An optimization method and system based on adaptive design of experiments and design space compression

Abstract

The application discloses an optimization method and system based on adaptive test design and design space compression, which firstly sets an initial design optimization target and a design region, sets corresponding optimization termination conditions, generates a plurality of test points based on the current design region to form a corresponding test point set. Then, test analysis is carried out on the generated test points, the optimal point in the current test point set is searched, and based on the current design region, the existing test points are adaptively generated to continue generating new test points to form a new test point set. Finally, test analysis is carried out on the test points in the newly generated test point set, new test points are searched, and it is judged whether the searched new optimal point is better than the last optimal point. If yes, the design region is rearranged based on the new optimal point; if no, the current design region is compressed. Finally, it is judged whether the set optimization termination conditions are met, so as to judge whether to continue optimization.

Description

Technical Field

[0001] This invention relates to the field of algorithm optimization, specifically to an optimization method and system based on adaptive experimental design and design space compression. Background Technology

[0002] Optimization algorithms are key technologies for finding optimal solutions to various engineering and scientific research problems. With the development of science and technology, new optimization algorithms are constantly emerging to address more complex and challenging problems. Currently, optimization algorithms play an important role in signal processing, image processing, production scheduling, task allocation, pattern recognition, automatic control, and mechanical design. They can improve system efficiency, reduce energy consumption, and make rational use of resources, and their optimization effects become more pronounced as the scale of the processed objects increases.

[0003] Traditional optimization methods, such as Newton's method and the simplex method, often fail to complete the search quickly enough when faced with large optimization problems because they require traversing the entire search space, leading to a "combinatorial explosion" of the search results. Therefore, inspired by biological evolution mechanisms, social dynamics, and the laws governing natural phenomena, many intelligent optimization algorithms have been invented.

[0004] Intelligent optimization algorithms include genetic algorithms, differential evolution algorithms, immune algorithms, ant colony optimization, particle swarm optimization, simulated annealing, tabu search, and neural network algorithms. These algorithms are developed by simulating natural phenomena and processes or the intelligent behavior of biological groups, and are characterized by simplicity, versatility, and ease of parallel processing.

[0005] Currently, optimization algorithms are widely used in various fields such as resource scheduling, logistics and distribution, financial market analysis, smart city management, machine learning, and cybersecurity. For example, in power systems, optimization algorithms can be used for load allocation and electricity demand forecasting in smart grids; in logistics, they can be used for route planning and load optimization; in financial markets, they can be used to build quantitative trading models; and in cybersecurity, they can be used in intrusion detection systems, and so on. Future research on optimization algorithms may move towards more efficient training methods, improved model interpretability, exploration of novel network structures, and integration with other machine learning methods.

[0006] However, in the field of engineering design, when applying optimization algorithms, the mathematical conditions of the problem are not actually sensitive. That is, it cannot be limited to linear and nonlinear problems, differentiability or gradient calculation is not required, continuity is not required, etc. This requires a certain degree of universality for the optimization problem, and requires optimization algorithms that involve black-box optimization problems. Summary of the Invention

[0007] The following provides a brief overview of one or more aspects to offer a basic understanding of them. This overview is not an exhaustive summary of all conceived aspects, nor is it intended to identify key or decisive elements of all aspects, nor to define the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form to prepare for the more detailed descriptions that follow.

[0008] The purpose of this invention is to solve the above-mentioned problems and provide an optimization system and method based on adaptive experimental design and design space compression. This system and method can adapt to black-box optimization problems, has a certain degree of universality for optimization problems, is not limited to linear and nonlinear problems, and does not require differentiability or gradient calculation, nor does it require continuity.

[0009] The technical solution of this invention is as follows:

[0010] This invention provides an optimization method based on adaptive experimental design and design space compression, comprising the following steps:

[0011] Step S1: Set the initial design optimization target and design region, and set the corresponding optimization termination conditions, including the number of iterations and the minimum compression space resolution;

[0012] Step S2: Generate multiple test points based on the current design area to form a corresponding test point set;

[0013] Step S3: Perform experimental analysis on the generated test points, and search for the optimal point in the current test point set according to the set design optimization objective;

[0014] Step S4: Based on the current design area, adaptively generate new test points from existing test points to form a new set of test points;

[0015] Step S5: Perform experimental analysis on the experimental points in the newly generated experimental point set and search for new experimental points;

[0016] Step S6: Determine whether the new optimal point found is better than the previous optimal point; if so, rearrange the design area based on the new optimal point; if not, compress the current design area.

[0017] Step S7: Determine whether the set optimization termination condition is met; if yes, return the currently found optimal point as the optimal solution; if no, repeat steps S4 to S6 to continue the optimization search until the set optimization termination condition is met.

[0018] According to an embodiment of the optimization method based on adaptive experimental design and design space compression of the present invention, in step S1, the optimization method based on adaptive experimental design and design space compression, when setting the initial design optimization target and design region, also sets the number of test points generated in each iteration and the space compression coefficient. The optimization method based on adaptive experimental design and design space compression generates a new set of test points and design region according to the set number of test points generated in each iteration and the space compression coefficient, thereby performing subsequent iterative optimization.

[0019] According to an embodiment of the optimization method based on adaptive experimental design and design space compression of the present invention, in step S2, the optimization method based on adaptive experimental design and design space compression uses an experimental design algorithm based on uniform space filling class to generate test points, thereby obtaining a uniformly distributed set of test points first.

[0020] According to an embodiment of the optimization method based on adaptive experimental design and design space compression of the present invention, in step S4, when the optimization method based on adaptive experimental design and design space compression uses an experimental design algorithm based on uniform space filling class to generate new experimental points, it adaptively generates new experimental points that are more likely to be far away from existing experimental points and uniformly, thereby forming a new set of experimental points.

[0021] According to an embodiment of the optimization method based on adaptive experimental design and design space compression of the present invention, in step S5, if the new optimal point is better than the previous optimal point, then the design area is rearranged based on the previous design area size with the new optimal point as the center for subsequent iterative optimization.

[0022] According to an embodiment of the optimization method based on adaptive experimental design and design space compression of the present invention, in step S5, if the new optimal point found is not as good as the previous optimal point, then the design area size of the previous design is compressed according to the set space compression coefficient to obtain the compressed design area of ​​the previous design for subsequent iterative optimization.

[0023] This invention also provides an optimization system based on adaptive experimental design and design space compression, comprising: an optimization initial setting module, an experimental point generation module, a region setting module, and a result feedback module; wherein,

[0024] The initial setup module is used to set the initial design optimization goals and design region, and to set the corresponding optimization termination conditions, including the number of iterations and the minimum compression space resolution.

[0025] The test point generation module is used to generate multiple test points based on the current design area, forming a corresponding test point set;

[0026] The test analysis module is used to perform test analysis on the test points generated by the test point generation module, and to search for the optimal point in the current test point set according to the set design optimization objectives;

[0027] The region setting module is used to adjust the current design region based on the comparison between the current searched optimal point and the previous optimal point, and then transmit the adjusted design region to the test point generation module.

[0028] The results feedback module is used to return the found optimal point as the optimal solution after the set optimization termination conditions are met.

[0029] According to an embodiment of the optimization system based on adaptive experimental design and design space compression of the present invention, the initial optimization setting module, when setting the initial design optimization target and design region, also sets the number of test points generated in each iteration and the space compression coefficient. Based on the set number of test points generated in each iteration and the space compression coefficient, a new set of test points and design region compression are generated, thereby performing subsequent iterative optimization.

[0030] According to an embodiment of the optimization system based on adaptive experimental design and design space compression of the present invention, the test point generation module uses an experimental design algorithm based on uniform space filling to generate test points, thereby obtaining a uniformly distributed set of test points.

[0031] According to an embodiment of the optimization system based on adaptive experimental design and design space compression of the present invention, when the experimental point generation module uses an experimental design algorithm based on uniform space filling to generate new experimental points, it adaptively generates new experimental points that are more likely to be far away from existing experimental points and uniformly, thereby forming a new set of experimental points.

[0032] According to an embodiment of the optimization system based on adaptive experimental design and design space compression of the present invention, if the new optimal point found by the experimental analysis module is better than the previous optimal point, the region setting module rearranges the region based on the previous design region size with the new optimal point as the center, so as to perform subsequent iterative optimization.

[0033] According to an embodiment of the optimization system based on adaptive experimental design and design space compression of the present invention, if the new optimal point searched by the experimental analysis module is not as good as the previous optimal point, the region setting module compresses the previous design region size according to the set space compression coefficient, thereby obtaining the compressed previous design region for subsequent iterative optimization.

[0034] The present invention also provides a computer-readable medium storing computer program code that, when executed by a processor, implements the method described above.

[0035] The present invention also provides an optimization device based on adaptive experimental design and design space compression, comprising:

[0036] Memory, used to store instructions that can be executed by a processor; and

[0037] A processor for executing the instructions to implement the method described above.

[0038] Compared with existing technologies, this invention offers the following advantages: Addressing optimization problems in engineering design, this invention eliminates the need for an optimization system and method based on adaptive experimental design and design space compression. It is not limited by the mathematical conditions of the optimization problem and can search for the optimal solution. Through this invention, optimization algorithms suitable for black-box optimization problems can be adapted, allowing the search for the optimal solution regardless of whether the problem is linear or nonlinear, differentiable or gradient-calculated, or whether continuity is required, thus satisfying the optimization needs of high-dimensional, global problems. Attached Figure Description

[0039] The above-described features and advantages of the present invention will be better understood after reading the following detailed description of embodiments of the present disclosure in conjunction with the accompanying drawings. In the drawings, components are not necessarily drawn to scale, and components having similar related characteristics or features may have the same or similar reference numerals.

[0040] Figure 1 This is a flowchart illustrating an embodiment of the optimization method based on adaptive experimental design and design space compression of the present invention.

[0041] Figure 2 This is a system architecture diagram illustrating an embodiment of the optimization system based on adaptive experimental design and design space compression of the present invention. Detailed Implementation

[0042] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this application. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0043] As indicated in this application and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" are not specifically singular and may include plural forms. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0044] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of this application. It should also be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn to actual scale. Techniques, methods, and devices known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be considered part of the specification. In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values. It should be noted that similar reference numerals and letters in the following drawings denote similar items; therefore, once an item is defined in one drawing, it need not be further discussed in subsequent drawings.

[0045] In detailing the embodiments of the present invention, for ease of explanation, the cross-sectional views illustrating the device structure will be partially enlarged and not to scale. Furthermore, the schematic diagrams are merely examples and should not limit the scope of protection of the present invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0046] In the description of this application, it should be understood that the orientation or positional relationship indicated by directional terms such as "front, back, up, down, left, right", "horizontal, vertical, horizontal" and "top, bottom" is usually based on the orientation or positional relationship shown in the accompanying drawings, and is only for the convenience of describing this application and simplifying the description. Unless otherwise stated, these directional terms do not indicate or imply that the device or element referred to must have a specific orientation or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the scope of protection of this application; the directional terms "inner" and "outer" refer to the inner and outer contours relative to the outline of each component itself.

[0047] An embodiment of an optimization method based on adaptive experimental design and design space compression is disclosed herein. Figure 1 This is a flowchart illustrating an embodiment of the optimization method based on adaptive experimental design and design space compression according to the present invention. Please refer to... Figure 1 The following is a detailed explanation of each step in the optimization method based on adaptive experimental design and design space compression.

[0048] Step S1: Set the initial design optimization target and design region, and set the corresponding optimization termination conditions, including the number of iterations and the minimum compressed space resolution.

[0049] In this embodiment, when setting the initial design optimization target and design region, the number of test points N and the spatial compression coefficient ρ for each iteration are also set. The minimum compressed spatial resolution ρ refers to the point at which optimization stops when the optimized design region is compressed to a certain ratio (i.e., the current optimized region size / the initial design region size). During test point generation, a new set of test points is generated based on the set number N for each iteration, and the corresponding design region is arranged for subsequent iterative optimization.

[0050] Step S2: Generate multiple test points based on the current design area to form a corresponding test point set.

[0051] Step S3: Perform experimental analysis on the generated test points and search for the optimal point in the current test point set according to the set design optimization objective.

[0052] In this embodiment, the existing set of test points is defined as S, and it is initialized as an empty set: Then, an experimental design algorithm based on uniform space-filling is used to generate experimental points, thereby obtaining a uniformly distributed set of experimental points P. U Among them, the test point set P is generated. U Then, the generated test point set P was tested. U Experimental analysis was conducted at the test points, and the optimal point at the current test point was found and recorded as x based on the set design optimization objective. best .

[0053] Step S4: Based on the current design area, adaptively generate new test points from existing test points to form a new set of test points.

[0054] In this embodiment, after completing the previous step S3, based on the current design region A... d We will continue to use the experimental design algorithm based on uniform space-filling class to generate a new set of test points P. new During generation, existing test points are adaptively considered, and new test points are generated more evenly and are further away from existing test points.

[0055] Specifically, an experimental design algorithm based on uniform space-filling classes is used to generate n*N. per There are 10 new test points, and then the distance of each new test point from the existing point set P is calculated. U Minimum distance D of the test point min Based on the calculated minimum distance D min Select the point with the largest minimum distance, and then sequentially pick out points from the newly generated test points that are closest to the existing test point set P. U Add points that are as far away as possible to the test point set until the current number of new points in the set reaches N. per A new test point set P is obtained.new .

[0056] Step S5: Perform experimental analysis on the experimental points in the newly generated experimental point set and search for new experimental points.

[0057] Step S6: Determine whether the new optimal point found is better than the previous optimal point; if so, rearrange the design area based on the new optimal point; if not, compress the current design area.

[0058] In this embodiment, a new test point set P is generated through the above steps. new Then, for the test point set P new We analyze each test point in the dataset to find the test point set P. new The best point Then the best point With the optimal point x best Compare them. Where, if... Compared to x best If it is better, that is, closer to the design optimization goal, then update the optimal point. And rearrange the design area around that point. If It's better to x best For an even better approach, the current design area is compressed using a compression factor δ. Taking a two-dimensional rectangular area as an example, using the current x... best The length and width of the rectangular area are compressed to δ times the original (e.g., 0.9) for spatial compression, and then the compressed design area is used for subsequent iterative optimization.

[0059] Step S7: Determine whether the set optimization termination condition is met; if yes, return the currently found optimal point as the optimal solution; if no, repeat steps S4 to S6 to continue the optimization search until the set optimization termination condition is met.

[0060] In this embodiment, after each iteration of optimization, it is determined whether the optimization termination condition is met, i.e., the set number of iterations has been reached, or the minimum compressed spatial resolution has been reached. If the condition is met, the currently found optimal point is returned as the optimal solution. If the condition is not met, steps S4 to S6 are repeated to continue optimization until the set optimization termination condition is met.

[0061] This specification also provides an optimization system based on adaptive experimental design and design space compression. Figure 2 This is a system architecture diagram illustrating an embodiment of the optimization system based on adaptive experimental design and design space compression of the present invention. Figure 2As shown in the figure, in this embodiment, the optimization system based on adaptive experimental design and design space compression includes an initial optimization setting module, an experimental point generation module, a region setting module, and a result feedback module. The initial optimization setting module is used to set the initial design optimization objective and design region, and to set corresponding optimization termination conditions, including the number of iterations and the minimum compression space resolution. The experimental point generation module generates multiple experimental points based on the current design region, forming a corresponding experimental point set. The experimental analysis module performs experimental analysis on the experimental points generated by the experimental point generation module, searching for the optimal point in the current experimental point set according to the set design optimization objective. The region setting module adjusts the current design region based on the comparison between the currently found optimal point and the previous optimal point, and transmits the adjusted design region to the experimental point generation module. The result feedback module returns the found optimal point as the optimal solution after the set optimization termination conditions are met.

[0062] Specifically, in this embodiment, the initial optimization module sets the number of test points N and the spatial compression coefficient ρ for each iteration when setting the initial design optimization target and design region. The minimum compressed spatial resolution ρ refers to the point at which optimization stops when the optimized design region is compressed to a certain ratio (i.e., the current optimized region size / the initial design region size). During test point generation, a new set of test points is generated based on the set number N for each iteration, and the corresponding design region is arranged for subsequent iterative optimization.

[0063] Before generating test points, the test point generation module needs to define an existing test point set S and initialize it as an empty set: Then, an experimental design algorithm based on uniform space-filling is used to generate experimental points, thereby obtaining a uniformly distributed set of experimental points P. U Among them, the test point set P is generated. U Then, the generated test point set P was tested. U Experimental analysis was conducted at the test points, and the optimal point at the current test point was found and recorded as x based on the set design optimization objective. best .

[0064] Furthermore, in this embodiment, after generating the existing set of test points, the test point generation module also generates test points based on the current design region A. d We will continue to use the experimental design algorithm based on uniform space-filling class to generate a new set of test points P. new During generation, existing test points are adaptively considered, and new test points are generated more evenly and are further away from existing test points.

[0065] Specifically, the test point generation module uses an experimental design algorithm based on uniform space filling to generate n*N test points.per There are 10 new test points, and then the distance of each new test point from the existing point set P is calculated. U Minimum distance D of the test point min Based on the calculated minimum distance D min Select the point with the largest minimum distance, and then sequentially pick out points from the newly generated test points that are closest to the existing test point set P. U Add points that are as far away as possible to the test point set until the current number of new points in the set reaches N. per A new test point set P is obtained. new .

[0066] In this embodiment, the test point generation module generates a new test point set P. new Then, the experimental analysis module begins to analyze the experimental point set P. new The test points in the dataset are analyzed to find the test point set P. new The best point Then the best point With the optimal point x best Compare them. Where, if... Compared to x best If it is better, that is, closer to the design optimization goal, then update the optimal point. And rearrange the design area around that point. If It's better to x best For an even better approach, the current design area is compressed using a compression factor δ. Taking a two-dimensional rectangular area as an example, using the current x... best The length and width of the rectangular area are compressed to δ times the original (e.g., 0.9) for spatial compression, and then the compressed design area is used for subsequent iterative optimization.

[0067] In this embodiment, after each iteration of optimization, the result feedback module determines whether the optimization termination condition is met, i.e., the set number of iterations or the minimum compressed spatial resolution is reached. If the condition is met, the currently found optimal point is returned as the optimal solution. If the condition is not met, the optimization continues until the set optimization termination condition is met.

[0068] This specification also provides a computer-readable medium storing computer program code that, when executed by a processor, implements the optimization method based on adaptive experimental design and design space compression as described above.

[0069] This specification also provides an optimization method based on adaptive experimental design and design space compression, including a processor-executable instruction memory and a processor for executing instructions in the instruction memory to implement the optimization method based on adaptive experimental design and design space compression as described above.

[0070] The prior description of this disclosure is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to this disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not intended to be limited to the examples and designs described herein, but should be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0071] Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps are described above in a generalized manner in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in different ways for each specific application, but such implementation decisions should not be construed as departing from the scope of the invention.

[0072] The various illustrative logic blocks, modules, and circuits described in conjunction with the embodiments disclosed herein can be implemented or performed using a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. The general-purpose processor may be a microprocessor, but in alternatives, it may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors cooperating with a DSP core, or any other such configuration.

[0073] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of both. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor such that the processor can read and write information to / from the storage medium. In an alternative, the storage medium may be integrated into the processor. The processor and storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In an alternative, the processor and storage medium may reside as discrete components in the user terminal.

[0074] In one or more exemplary embodiments, the described functionality may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software as a computer program product, the functionality may be stored or transmitted as one or more instructions or code on or through a computer-readable medium. A computer-readable medium includes both computer storage media and communication media, encompassing any medium that facilitates the transfer of a computer program from one location to another. A storage medium may be any available medium accessible to a computer. By way of example and not limitation, such a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disc storage, disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and is accessible to a computer. Any connection is also legitimately referred to as a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of a medium. As used in this article, disk and disc include compact discs (CDs), laser discs, optical discs, digital multi-purpose discs (DVDs), floppy disks, and Blu-ray discs. Disks typically reproduce data magnetically, while discs reproduce data optically using lasers. Combinations of these should also be included within the scope of computer-readable media.

Claims

1. An optimization method based on adaptive experimental design and design space compression, characterized in that, Includes the following steps: Step S1: Set the initial design optimization target and design region, and set the corresponding optimization termination conditions, including the number of iterations and the minimum compression space resolution; Step S2: Generate multiple test points based on the current design area to form a corresponding test point set; Step S3: Perform experimental analysis on the generated test points, and search for the optimal point in the current test point set according to the set design optimization objective; Step S4: Based on the current design area, adaptively generate new test points from existing test points to form a new set of test points; Step S5: Perform experimental analysis on the experimental points in the newly generated experimental point set and search for new experimental points; Step S6: Determine whether the new optimal point found is better than the previous optimal point; if so, rearrange the design area based on the new optimal point; if not, compress the current design area. Step S7: Determine whether the set optimization termination condition is met; if yes, return the currently found optimal point as the optimal solution; if no, repeat steps S4 to S6 to continue the optimization search until the set optimization termination condition is met.

2. The optimization method based on adaptive experimental design and design space compression according to claim 1, characterized in that, In step S1, the optimization method based on adaptive experimental design and design space compression sets the number of experimental points and the space compression coefficient for each iteration when setting the initial design optimization target and design region. The optimization method based on adaptive experimental design and design space compression generates a new set of experimental points and design region according to the set number of experimental points and space compression coefficient for each iteration, thereby performing subsequent iterative optimization.

3. The optimization method based on adaptive experimental design and design space compression according to claim 1, characterized in that, In step S2, the optimization method based on adaptive experimental design and design space compression uses an experimental design algorithm based on uniform space filling to generate test points, thereby obtaining a uniformly distributed set of test points.

4. The optimization method based on adaptive experimental design and design space compression according to claim 3, characterized in that, In step S4, when the optimization method based on adaptive experimental design and design space compression uses an experimental design algorithm based on uniform space filling to generate new experimental points, it adaptively generates new experimental points that are more likely to be far away from existing experimental points and uniformly, thereby forming a new set of experimental points.

5. The optimization method based on adaptive experimental design and design space compression according to claim 1, characterized in that, In step S5, if the new optimal point is better than the previous optimal point, then the area is rearranged based on the previous design area size, with the new optimal point as the center, for subsequent iterative optimization.

6. The optimization method based on adaptive experimental design and design space compression according to claim 4, characterized in that, In step S5, if the new optimal point found is not as good as the previous optimal point, then the design area size of the previous design is compressed according to the set spatial compression coefficient to obtain the compressed design area of ​​the previous design for subsequent iterative optimization.

7. An optimization system based on adaptive experimental design and design space compression, characterized in that, include: The initial setup module, test point generation module, region setting module, and result feedback module have been optimized; among them, The initial setup module is used to set the initial design optimization goals and design region, and to set the corresponding optimization termination conditions, including the number of iterations and the minimum compression space resolution. The test point generation module is used to generate multiple test points based on the current design area, forming a corresponding test point set; The test analysis module is used to perform test analysis on the test points generated by the test point generation module, and to search for the optimal point in the current test point set according to the set design optimization objectives; The region setting module is used to adjust the current design region based on the comparison between the current searched optimal point and the previous optimal point, and then transmit the adjusted design region to the test point generation module. The results feedback module is used to return the found optimal point as the optimal solution after the set optimization termination conditions are met.

8. The optimization system based on adaptive experimental design and design space compression according to claim 7, characterized in that, The initial setup optimization module sets the initial design optimization target and design region, as well as the number of test points and spatial compression coefficient for each iteration. Based on the set number of test points and spatial compression coefficient for each iteration, a new set of test points and design region compression are generated, thereby enabling subsequent iterative optimization.

9. The optimization system based on adaptive experimental design and design space compression according to claim 7, characterized in that, The test point generation module uses an experimental design algorithm based on uniform space filling to generate test points, thereby obtaining a uniformly distributed set of test points.

10. The optimization system based on adaptive experimental design and design space compression according to claim 9, characterized in that, When the test point generation module uses a test design algorithm based on uniform space filling to generate new test points, it adapts to existing test points, generates new test points that are more likely to be far away from existing test points, and generates them uniformly, thus forming a new set of test points.

11. The optimization system based on adaptive experimental design and design space compression according to claim 7, characterized in that, If the new optimal point found by the experimental analysis module is better than the previous optimal point, the region setting module will rearrange the region based on the previous design region size, with the new optimal point as the center, for subsequent iterative optimization.

12. The optimization system based on adaptive experimental design and design space compression according to claim 7, characterized in that, If the new optimal point found by the experimental analysis module is not as good as the previous optimal point, the region setting module compresses the previous design region size according to the set spatial compression coefficient to obtain the compressed previous design region for subsequent iterative optimization.

13. A computer-readable medium storing computer program code, characterized in that, The computer program code, when executed by a processor, implements the method as described in any one of claims 1-6.

14. An optimization device based on adaptive experimental design and design space compression, characterized in that, include: Memory is used to store instructions that can be executed by the processor; as well as A processor for executing the instructions to implement the method as described in any one of claims 1-6.

Images