal parameter combination that meets the optimization objective; in the iteration process, the search space is limited by combining the constraint conditions, and the global search and local convergence are balanced.

[0028] S104: verifying the optimization factor combination and outputting the target parameter.

[0029] The obtained optimization factor combination is applied to the isolator model or actual measurement verification to ensure that the parameters can achieve the expected vibration reduction performance under actual working conditions, and the final target parameter is output as the optimization result.

[0030] In an embodiment, as shown in FIG. 1, the importance of the candidate factors is evaluated using the Relief algorithm, including: Figure 2 S201: selecting similar data by comparing the similarity of samples in the sample set; In the sample set, a target sample is selected, and similar and dissimilar neighboring samples to the target sample in the output characteristics (such as stiffness performance or vibration amplitude) are found; S202: accumulating the importance of the candidate factors according to the similar data to obtain the factor weight.

[0031] The difference between the target sample and the similar sample in the input characteristics (rubber hardness, diameter, height, pre-pressing amount, angle) is compared: if the difference is small in the same type of sample and large in the different type of sample, the feature can better distinguish the stiffness performance, and the weight is increased; if the difference is not obvious in the same type and different type of sample, the weight of the feature is low; after iterative accumulation of a large number of samples, the final weight score of each candidate factor is obtained, reflecting the importance of the factor.

[0032] In an embodiment, the optimization factor set is determined according to the factor weight, as shown in FIG. 2, including: Figure 3 S301: screening the factor weight according to a preset weight threshold to obtain the optimization factor set; According to the preset weight threshold, all candidate factors are screened according to the weight size. For factors with a weight greater than or equal to the threshold, they are included in the optimization factor set; candidate factors with a weight less than the threshold are discarded to avoid redundant interference with the optimization process.

[0033] S302: candidate factors that do not reach the threshold are not included in the optimization factor set.

[0034] The final optimization factor set includes a factor combination that most affects the isolation performance, thereby reducing the optimization dimension, improving the calculation efficiency and optimization accuracy. ​​

[0035] In an embodiment, a particle swarm optimization algorithm is used to determine a combination of optimization factors in the optimization factor set that meets the optimization target, as shown in Figure 4 including: S401: In the initialization process of the particle swarm optimization algorithm, the particle coding corresponds to the parameter value in the optimization factor set; Each parameter (such as hardness, diameter, height, pre-pressing amount, angle) in the optimization factor set is mapped to the position vector of the particle, and the parameter value represents the coordinates of the particle; within the range that meets the constraint condition, the initial particle swarm is generated by random value and empirical combination method to ensure the diversity of the initial solution space.

[0036] S402: The initialization process is generated by random and empirical combination methods within the range defined by the constraint condition, and the boundary bounce or truncation processing is used for the particles that exceed the boundary.

[0037] For the particle parameters that exceed the constraint condition in the generation process, the boundary bounce (the value is adjusted back to the boundary range) or truncation (directly truncated to the boundary value) method is used for correction; based on the initialization, the advantages and disadvantages of each particle are calculated according to the fitness function (such as the vibration reduction effect index), the speed and position of the particle are updated, and through the guidance of the individual historical optimal value and the global optimal value of the group, the parameter combination that meets the optimization target is constantly converged.

[0038] The unique algorithm combination of Relief-PSO (Particle Swarm Optimization) plays a core role in this analysis method. The Relief algorithm has strong feature selection ability and can accurately identify key factors that significantly affect the stiffness of the isolator from complex influencing factors, and quantitatively evaluate the influence degree. The PSO algorithm uses efficient global search characteristics to optimize various parameters of the isolator, aiming to find the optimal stiffness configuration scheme under different working conditions.

[0039] The Relief algorithm performs feature selection and quantitative evaluation on the influence of the five key elements, i.e. rubber hardness, rubber diameter, rubber rod height, rubber pre-pressing amount, and initial angle of the isolator, on the stiffness of the isolator. Relief is a feature weight algorithm that evaluates the importance of features by calculating the correlation of each feature with the same label, and assigns different weights to each feature accordingly.

[0040] The present application uses the Relief algorithm to evaluate and select candidate factors, and combines the particle swarm optimization algorithm to search for the optimal combination in the optimization factor set, achieving the technical effect of efficiently determining the optimal solution of the isolator stiffness parameters in a complex parameter space, thereby significantly improving the scientificity of the isolation design and the vibration reduction effect, reducing the test cost and improving the design efficiency.

[0041] Below is a specific embodiment of the present application, assuming there is a sample set and a feature set , where represents the feature dimension of a single sample, corresponding to the category label , . The Relief algorithm defines the difference degree of samples and in the feature as follows: for discrete type features such as classification or attribute:

[0042] For continuous numerical features:

[0043] In the formula, represents the th feature of k , , respectively represent the maximum and minimum values of the feature in the set X .

[0044] The Relief algorithm first randomly extracts a sample from X , then finds the nearest same-class sample and different-class sample, and finally updates the weight of each feature. The calculation expression is as follows:

[0045] If the feature can clearly distinguish the sample category, the difference between the same-class samples should be smaller, while the difference between the different-class samples should be larger. Therefore, the larger the feature weight is, the more prominent the classification ability of the feature is.

[0046] The weight of each candidate feature is represented by the Relief method, as shown in Figure 5 .

[0047] The particle swarm optimization (PSO) simulates bird foraging to solve optimization problems. In the process of random foraging of a bird swarm, if a bird does not know the specific location of food, it will guide its next action according to the position of other members in the group, and eventually the entire bird swarm will gather around the same food location. The particle swarm optimization algorithm regards the potential solution in the optimization problem as a particle, which has position and speed attributes, and can move in the search space according to its own speed and other particle information to find the global optimal position in the search space. The principle of the PSO algorithm is shown in Figure 6 .

[0048] ​Assume that the dimension of the target search space is n , the iteration number is t , the position of the i th particle is , the velocity is , the historical optimal position is , and the global optimal position of the entire particle swarm is , then the velocity and position of the d th optimization target in the next search of the particle are as follows:

[0049]

[0050] In the formula, , r 1, r 2 are random numbers in the interval [0, 1], which are used to increase the randomness of the search process, c 1, c 2 are learning rates, which are used to adjust the influence degree of the own optimal position and the global optimal position of the group on the current velocity. w is the inertia weight, which represents the influence of the velocity of the particle in the last iteration on the current velocity. The value of the original particle swarm algorithm w is 1.

[0051] The spatial search ability of the particle is directly related to its velocity. If the particle velocity is large, the corresponding search step is large, and the particle has strong global exploration ability. Conversely, if the particle velocity is small, the particle has strong local search ability. In order to strengthen the global exploration ability of the population in the early iteration and the local search ability in the later iteration, a linear descending weight strategy is introduced. Assume that w the value range of w min is [ w max ], the maximum iteration number of the particle swarm algorithm is t max , then the value of t in the w th iteration process is as follows:

[0052] In practical applications, the Relief-PSO method combining the Relief algorithm with the PSO algorithm shows significant advantages. After the weight evaluation of the key factors is completed by the Relief algorithm, the PSO algorithm starts the optimization journey of the parameters of the vibration isolator based on the weight results. In the simulation stage, a highly realistic vibration isolator system model of the vibrating screen in the coal preparation plant is constructed, and the rubber hardness, rubber diameter, rubber rod height, rubber pre-pressing amount, and initial angle of the vibration isolator are taken as variable inputs of the model. The PSO algorithm is used to drive the particles to constantly explore in the parameter space, and the speed and position of the particles are updated. In each iteration process, the fitness value corresponding to each particle is calculated according to the target function of the stiffness of the vibration isolator, so as to evaluate the advantages and disadvantages of the stiffness of the vibration isolator under the current parameter combination.

[0053] After a large number of simulation iterations, Figure 7 In order to further verify the reliability of the simulation results, actual engineering tests are carried out. Various high-precision sensors are installed on the vibrating screen equipment in the coal preparation plant to monitor the actual stiffness and vibration response data of the vibration isolator under different working conditions in real time. The collected actual data are analyzed and processed, and compared with the simulation results. In the actual test process, the parameters of the vibration isolator are continuously adjusted to simulate different coal preparation conditions, covering different raw coal properties, vibrating screen operating frequencies, and load strengths.

[0054] Based on the same inventive concept, the embodiments of the present application also provide a stiffness parameter optimization device of a vibration isolator, which can be used to implement the method described in the above embodiments, as described in the following embodiments. Since the principle of solving the problem of the stiffness parameter optimization device of the vibration isolator is similar to that of the stiffness parameter optimization method of the vibration isolator, the implementation of the stiffness parameter optimization device of the vibration isolator can be referred to the implementation of the stiffness parameter optimization method of the vibration isolator, and the repeated parts will not be described herein. The term "unit" or "module" used below can be a combination of software and / or hardware that implements a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware is also possible and is conceived.

[0055] The stiffness parameter optimization device of the vibration isolator provided in the present application comprises: An optimization target and constraint determination unit is configured to obtain a sample set formed by vibration screen working state data and vibration isolation performance data, and determine an optimization target and a constraint condition. The weight determination unit is configured to determine the factor weight of the candidate factors by using a Relief algorithm, and determine the optimization factor set according to the factor weight. The particle swarm optimization unit is configured to determine the optimization factor combination meeting the optimization target in the optimization factor set by using a particle swarm optimization algorithm. The output unit is configured to verify the optimization factor combination and output the target parameter.

[0056] In an embodiment, the weight determination unit comprises: The similarity comparison module is configured to select similar data by performing similarity comparison on the samples in the sample set. The factor weight module is configured to obtain the factor weight by accumulating the importance of the candidate factors according to the similar data.

[0057] In an embodiment, the weight determination unit further comprises: The screening module is configured to screen the factor weight according to the preset weight threshold to obtain the optimization factor set. The elimination module is configured to eliminate the candidate factors not reaching the threshold from the optimization factor set.

[0058] In an embodiment, the particle swarm optimization unit comprises: The initialization module is configured to use the particle code to correspond to the parameter value in the optimization factor set in the initialization process of the particle swarm optimization algorithm. The out-of-bound processing module is configured to generate the particle in the range limited by the constraint condition by using a random method and an experience combination method in the initialization process, and use boundary rebound or truncation processing for the out-of-bound particle.

[0059] The present application determines the optimization factor set by using the Relief algorithm to evaluate and screen the importance of the candidate factors, and searches the optimal combination in the optimization factor set by using the particle swarm optimization algorithm, thereby achieving the technical effect of efficiently determining the optimal solution of the isolator stiffness parameter in the complex parameter space, and significantly improving the scientificity of the isolation design and the vibration reduction effect, reducing the test cost and improving the design efficiency.

[0060] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0061] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device that implements the flow Figure 1 one or more flows and / or blocks Figure 1 one or more flows and / or blocks

[0062] The principles and implementation manners of the present application are described in the specific embodiments. The above embodiments are only used to help understand the method of the present application and its core idea; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manners and application ranges will be changed; in conclusion, the content of the present application should not be understood as a limitation.

[0063] Figure 8 The electronic device entity structure schematic diagram provided by the embodiments of the present application is shown in FIG. 1, which includes a processor 801, a memory 802, and a bus 803. Figure 8

[0064] The processor 801, the memory 802, and the bus 803 complete mutual communication.

[0065] The processor 801 is used to call the computer program in the memory 802, and the processor executes the computer program to implement all steps in the method in the above embodiments, for example, the processor executes the computer program to implement the following steps: S101: Obtain a sample set formed by vibration screen working state data and vibration isolation performance data, determine an optimization target and a constraint condition; S102: Use the Relief algorithm to evaluate the factor weight of the candidate factor, and determine the optimization factor set according to the factor weight; the candidate factor includes at least two of the following: rubber hardness, rubber diameter, rubber rod height, rubber pre-pressing amount, and isolator initial angle; S103: Use the particle swarm optimization algorithm to determine the optimization factor combination in the optimization factor set to meet the optimization target; S104: Verify the optimization factor combination and output the target parameter.

[0066] ​The embodiments of the present application further provide a computer readable storage medium capable of implementing all steps of the method in the above-mentioned embodiments, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement all steps of the method in the above-mentioned embodiments, for example, the steps of: S101: acquiring data for representing working state of a vibrating screen and data for representing isolation performance to form a sample set, and determining an optimization target and a constraint condition; S102: evaluating factor weights of candidate factors by using a Relief algorithm, and determining an optimization factor set according to the factor weights; the candidate factors include at least two of rubber hardness, rubber diameter, rubber rod height, rubber pre-pressing amount, and initial angle of an isolator; S103: determining an optimization factor combination satisfying the optimization target in the optimization factor set by using a particle swarm optimization algorithm; S104: verifying the optimization factor combination and outputting a target parameter.

[0067] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on its differences from other embodiments. In particular, for hardware + program embodiments, since they are basically similar to method embodiments, the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. Although the embodiments in this specification provide the method operation steps as shown in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive means. The order of steps listed in the embodiments is merely one possible execution order among many steps and does not represent the only execution order. In actual device or terminal product execution, the methods can be executed in the order shown in the embodiments or drawings or in parallel (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed data processing environment). The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, product, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitations, the presence of other identical or equivalent elements in the process, method, product, or apparatus that includes said elements is not excluded. For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing the embodiments of this specification, the functions of each module can be implemented in one or more software and / or hardware, or the module implementing the same function can be implemented by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms. This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to produce a machine, such that the instructions, which are executable by the processor of the computer or other programmable data processing device, produce instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0068] Those skilled in the art will appreciate that embodiments of the present specification can be devised for a method, a system, or a computer program product. Accordingly, embodiments of the present specification can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present specification can be in the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk memory, CD-ROM, optical storage medium, etc.) embodying computer usable program code. Each of the various embodiments of the present specification is described in a progressive manner, and reference can be made to other embodiments for the same or similar parts. Each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and reference can be made to the description of the method embodiments. In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the embodiments of the present specification.

[0069] In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. In addition, those skilled in the art can combine and combine the different embodiments or examples described in the present specification and the features of the different embodiments or examples without contradiction. The above is only an embodiment of the embodiments of the present specification and is not intended to limit the embodiments of the present specification. The embodiments of the present specification can have various modifications and changes for those skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the embodiments of the present specification shall be included in the scope of the claims of the embodiments of the present specification.

Claims

1. A method of optimizing a stiffness parameter of an isolator, characterized in that, include: Acquire data to characterize the working state and vibration isolation performance of the vibrating screen, form a sample set based on the working state data and the vibration isolation performance data, and determine the optimization objective and constraints. The constraints are used to limit the effective range of the optimization parameters; The Relief algorithm is used to evaluate the weights of candidate factors, and the set of optimization factors is determined based on the weights. The candidate factors include at least two of the following: rubber hardness, rubber diameter, rubber rod height, rubber preload, and vibration isolator initial angle. The particle swarm optimization algorithm is used to determine the combination of optimization factors that satisfy the optimization objective and meet the constraints from the set of optimization factors; The combination of optimization factors is verified and the target parameters are output.

2. The method of stiffness parameter optimization of an isolator according to claim 1, wherein, The assessment of the importance of candidate factors using the Relief algorithm includes: By comparing the similarity of samples in the sample set, similar data are selected; The weights of the candidate factors are obtained by accumulating their importance based on the similar data.

3. The method of stiffness parameter optimization of an isolator according to claim 1, wherein, The step of determining the set of optimization factors based on the factor weights includes: The set of optimization factors is obtained by filtering the weights of the factors according to a preset weight threshold. Candidate factors that do not reach the threshold are not included in the set of optimization factors.

4. The method of stiffness parameter optimization of an isolator according to claim 1, wherein The step of using particle swarm optimization algorithm to determine the combination of optimization factors in the set of optimization factors that satisfies the optimization objective and meets the constraints includes: During the initialization process of the particle swarm optimization algorithm, particle codes are used to correspond to the parameter values ​​in the set of optimization factors; The initialization process is generated within the range defined by the constraints using a combination of random and empirical methods, and out-of-bounds particles are treated by boundary bounce or truncation.

5. A device for optimizing the stiffness parameters of an isolator, characterized in that it comprises: include: The optimization objective and constraint determination unit is used to acquire data characterizing the working state and vibration isolation performance of the vibrating screen, form a sample set based on the working state data and the vibration isolation performance data, and determine the optimization objective and constraint conditions; the constraint conditions are used to limit the effective range of the optimization parameters. The weight determination unit is used to evaluate the weights of candidate factors using the Relief algorithm and determine the set of optimization factors based on the weights of the factors; the candidate factors include at least two of the following: rubber hardness, rubber diameter, rubber rod height, rubber preload, and vibration isolator initial angle; The particle swarm optimization unit is used to determine, from the set of optimization factors, a combination of optimization factors that satisfies the optimization objective and meets the constraints using the particle swarm optimization algorithm. The output unit is used to verify the combination of optimization factors and output the target parameters.

6. The device for optimizing the stiffness parameters of a vibration isolator according to claim 5, characterized in that, The weight determination unit includes: The similarity comparison module is used to select similar data by comparing the similarity of samples in the sample set; The factor weighting module is used to accumulate the importance of the candidate factors based on the similar data to obtain the factor weights.

7. The stiffness parameter optimization device for a vibration isolator according to claim 5, characterized in that, The weight determination unit further includes: The filtering module is used to filter the factor weights according to a preset weight threshold to obtain the set of optimization factors; The elimination module is used to remove candidate factors that do not reach the threshold from the set of optimization factors.

8. The device for optimizing the stiffness parameters of a vibration isolator according to claim 5, characterized in that, The particle swarm optimization unit includes: An initialization module is used to assign particle codes to the parameter values ​​in the set of optimization factors during the initialization process of the particle swarm optimization algorithm. The out-of-bounds handling module is used to generate the initialization process within the range defined by the constraints using a combination of random and empirical methods, and to perform boundary bounce or truncation processing on particles that exceed the boundaries.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the sampling method for wastewater quality analysis according to any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the sampling method prior to wastewater quality analysis as described in any one of claims 1 to 4.

Images