Energy blocker design method, device and equipment and computer readable storage medium

Abstract

The invention discloses an energy blocker design method, device and equipment and a computer readable storage medium, and belongs to the technical field of oil and gas development. The method comprises the following steps: constructing an initial energy blocker population; based on a pre-trained fitness evaluation model, evaluating the fitness of each energy blocker in the energy blocker population; according to the fitness, performing genetic variation on the energy barrier population to update the energy barrier population, and detecting whether the energy barrier population meets a preset termination condition; if the preset termination condition is not met, returning to execute the step of evaluating the fitness of each energy blocker in the energy blocker population based on a pre-trained fitness evaluation model; and if the preset termination condition is met, taking the energy blocker with the highest fitness as a target energy blocker. According to the invention, the automatic design of the energy barrier structure is realized, the design period is shortened, and the design cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of oil and gas development, and in particular to an energy blocker design method, device, equipment and computer-readable storage medium. Background Art

[0002] In order to exploit unconventional oil and gas more efficiently and energy-efficiently, energy blockers are generally added to constrain electric pulses in underground reservoir gas production operations to prevent the energy of electric pulses from being lost and to increase the impact of electric pulses. Electromagnetic energy blockers have the advantages of compact structure, high efficiency, easy control, and high efficiency, so they have been widely used in the field of unconventional oil and gas development efficiency enhancement.

[0003] At present, the traditional design method is often that designers formulate preliminary design plans, and then improve the design plans through actual tests until they meet the requirements of unconventional oil and gas development.

[0004] However, this design method generally requires multiple field tests and improvements in the process of improving the design scheme to obtain a perfect design scheme. Especially when the improvement direction is wrong, it will further increase the time and cost required for the design of the electromagnetic energy blocker. Summary of the invention

[0005] The main purpose of the present invention is to provide an energy blocker design method, device, equipment and computer-readable storage medium, aiming to solve the technical problem that the repeated trial and error process leads to a long design cycle and high cost when designing an electromagnetic energy blocker.

[0006] To achieve the above object, the present invention provides an energy blocker design method, the method comprising:

[0007] Constructing an initial energy blocker population, wherein the energy blocker population is composed of a plurality of energy blockers of different structures;

[0008] Based on a pre-trained fitness evaluation model, evaluating the fitness of each energy blocker in the energy blocker population, wherein the fitness evaluation model is trained based on a neural network;

[0009] According to the fitness of each energy blocker in the energy blocker population, genetically mutate the energy blocker population to update the energy blocker population, and detect whether the energy blocker population meets a preset termination condition;

[0010] If it is detected that the energy blocker population does not meet the preset termination condition, the process returns to execute: the step of evaluating the fitness of each energy blocker in the energy blocker population based on the pre-trained fitness evaluation model;

[0011] If it is detected that the energy blocker population meets the preset termination condition, the energy blocker with the highest fitness in the energy blocker population that meets the preset termination condition is used as the target energy blocker.

[0012] Optionally, the method further comprises:

[0013] Acquiring structural parameters of the energy blocker to be simulated, wherein the structural parameters represent the structure of the energy blocker;

[0014] Performing simulation tests according to the structural parameters of the energy blocker to be simulated to obtain performance parameters of the energy blocker to be simulated, wherein the performance parameters represent the performance of the energy blocker;

[0015] The structural parameters and performance parameters of the energy blocker to be simulated are used as input parameters of the neural network, and the neural network is iteratively optimized to obtain a trained fitness evaluation model.

[0016] Optionally, the step of constructing an initial energy blocker population comprises:

[0017] Obtain the value range of the preset structural parameters;

[0018] According to the value range, a plurality of energy blockers with different structures are generated to construct an initial energy blocker population.

[0019] Optionally, the step of evaluating the fitness of each energy blocker in the energy blocker population based on a pre-trained fitness evaluation model comprises:

[0020] Inputting the structural parameters of each energy blocker in the energy blocker population into the fitness evaluation model to obtain the performance parameters of each energy blocker in the energy blocker population output by the fitness evaluation model;

[0021] The fitness of each energy blocker in the energy blocker population is determined according to the performance parameters of each energy blocker in the energy blocker population.

[0022] Optionally, the step of performing genetic mutation on the energy blocker population according to the fitness of each energy blocker in the energy blocker population to update the energy blocker population comprises:

[0023] selecting energy blockers in the energy blocker population according to the fitness of each energy blocker in the energy blocker population to obtain a first energy blocker;

[0024] Crossing the structural parameters of the first energy blocker to obtain a second energy blocker;

[0025] Varying the structural parameters of the second energy blocker to obtain a third energy blocker;

[0026] The energy blocker population is updated based on the first energy blocker, the second energy blocker, and the second energy blocker.

[0027] Optionally, the step of updating the energy blocker population according to the first energy blocker, the second energy blocker and the second energy blocker comprises:

[0028] constructing a population of offspring energy blockers according to the first energy blocker, the second energy blocker and the second energy blocker;

[0029] The descendant energy blocker population is used as the latest energy blocker population.

[0030] Optionally, the step of detecting whether the energy blocker population meets a preset termination condition comprises:

[0031] Detecting the highest value of the fitness of each energy blocker in the energy blocker population;

[0032] If the highest value is less than or equal to a preset value, it is determined that the energy blocker population does not meet the preset termination condition;

[0033] If the highest value is greater than a preset value, it is determined that the energy blocker population meets a preset termination condition.

[0034] In addition, to achieve the above-mentioned purpose, the present invention also provides an energy blocker design device, the device comprising:

[0035] An initialization module, used for constructing an initial energy blocker population, wherein the energy blocker population is composed of a plurality of energy blockers of different structures;

[0036] A genetic variation module, used for evaluating the fitness of each energy blocker in the energy blocker population based on a pre-trained fitness evaluation model, wherein the fitness evaluation model is trained based on a neural network; performing genetic variation on the energy blocker population according to the fitness of each energy blocker in the energy blocker population to update the energy blocker population, and detecting whether the energy blocker population meets a preset termination condition; if it is detected that the energy blocker population does not meet the preset termination condition, returning to execute: the step of evaluating the fitness of each energy blocker in the energy blocker population based on the pre-trained fitness evaluation model until the energy blocker population meets the preset termination condition;

[0037] The iterative termination module is used to, if it is detected that the energy blocker population meets the preset termination condition, use the energy blocker with the highest fitness in the energy blocker population that meets the preset termination condition as the target energy blocker.

[0038] In addition, to achieve the above-mentioned purpose, the present invention also provides an energy blocker design device, which includes: a memory, a processor, and an energy blocker design program stored in the memory and executable on the processor, wherein the energy blocker design program is configured to implement the steps of the energy blocker design method described above.

[0039] In addition, to achieve the above objectives, the present invention also provides a computer-readable storage medium, on which an energy blocker design program is stored, and when the energy blocker design program is executed by a processor, the steps of the energy blocker design method described above are implemented.

[0040] The present invention constructs an initial energy blocker population, wherein the energy blocker population is composed of a plurality of energy blockers with different structures; based on a pre-trained fitness evaluation model, the fitness of each energy blocker in the energy blocker population is evaluated, wherein the fitness evaluation model is based on neural network training; according to the fitness of each energy blocker in the energy blocker population, genetic mutation is performed on the energy blocker population to update the energy blocker population, and whether the energy blocker population meets a preset termination condition is detected; if it is detected that the energy blocker population does not meet the preset termination condition, the step of returning to execute: based on the pre-trained fitness evaluation model, the step of evaluating the fitness of each energy blocker in the energy blocker population; if it is detected that the energy blocker population meets the preset termination condition, the energy blocker with the highest fitness in the energy blocker population that meets the preset termination condition is used as the target energy blocker. The present invention uses a neural network to learn the relationship between the structural parameters and performance parameters of the energy blocker, and realizes the fitness evaluation of each energy blocker in the energy blocker population, so that the performance of energy blockers with different structures can be determined without actual measurement. Then, the energy blocker population is genetically mutated according to the fitness of each energy blocker, and the energy blocker population is continuously updated. When the energy blocker population meets the preset termination condition, the energy blocker with the highest fitness is used as the target energy blocker, and the optimal solution of the energy blocker structure is quickly searched for with the help of a genetic algorithm, so as to realize the automatic design of the energy blocker structure, greatly shorten the design cycle, reduce the design cost, and compared with the energy blocker designed by the traditional design method, the target energy blocker finally searched by the method has better performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1It is a schematic diagram of the process of the first embodiment of the energy blocker design method of the present invention;

[0042] Figure 2 A schematic diagram of a process of fitness evaluation according to an embodiment of the present invention;

[0043] Figure 3 A schematic diagram of a genetic variation process according to an embodiment of the present invention;

[0044] Figure 4 A schematic diagram of a module of an energy blocker design device involved in an embodiment of the present invention;

[0045] Figure 5 It is a structural schematic diagram of an energy blocker design device for a hardware operating environment involved in an embodiment of the present invention.

[0046] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0047] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0048] The embodiment of the present invention provides an energy blocker design method, referring to Figure 1 , Figure 1 It is a schematic flow chart of the first embodiment of the energy blocker design method of the present invention.

[0049] In this embodiment, the energy blocker design method includes:

[0050] Step S100: constructing an initial energy blocker population, wherein the energy blocker population is composed of a plurality of energy blockers of different structures;

[0051] In this embodiment, the energy blocker is an electromagnetic energy blocker. Those skilled in the art will know that the electromagnetic energy blocker generally includes a permanent magnet, an electromagnetic coil, a capsule, a discharge unit, an iron core, and an electromagnetic shell, etc., and is used to constrain the energy generated by the energy converter during oil and gas production, block the energy loss in other directions, and concentrate the energy in a specified direction to impact the reservoir, thereby improving the efficiency of oil and gas production and reducing energy consumption. The performance of the energy blocker depends largely on the quality of the structure.

[0052] In this embodiment, the structure of the electromagnetic energy blocker mainly refers to the permanent magnet, the capsule and the electromagnetic coil, and different structures refer to differences in any one or more of the permanent magnet, the capsule or the electromagnetic coil.

[0053] For ease of understanding, in one example, if the height of the permanent magnet of energy blocker A is 10 cm and the height of the permanent magnet of energy blocker B is 9 cm, then energy blocker A and energy blocker B are energy blockers of different structures.

[0054] In another example, if the capsule radius of energy blocker C is 5 cm and the number of electromagnetic coil turns is 10, and the capsule radius of energy blocker D is 8 cm and the number of electromagnetic coil turns is 8, then energy blocker C and energy blocker D are energy blockers of different structures.

[0055] It should be noted that the energy blocker design method proposed in this embodiment is implemented based on a genetic algorithm, which is a computational model of biological evolution that simulates the natural selection and genetics mechanism of Darwin's theory of biological evolution. It is a method for searching for the optimal solution by simulating the natural evolution process.

[0056] The main features of genetic algorithms are that they operate directly on structural objects, without the limitation of derivatives and function continuity; they have inherent implicit parallelism and better global optimization capabilities; they use probabilistic optimization methods, and can automatically obtain and guide the optimization search space without the need for certain rules, and adjust the search direction adaptively. The basic operation process of genetic algorithms generally includes initializing the population, fitness evaluation, selection operation, crossover operation, mutation operation and termination condition judgment.

[0057] This embodiment initializes the population according to the genetic algorithm to construct an initial energy blocker population. There are no energy blockers with exactly the same structure in the population. Starting from the initial energy blocker population, the process of population evolution in the biological world is simulated, and the energy blocker population is updated through continuous genetic mutation until the preset termination condition is met, so as to realize a rapid search for energy blockers of different structures, and then obtain an energy blocker with better performance (that is, the energy blocker with the highest fitness).

[0058] Step S200: evaluating the fitness of each energy blocker in the energy blocker population based on a pre-trained fitness evaluation model, wherein the fitness evaluation model is trained based on a neural network;

[0059] In this embodiment, the fitness evaluation model is a model obtained in advance through neural network training, and can predict the performance according to the structure of the energy blocker, thereby evaluating the fitness of the energy blocker.

[0060] It should be noted that in the genetic algorithm, fitness refers to the degree of adaptation of an individual to the environment. In this embodiment, the fitness of the energy blocker is determined according to its performance, and the better the performance, the higher the fitness.

[0061] To facilitate understanding, in one example, the structure of the energy blocker refers to the height and radius of the permanent magnet, and the performance of the energy blocker refers to the energy blocking ratio. Those skilled in the art will know that the energy blocking ratio is the ratio of the total energy value after the energy blocker is installed to the total energy value before the energy blocker is installed minus 1. If the height of the permanent magnet of energy blocker A is 10 cm and the radius is 8 cm, and the fitness evaluation model predicts that the energy blocking ratio of A is 0.8, then the energy blocking ratio is used as the fitness of A, that is, the fitness of A is 0.8. This embodiment utilizes the powerful information integration ability of the neural network, learns the complex nonlinear relationship between the structure and performance of the energy blocker, predicts the performance of energy blockers of different structures, thereby realizing the fitness evaluation of the energy blocker, assisting the genetic algorithm in the genetic variation of the energy blocker population, improving the speed and accuracy of the search, and searching for the optimal solution (that is, searching for the target energy blocker) faster and more accurately.

[0062] The calculation formula of energy blocking ratio is as follows:

[0063] Energy blocking ratio = total energy value after installing the energy blocker / total energy value before installing the energy blocker - 1.

[0064] Step S300: performing genetic mutation on the energy blocker population according to the fitness of each energy blocker in the energy blocker population to update the energy blocker population, and detecting whether the energy blocker population meets a preset termination condition;

[0065] In this embodiment, after obtaining the fitness of each energy blocker in the energy blocker population through a neural network, the energy blocker population can be genetically mutated through the selection operation, crossover operation and mutation operation of the genetic algorithm to update the energy blocker population, that is, to update the energy blockers in the energy blocker population, so that the energy blocker population has more energy blockers with different structures, expands the search space, and thus searches for energy blockers with higher fitness.

[0066] It is worth mentioning that, in this embodiment, the preset termination condition is used to determine whether it is necessary to continue updating the energy blocker population through the genetic algorithm, and the preset termination condition is pre-set by the user according to actual needs.

[0067] To facilitate understanding, in one example, the preset termination condition may be the number of iterations of the genetic algorithm, that is, the number of times the energy blocker population passes through the genetic algorithm update. It is not difficult to understand that the user may set the number of iterations of the genetic algorithm according to actual needs before initializing the population (i.e., constructing the initial energy blocker population).

[0068] In another example, the preset termination condition may also be whether the average fitness of each energy blocker in the energy blocker population reaches a threshold value. It is not difficult to understand that the user may set the threshold value according to actual needs before initializing the population.

[0069] Step S400: if it is detected that the energy blocker population does not meet the preset termination condition, then return to execute: the step of evaluating the fitness of each energy blocker in the energy blocker population based on the pre-trained fitness evaluation model;

[0070] In this embodiment, if it is detected that the energy blocker population does not satisfy the preset termination condition, it means that it is necessary to continue to perform genetic mutation on the energy blocker population to iteratively update the energy blocker population. Therefore, the process returns to step S200 to perform a fitness evaluation on the energy blocker population updated after this genetic mutation, that is, to evaluate the fitness of all energy blockers in the energy blocker population, thereby performing a new round of genetic mutation until the energy blocker population satisfies the preset termination condition to ensure that the optimal solution is searched.

[0071] Step S500: If it is detected that the energy blocker population meets the preset termination condition, the energy blocker with the highest fitness in the energy blocker population meeting the preset termination condition is used as the target energy blocker.

[0072] In this embodiment, the target energy blocker refers to the energy blocker with the highest fitness that can be searched by the genetic algorithm under the preset termination conditions. The ultimate goal of the energy blocker design method provided in this embodiment is to search for the target energy blocker through the genetic algorithm, so as to improve the efficiency of oil and gas development by designing and producing energy blocks with better performance according to the structure of the target energy blocker.

[0073] This embodiment constructs an initial energy blocker population, wherein the energy blocker population is composed of a plurality of energy blockers with different structures; based on a pre-trained fitness evaluation model, the fitness of each energy blocker in the energy blocker population is evaluated, wherein the fitness evaluation model is trained based on a neural network; according to the fitness of each energy blocker in the energy blocker population, genetic mutation is performed on the energy blocker population to update the energy blocker population, and whether the energy blocker population satisfies a preset termination condition is detected; if it is detected that the energy blocker population does not satisfy the preset termination condition, the step of returning to execute: based on the pre-trained fitness evaluation model, the step of evaluating the fitness of each energy blocker in the energy blocker population; if it is detected that the energy blocker population satisfies the preset termination condition, the energy blocker with the highest fitness in the energy blocker population that satisfies the preset termination condition is used as the target energy blocker. This embodiment uses a neural network to learn the relationship between the structural parameters and performance parameters of the energy blocker, and implements fitness evaluation of each energy blocker in the energy blocker population, so that the performance of energy blockers with different structures can be determined without actual measurement. Then, the energy blocker population is genetically mutated according to the fitness of each energy blocker, and the energy blocker population is continuously updated. When the energy blocker population meets the preset termination condition, the energy blocker with the highest fitness is used as the target energy blocker, and the optimal solution of the energy blocker structure is quickly searched for with the help of a genetic algorithm, so as to realize the automatic design of the energy blocker structure, greatly shorten the design cycle, reduce the design cost, and compared with the energy blocker designed by the traditional design method, the target energy blocker finally searched by this method has better performance.

[0074] Furthermore, in a possible implementation manner, the method further includes:

[0075] Step A10: Acquire structural parameters of the energy blocker to be simulated, wherein the structural parameters characterize the structure of the energy blocker;

[0076] In this embodiment, the structural parameters may include permanent magnet height, permanent magnet radius, capsule height, capsule radius, electromagnetic coil turns, and electromagnetic coil current, etc. The energy blocker to be simulated refers to an energy blocker used for simulation testing, and the structural parameters of the energy blocker to be simulated are set by the user according to requirements.

[0077] Step A20: performing simulation tests according to the structural parameters of the energy blocker to be simulated to obtain performance parameters of the energy blocker to be simulated, wherein the performance parameters represent the performance of the energy blocker;

[0078] In this embodiment, the performance parameters may include energy blocking ratio, frequency response, etc.

[0079] In this embodiment, according to the structural parameters of the energy blocker to be simulated, the operating conditions of the energy blocker to be simulated are simulated by simulation software to obtain the performance parameters of the energy blocker to be simulated, and prepare training data for training the neural network.

[0080] It is not difficult to understand that when doing simulation tests, it is not just a simulation test on one energy blocker to be simulated, but a simulation test on multiple energy blockers to be simulated with different structures, so as to obtain multiple sets of corresponding structural parameters and performance parameters as training data, which are input into the neural network for training.

[0081] Step A30: Using the structural parameters and performance parameters of the energy blocker to be simulated as input parameters of the neural network, iteratively optimizing the neural network to obtain a trained fitness evaluation model.

[0082] In this embodiment, after obtaining the structural parameters and performance parameters of multiple energy blockers to be simulated through simulation tests, the structural parameters and performance parameters are used as input parameters of the neural network, and the neural network is iteratively optimized to guide the neural network to learn the relationship between the structural parameters and the performance parameters, so that the performance parameters output by the neural network according to the structural parameters are more consistent with the actual performance parameters, thereby improving the accuracy of the genetic algorithm search and accurately searching for the energy blocker with the optimal structure, that is, searching for the energy blocker with the best energy blocking effect.

[0083] In this embodiment, a neural network is trained to learn the relationship between the structural parameters and performance parameters of the energy blocker, and a trained fitness evaluation model is obtained, so that the performance of the energy blocker can be determined by simply inputting the structural parameters of the energy blocker, saving the time and cost of repeated testing when designing the energy blocker, greatly improving the design cycle, and in the process of iterative updating of the genetic algorithm, the results output by the neural network can fully approximate any complex nonlinear relationship, which can effectively reduce the difficulty of designing the fitness evaluation function, improve the accuracy of the genetic algorithm search results, and then search for a target energy blocker with a higher energy blocking ratio.

[0084] In a possible implementation, the step of constructing an initial energy blocker population includes:

[0085] Step S110: obtaining a preset value range of a structural parameter;

[0086] Step S120: generating a plurality of energy blockers of different structures according to the value range to construct an initial energy blocker population.

[0087] In this embodiment, the user can pre-set the value range of the structural parameters, thereby limiting the genetic algorithm to randomly generate multiple energy blockers with different structures within the value range to construct an initial energy blocker population, and perform genetic mutation on the energy blocker population within the value range.

[0088] It is not difficult to understand that the value range is set by the user based on the relevant knowledge of energy blocker design and the experience accumulated in practical applications. The purpose of setting the value range is to narrow the search space of the genetic algorithm, improve the search speed and accuracy, and achieve faster and more accurate search, thereby further shortening the design cycle of the energy blocker.

[0089] In one possible implementation, please refer to Figure 2 , Figure 2 The flowchart of fitness evaluation in an embodiment of the present invention is as follows. The step of evaluating the fitness of each energy blocker in the energy blocker population based on a pre-trained fitness evaluation model includes:

[0090] Step S210: inputting the structural parameters of each energy blocker in the energy blocker population into the fitness evaluation model to obtain the performance parameters of each energy blocker in the energy blocker population output by the fitness evaluation model;

[0091] In this embodiment, after the structural parameters of each energy blocker in the energy blocker population are input into the fitness evaluation model, the fitness evaluation model outputs corresponding performance parameters based on the input structural parameters, thereby obtaining the performance parameters of each energy blocker in the energy blocker population, making it convenient to determine the fitness of each energy blocker according to the performance parameters of each energy blocker.

[0092] Step S220: determining the fitness of each energy blocker in the energy blocker population according to the performance parameters of each energy blocker in the energy blocker population.

[0093] In this embodiment, the performance parameter refers to the energy blocking ratio. In one example, the energy blocking ratio can be directly used as the fitness. For example, if the energy blocking ratio of energy blocker A is 0.7, then the fitness of A is determined to be 0.7. In another example, the highest value of the fitness of each energy blocker in the energy blocker population after this update can be first determined, and the ratio of the fitness of the energy blocker to the highest value can be used as the fitness. For example, if the highest value is 0.8 and the energy blocking ratio of energy blocker B is 0.4, then the fitness of B is determined to be 0.5.

[0094] The fitness evaluation model obtained through neural network training in this embodiment performs fitness evaluation on the energy blocker population (that is, evaluates the fitness of each energy blocker in the energy blocker population), which greatly reduces the difficulty of designing a fitness evaluation function by the genetic algorithm. The fitness of each energy blocker in the energy blocker population can be quickly calculated with the help of the improved fitness evaluation model in this embodiment.

[0095] In one possible implementation, please refer to Figure 3 , Figure 3 : is a schematic diagram of a genetic variation process according to an embodiment of the present invention, wherein the step of genetically varying the energy blocker population according to the fitness of each energy blocker in the energy blocker population to update the energy blocker population comprises:

[0096] Step S310: selecting energy blockers in the energy blocker population according to the fitness of each energy blocker in the energy blocker population to obtain a first energy blocker;

[0097] It should be noted that selection refers to the selection operation of the genetic algorithm, the purpose of which is to directly pass on the optimized individuals (i.e., individuals with high fitness) to the next generation or to generate new individuals through pairing and crossover and then pass them on to the next generation.

[0098] In this embodiment, the first energy blocker refers to an energy blocker selected from the energy blocker population through a selection operation. Compared with energy blockers that are not selected, the first energy blocker has a higher fitness.

[0099] It is not difficult to understand that when selecting energy blockers in the energy blocker population, selection strategies such as roulette selection method, random traversal sampling method and tournament selection method can be used to select multiple energy blockers from the energy blocker population as the first energy blocker according to the fitness of each energy blocker with a certain probability. Among them, selection strategies such as roulette selection method, random traversal sampling method and tournament selection method are commonly used selection strategies in genetic algorithms. This embodiment does not elaborate on this, nor does it make specific limitations. Users can select any one of the selection strategies according to their needs to select energy blockers in the energy blocker population.

[0100] Step S320: Cross-reference the structural parameters of the first energy blocker to obtain a second energy blocker;

[0101] It should be noted that crossover refers to the crossover operation of the genetic algorithm, which pairs the individuals selected by the selection operation as parents, exchanges and reorganizes part of the structure of the two successfully paired parent individuals in a certain way, generates new individuals, expands the search space, and thus improves the global search capability of the genetic algorithm.

[0102] In this embodiment, the second energy blocker refers to an energy blocker obtained by exchanging and reorganizing the structural parameters of the first energy blocker through a crossover operation.

[0103] It is not difficult to understand that when the structural parameters of the first energy blocker are crossed, the first energy blocker can be paired and the structural parameters can be exchanged and reorganized through crossover strategies such as single-point crossover, multi-point crossover and uniform crossover, so as to produce a new energy blocker (i.e., the second energy blocker). Among them, crossover strategies such as single-point crossover, multi-point crossover and uniform crossover are commonly used crossover measurements in genetic algorithms. This embodiment does not elaborate on this, nor does it make specific limitations. The user can select any of the crossover strategies according to needs to cross the structural parameters of the first energy blocker.

[0104] Step S330: mutating the structural parameters of the second energy blocker to obtain a third energy blocker;

[0105] It should be noted that mutation refers to the mutation operation of the genetic algorithm, which introduces certain random disturbances to change the structure of the individuals generated by the crossover operation within a certain range, thereby realizing the generation of new individuals and improving the local search capability of the genetic algorithm.

[0106] In this embodiment, the third energy blocker refers to an energy blocker obtained by randomly perturbing the structural parameters of the second energy blocker through a mutation operation.

[0107] It is not difficult to understand that when the structural parameters of the second energy blocker are varied, one or more structural parameters of the second energy blocker can be randomly selected for variation, so that the values ​​of the structural parameters fluctuate randomly within a certain range, thereby producing a new energy blocker (i.e., the third energy blocker). Among them, the range of random fluctuation, the structural parameters to be varied, and the number of third energy blockers obtained by varying a single second energy blocker can all be set according to user needs, and this embodiment does not impose specific restrictions on this.

[0108] Step S340: updating the energy blocker population according to the first energy blocker, the second energy blocker and the second energy blocker.

[0109] In this embodiment, after the first energy blocker, the second energy blocker and the third energy blocker are obtained through the three operations of selection, crossover and mutation, the energy blocker population is updated according to the first energy blocker, the second energy blocker and the third energy blocker, so that the average fitness of each energy blocker in the energy blocker population is higher, and the energy blocker population as a whole moves in the direction where the optimal solution exists.

[0110] Specifically, in one example, the method for updating the energy blocker population can be to directly add the first energy blocker, the second energy blocker, and the third energy blocker to the energy blocker population. It is not difficult to understand that the updated energy blocker population contains both the energy blockers that existed before this genetic variation and the energy blockers (i.e., the second energy blocker and the third energy blocker) generated after this genetic variation. The method of directly adding the first energy blocker, the second energy blocker, and the third energy blocker to the energy blocker population retains the original energy blockers, which can effectively avoid the situation where the genetic algorithm falls into a local extreme value.

[0111] Further, in a possible implementation manner, the step of updating the energy blocker population according to the first energy blocker, the second energy blocker and the second energy blocker includes:

[0112] Step S341: constructing a descendant energy blocker population according to the first energy blocker, the second energy blocker and the second energy blocker;

[0113] In this embodiment, the offspring energy blocker population refers to a population consisting only of the first energy blocker, the second energy blocker and the third energy blocker obtained through selection, crossover and mutation of this genetic variation.

[0114] Step S342: taking the descendant energy blocker population as the latest energy blocker population.

[0115] In this embodiment, a child energy blocker population is constructed by using the first energy blocker, the second energy blocker and the third energy blocker, and the child energy blocker population is used as the latest energy blocker population to update the energy blocker population.

[0116] Each time the energy blocker population is updated, this embodiment will eliminate a portion of the energy blockers, effectively reducing the complexity of the computer processing algorithm, increasing the speed of iterative updates, and enabling the energy blocker population to meet the preset termination conditions more quickly, thereby determining the target energy blocker.

[0117] In a possible implementation, the step of detecting whether the energy blocker population meets a preset termination condition includes:

[0118] Step B10: detecting the maximum value of the fitness of each energy blocker in the energy blocker population;

[0119] Step B20: If the highest value is less than or equal to a preset value, it is determined that the energy blocker population does not meet a preset termination condition;

[0120] Step B30: If the highest value is greater than a preset value, it is determined that the energy blocker population meets a preset termination condition.

[0121] In this embodiment, after each update of the energy blocker population, the fitness of each energy blocker in the energy blocker population is counted to determine the highest value of the fitness. If the highest value is less than or equal to the preset value, it is determined that the energy blocker population does not meet the preset termination condition, and the energy blocker population is updated through the genetic algorithm. If the highest value is greater than the preset value, it is determined that the energy blocker population meets the preset termination condition, and the genetic algorithm is terminated, so that the energy blocker corresponding to the highest value is used as the target energy blocker.

[0122] Compared with the method of judging whether to continue updating the energy blocker population based on the average value of the number of iterations and the fitness, the method of this embodiment judges whether to continue updating the energy blocker population based on the maximum value of the fitness. When the energy blocking ratio is directly used as the fitness, it can ensure that the genetic algorithm can stably search for the target energy blocker whose energy blocking ratio meets the user's needs.

[0123] In addition, the present invention also provides an energy blocker design device, please refer to Figure 4 , Figure 4 The schematic diagram of the module of the energy blocker design device involved in the embodiment of the present invention is as follows:

[0124] An initialization module 10, used to construct an initial energy blocker population, wherein the energy blocker population is composed of a plurality of energy blockers of different structures;

[0125] A genetic variation module 20 is used to evaluate the fitness of each energy blocker in the energy blocker population based on a pre-trained fitness evaluation model, wherein the fitness evaluation model is trained based on a neural network; according to the fitness of each energy blocker in the energy blocker population, genetically mutate the energy blocker population to update the energy blocker population, and detect whether the energy blocker population meets a preset termination condition; if it is detected that the energy blocker population does not meet the preset termination condition, return to execute: the step of evaluating the fitness of each energy blocker in the energy blocker population based on the pre-trained fitness evaluation model until the energy blocker population meets the preset termination condition;

[0126] The iterative termination module 30 is used to, if it is detected that the energy blocker population satisfies a preset termination condition, use the energy blocker with the highest fitness in the energy blocker population that satisfies the preset termination condition as the target energy blocker.

[0127] In one embodiment, the training module 40 (not shown) is used to:

[0128] Acquiring structural parameters of the energy blocker to be simulated, wherein the structural parameters represent the structure of the energy blocker;

[0129] Performing simulation tests according to the structural parameters of the energy blocker to be simulated to obtain performance parameters of the energy blocker to be simulated, wherein the performance parameters represent the performance of the energy blocker;

[0130] The structural parameters and performance parameters of the energy blocker to be simulated are used as input parameters of the neural network, and the neural network is iteratively optimized to obtain a trained fitness evaluation model.

[0131] In one embodiment, the initialization module 10 is further used for:

[0132] Obtain the value range of the preset structural parameters;

[0133] According to the value range, a plurality of energy blockers with different structures are generated to construct an initial energy blocker population.

[0134] In one embodiment, the genetic variation module 20 is further configured to:

[0135] Inputting the structural parameters of each energy blocker in the energy blocker population into the fitness evaluation model to obtain the performance parameters of each energy blocker in the energy blocker population output by the fitness evaluation model;

[0136] The fitness of each energy blocker in the energy blocker population is determined according to the performance parameters of each energy blocker in the energy blocker population.

[0137] In one embodiment, the genetic variation module 20 is further configured to:

[0138] selecting energy blockers in the energy blocker population according to the fitness of each energy blocker in the energy blocker population to obtain a first energy blocker;

[0139] Crossing the structural parameters of the first energy blocker to obtain a second energy blocker;

[0140] Varying the structural parameters of the second energy blocker to obtain a third energy blocker;

[0141] The energy blocker population is updated based on the first energy blocker, the second energy blocker, and the second energy blocker.

[0142] In one embodiment, the genetic variation module 20 is further configured to:

[0143] constructing a population of offspring energy blockers according to the first energy blocker, the second energy blocker and the second energy blocker;

[0144] The descendant energy blocker population is used as the latest energy blocker population.

[0145] In one embodiment, the genetic variation module 20 is further configured to:

[0146] Detecting the highest value of the fitness of each energy blocker in the energy blocker population;

[0147] If the highest value is less than or equal to a preset value, it is determined that the energy blocker population does not meet the preset termination condition;

[0148] If the highest value is greater than a preset value, it is determined that the energy blocker population meets a preset termination condition.

[0149] The energy blocker design device provided in the embodiment of the present invention adopts the energy blocker design method in the above embodiment, which can solve the technical problem that the repeated trial and error process leads to a long design cycle and high cost when designing an electromagnetic energy blocker. Compared with the prior art, the beneficial effects of the energy blocker design device provided in the embodiment of the present invention are the same as the beneficial effects of the energy blocker design method provided in the above embodiment, and the other technical features in the energy blocker design device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0150] In addition, the present invention also provides an energy blocker design device, which includes a memory, a processor, and an energy blocker design program stored in the memory and executable on the processor. When the energy blocker design program is executed by the processor, the steps of the energy blocker design method described above are implemented.

[0151] Please refer to Figure 5 , Figure 5 A schematic diagram of the structure of an energy blocker design device for a hardware operating environment involved in an embodiment of the present invention.

[0152] like Figure 5As shown, the energy blocker design device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM) memory, or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0153] Those skilled in the art will understand that Figure 5 The structures shown in the drawings do not constitute limitations on the energy blocker design device, and may include more or fewer components than shown, or combinations of certain components, or different arrangements of components.

[0154] like Figure 5 As shown, the memory 1005 as a storage medium may include an operating system, a data storage module, a network communication module, a user interface module, and an energy blocker design program.

[0155] exist Figure 5 In the energy blocker design device shown, the network interface 1004 is mainly used for data communication with other devices; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the energy blocker design device of the present invention can be set in the energy blocker design device, and the energy blocker design device calls the energy blocker design program stored in the memory 1005 through the processor 1001, and executes the energy blocker design method provided by the embodiment of the present invention.

[0156] In addition, the present invention also provides a computer-readable storage medium, on which an energy blocker design program is stored. When the energy blocker design program is executed by a processor, the steps of the energy blocker design method as described above are implemented.

[0157] The specific implementation of the computer-readable storage medium of the present invention is basically the same as the various embodiments of the above-mentioned energy blocker design method, and will not be repeated here.

[0158] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0159] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0160] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0161] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for designing an energy blocker, characterized in that: The energy blocker design method comprises the following steps: Constructing an initial energy blocker population, wherein the energy blocker population is composed of a plurality of energy blockers of different structures; Based on a pre-trained fitness evaluation model, evaluating the fitness of each energy blocker in the energy blocker population, wherein the fitness evaluation model is trained based on a neural network; According to the fitness of each energy blocker in the energy blocker population, genetically mutate the energy blocker population to update the energy blocker population, and detect whether the energy blocker population meets a preset termination condition; If it is detected that the energy blocker population does not meet the preset termination condition, the process returns to execute: the step of evaluating the fitness of each energy blocker in the energy blocker population based on the pre-trained fitness evaluation model; If it is detected that the energy blocker population meets the preset termination condition, the energy blocker with the highest fitness in the energy blocker population that meets the preset termination condition is used as the target energy blocker.

2. The energy blocker design method according to claim 1, characterized in that: The method further comprises: Acquiring structural parameters of the energy blocker to be simulated, wherein the structural parameters represent the structure of the energy blocker; Performing simulation tests according to the structural parameters of the energy blocker to be simulated to obtain performance parameters of the energy blocker to be simulated, wherein the performance parameters represent the performance of the energy blocker; The structural parameters and performance parameters of the energy blocker to be simulated are used as input parameters of the neural network, and the neural network is iteratively optimized to obtain a trained fitness evaluation model.

3. The energy blocker design method according to claim 2, characterized in that: The step of constructing an initial energy blocker population comprises: Obtain the value range of the preset structural parameters; According to the value range, a plurality of energy blockers with different structures are generated to construct an initial energy blocker population.

4. The energy blocker design method according to claim 3, characterized in that: The step of evaluating the fitness of each energy blocker in the energy blocker population based on the pre-trained fitness evaluation model comprises: Inputting the structural parameters of each energy blocker in the energy blocker population into the fitness evaluation model to obtain the performance parameters of each energy blocker in the energy blocker population output by the fitness evaluation model; The fitness of each energy blocker in the energy blocker population is determined according to the performance parameters of each energy blocker in the energy blocker population.

5. The energy blocker design method according to claim 3, characterized in that: The step of performing genetic variation on the energy blocker population according to the fitness of each energy blocker in the energy blocker population to update the energy blocker population comprises: selecting energy blockers in the energy blocker population according to the fitness of each energy blocker in the energy blocker population to obtain a first energy blocker; Crossing the structural parameters of the first energy blocker to obtain a second energy blocker; Varying the structural parameters of the second energy blocker to obtain a third energy blocker; The energy blocker population is updated based on the first energy blocker, the second energy blocker, and the second energy blocker.

6. The energy blocker design method according to claim 5, characterized in that: The step of updating the energy blocker population according to the first energy blocker, the second energy blocker and the second energy blocker comprises: constructing a population of offspring energy blockers according to the first energy blocker, the second energy blocker and the second energy blocker; The descendant energy blocker population is used as the latest energy blocker population.

7. The energy blocker design method according to any one of claims 1 to 6, characterized in that: The step of detecting whether the energy blocker population meets a preset termination condition comprises: Detecting the highest value of the fitness of each energy blocker in the energy blocker population; If the highest value is less than or equal to a preset value, it is determined that the energy blocker population does not meet the preset termination condition; If the highest value is greater than a preset value, it is determined that the energy blocker population meets a preset termination condition.

8. An energy blocker design device, characterized in that: The device comprises: An initialization module, used for constructing an initial energy blocker population, wherein the energy blocker population is composed of a plurality of energy blockers of different structures; A genetic variation module, used for evaluating the fitness of each energy blocker in the energy blocker population based on a pre-trained fitness evaluation model, wherein the fitness evaluation model is trained based on a neural network; performing genetic variation on the energy blocker population according to the fitness of each energy blocker in the energy blocker population to update the energy blocker population, and detecting whether the energy blocker population meets a preset termination condition; if it is detected that the energy blocker population does not meet the preset termination condition, returning to execute: the step of evaluating the fitness of each energy blocker in the energy blocker population based on the pre-trained fitness evaluation model until the energy blocker population meets the preset termination condition; The iterative termination module is used to, if it is detected that the energy blocker population meets the preset termination condition, use the energy blocker with the highest fitness in the energy blocker population that meets the preset termination condition as the target energy blocker.

9. An energy blocker design device, characterized in that: The device comprises: a memory, a processor, and an energy barrier design program stored in the memory and executable on the processor, wherein the energy barrier design program is configured to implement the steps of the energy barrier design method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an energy blocker design program, and when the energy blocker design program is executed by a processor, the steps of the energy blocker design method according to any one of claims 1 to 7 are implemented.

Images