Method and system for intelligently identifying categories of particles produced by medium-low energy heavy ion nuclear reaction

Abstract

Disclosed in the present invention are a method and system for intelligently identifying the categories of particles produced by a medium-low energy heavy ion nuclear reaction. The method comprises: creating a particle library including all possible categories of particles produced by the current medium-low energy heavy ion nuclear reaction; using a genetic algorithm and the created particle library to construct a particle identification curve set; collecting original data of two-dimensional energy spectrum features E and ΔE of an input particle to be identified; and using the constructed particle identification curve set to identify the category of the particle. The present invention realizes intelligent identification of the categories of particles produced by a medium-low energy heavy ion nuclear reaction, solves the problems of existing particle identification methods that rely on manual processes, such as being time-consuming and labor-intensive, and having low efficiency, poor repeatability, low accuracy, a large workload, and difficulty in handling a large amount of complex experimental data, can also support usage in various different experimental environments and support online environments, offers advantages such as speed, convenience, high efficiency and high accuracy, and has significant application value for nuclear physics research.

Description

A method and system for intelligently identifying particle types produced by medium and low energy heavy ion nuclear reactions Technical Field

[0001] The present invention relates to a method and system for intelligently identifying particle categories produced by medium- and low-energy heavy ion nuclear reactions, and belongs to the field of information processing technology. Background Art

[0002] Heavy ions are atomic nuclei whose mass or charge exceeds that of alpha particles. Collisions between heavy ions and atomic nuclei are called heavy ion nuclear reactions. Intermediate- and low-energy heavy ion nuclear reactions, which occur within the medium energy range, are currently the only means of studying the properties of high-temperature, high-density nuclear matter in Earth-based laboratories. These reactions can be used to explore the fundamental structure of matter and understand the origin of the universe, and are of great significance in physics research.

[0003] The main task of particle identification is to confirm the charge and mass of particles produced in nuclear reactions. This helps researchers identify the types of particles produced, thereby understanding the reaction process and further studying the reaction results. Particle identification is a very important step in heavy ion nuclear reaction experiments, because only by accurately identifying different types of particles can their properties and interactions be effectively studied.

[0004] In low- and medium-energy heavy-ion nuclear reaction experiments, researchers typically use telescopic detectors to collect information about particles produced during the nuclear reaction. These detectors consist of a thinner scintillator detector and a thicker scintillator detector. By using the particle deposition energy ΔE generated in the thinner scintillator detector as the y-axis and the deposition energy E in the thicker scintillator detector as the x-axis, a two-dimensional histogram of the particles can be plotted (this two-dimensional histogram is also called a two-dimensional energy spectrum). In the two-dimensional energy spectrum, the scattered points of the particles form multiple hyperbolic particle clusters, and particles in the same band-like clusters have the same charge and mass number. Currently, in the field of nuclear physics, the identification of particle categories relies primarily on manual cutting, fitting, and linearization of the particle's two-dimensional energy spectrum using professional nuclear data analysis software. The particle category is then manually determined based on the peaks of the linearized one-dimensional spectrum. This identification method not only has problems such as poor repeatability, time-consuming and labor-intensive, low efficiency, and high work intensity, but the key is that with the advancement of scientific theory and the continuous improvement of experimental instruments, the amount of data generated by medium and low-energy heavy ion nuclear reactions has reached billions. If the current manual identification processing method is used, it can no longer meet the complex experimental requirements and rapid identification requirements. Therefore, this field urgently needs a technology that can realize intelligent identification of particle categories produced by medium and low-energy heavy ion nuclear reactions. Technical issues

[0005] In view of the above-mentioned problems and needs in the prior art, the purpose of the present invention is to provide a method and system for intelligently identifying the types of particles produced by medium and low energy heavy ion nuclear reactions. Technical Solutions

[0006] In order to achieve the above-mentioned object of the invention, the present invention adopts the following technical solutions:

[0007] A method for intelligently identifying particle types produced by medium- and low-energy heavy ion nuclear reactions comprises the following steps:

[0008] S1) creating a particle library containing all particle types that may be produced by current medium and low energy heavy ion nuclear reactions, wherein the particle library is a nested array consisting of arrays consisting of charge numbers and mass numbers expressing the particle types;

[0009] S2) Using the genetic algorithm and the particle library created in step S1), a set of particle identification curves is constructed, wherein the particle identification curves all conform to the following formula (1):

[0010] (1);

[0011] Where: E and ΔE are the two-dimensional energy spectrum characteristic values ​​of the particle, Z is the charge number of the particle, A is the mass number of the particle, g, λ, ζ, α, β, µ and v are the parameters of the particle identification curve, and all the particle identification curve parameter values ​​are greater than 0 and are obtained by iterative optimization of the genetic algorithm;

[0012] The particle identification curve set is a set of multiple particle identification curves formed by substituting the particle identification curve parameter values ​​and the charge number and mass number of the corresponding particle category into formula (1);

[0013] S3) cleaning the input particle data generated by the current medium and low energy heavy ion nuclear reaction to be identified, and extracting only the collected data of the two-dimensional energy spectrum characteristics E and ΔE of each particle;

[0014] S4) Substitute the collected data of E corresponding to the particle j to be identified input in step S3) into the formula (1) described in step S2), and sequentially use the particle identification curve parameter value, charge number and mass number corresponding to each particle identification curve in the particle identification curve set constructed in step S2) to calculate the ΔE value respectively, and the calculated ΔE value is simply recorded as ΔE j ; ΔE (original acquisition value) - ΔE j The absolute value of (calculated value) is taken as the distance between the particle j to be identified and the corresponding particle identification curve, and ΔE-ΔE jThe charge number and mass number of the particle identification curve corresponding to the minimum value (i.e., the difference between the original collected value and the calculated value) are determined as the category of the particle j to be identified.

[0015] Furthermore, the process of constructing the particle identification curve set described in step S2) includes the following specific steps:

[0016] S21) obtaining an existing particle data set for the same reaction as the current low- to medium-energy heavy ion nuclear reaction, performing a cleaning process to remove redundant data features, and extracting only the acquired data of the two-dimensional energy spectrum features E and ΔE of each particle;

[0017] S22) Randomly generate a certain number of individuals, and the collection of these individuals is called a population; each individual is determined by the particle recognition curve parameters g, λ, ζ, α, β, µ, v and the integer judgment variable N that determines whether all particle categories in the particle library exist in the acquired existing particle data set. i The value of i is a natural number starting from 1 that is consistent with the order of the particle categories in the particle library, and N i The value is 0 or 1. When N i When the value of is 0, it means that the particle category in the particle library does not exist in the acquired particle data set. i When the value is 1, it means that the particle category in the particle library exists in the acquired particle data set; at the initial stage, g, λ, ζ, α, β, µ, v and N constitute each individual i The values ​​of are randomly generated by the system;

[0018] S23) Calculate the fitness value y of each individual according to the fitness function shown in the following formula (2):

[0019] (2);

[0020] Where: Nl represents the number of curves, Np i is the number of particles corresponding to the i-th curve, ΔE j is the ΔE calculated by formula (1) for particle j, ΔE is the original collection value for particle j; and Np i Not 0, Nl refers to N i is 1 and Np i The number of curves corresponding to particle categories that are not 0; and ΔE-ΔE j The value of particle j to N i The minimum distance of the curve corresponding to all particle categories is 1;

[0021] S24) selecting suitable individuals from the population and generating the next generation based on the calculated fitness value y of each individual;

[0022] S25) adding the next generation generated into the population by replacement or direct addition;

[0023] S26) Repeat steps S21) to S25) until the iteration stop condition is met;

[0024] S27) After completing the iteration, output the individual with the smallest fitness y value;

[0025] S28) N i is 1 and Np i The charge number and mass number of the particle categories that are not zero are respectively combined with the particle identification curve parameters g, λ, ζ, α, β, µ, and v in the output individuals and substituted into formula (1) to obtain the particle identification curve set.

[0026] As a preferred solution, the step S2) further includes the following optimization iteration steps:

[0027] S29) Grouping the particles in the constructed particle identification curve set according to the charge number, grouping particles with the same charge number into one group, and then repeating steps S21) to S28) for the particles in each group.

[0028] In one embodiment, the step S23) includes the following specific steps:

[0029] S231) traversing the existing particle data set obtained in step S21);

[0030] S232) acquiring collected data of a two-dimensional energy spectrum characteristic E and ΔE of a particle j;

[0031] S233) Press N in the current individual i Calculate ΔE-ΔE for the mass number and charge number of the particle category corresponding to 1 and the particle identification curve parameters g, λ, ζ, α, β, µ, and v in the current individual. j , take the minimum absolute value, and at the same time, obtain the Np of the particle category corresponding to the minimum absolute value i Add one to count the number of particles in this particle category;

[0032] S234) Continue to acquire the collected data of the two-dimensional energy spectrum characteristics E and ΔE of the next particle, and continue to repeat step S233).

[0033] In one embodiment, the step S24) includes the following specific steps:

[0034] S241) Selection: Based on the calculated fitness y value of each individual, select some individuals with relatively small fitness y values ​​as the next generation population;

[0035] S242) Mutation: Changing the random data characteristics of some individuals in a population to avoid excessive similarity between individuals in the population and promote population diversity;

[0036] S243) Crossover: Randomly crossover some individuals in the population to produce new individuals.

[0037] In one implementation scheme, the iteration stopping condition in step S26) is a preset maximum number of iterations, a continuous stagnation upper limit, or a fitness threshold.

[0038] In one embodiment, the method further comprises the steps of:

[0039] S5) saving the outlier particle data whose distances from all particle identification curves in the particle identification curve set exceed a preset threshold. When the preset number is reached, re-execute step S2) in combination with the original data to update the particle identification curve set.

[0040] A system for intelligently identifying particle types produced by medium- and low-energy heavy ion nuclear reactions, comprising:

[0041] The data processing module is used to clean the raw particle data generated by the input medium and low energy heavy ion nuclear reactions to extract the collected data of the two-dimensional energy spectrum characteristics E and ΔE of the particles;

[0042] A particle identification curve set construction module is used to create a particle library and construct a particle identification curve set using a genetic algorithm;

[0043] The particle category identification module is used to identify the particle categories produced by current medium and low energy heavy ion nuclear reactions.

[0044] In addition, the present invention also provides a storage medium, which stores one or more computer programs including execution instructions, and the execution instructions can be read and executed by electronic devices (including but not limited to computers, servers, or network devices, etc.) to implement the above-mentioned method of intelligent identification of particle categories produced by low-energy heavy ion nuclear reactions in the present invention.

[0045] The present invention also provides an electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores program instructions that can be executed by the at least one processor, and the program instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned method of intelligently identifying the particle categories produced by low-energy heavy ion nuclear reactions of the present invention.

[0046] The present invention also provides a computer program product, including a computer program stored on a storage medium, wherein the computer program includes program instructions. When the program instructions are executed by a computer, the method of the present invention for intelligently identifying the types of particles produced by low-energy heavy ion nuclear reactions can be implemented. Beneficial effects

[0047] Compared with the prior art, the beneficial technical effects of the present invention are:

[0048] The present invention first creates a particle library containing all particle categories that may be produced by current medium and low energy heavy ion nuclear reactions based on existing nuclear physics research information, and combines the collected particle two-dimensional deposition energy characteristic data to construct a particle identification curve set using a genetic algorithm. Then, the distance value between the particle to be identified and each particle identification curve in the particle identification curve set is calculated, and the category of the particle to be identified is determined by judging whether the distance value is within a preset threshold range and which particle identification curve is closest to the particle. This not only realizes the intelligent identification of particle categories produced by medium and low energy heavy ion nuclear reactions, but also solves the problems of existing manual particle identification methods such as time-consuming and labor-intensive, low efficiency, poor repeatability, poor accuracy, high work intensity and difficulty in dealing with large amounts of complex experimental data. In addition, there is no need to pre-label the data or train any data model, and the method can support use in various different experimental environments and online environments. It has the advantages of being fast, convenient, efficient and accurate, and has important application value for nuclear physics research. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] FIG1 is a flowchart illustrating a method for intelligently identifying particle types produced by low-energy heavy ion nuclear reactions according to an embodiment of the present invention;

[0050] FIG2 is a flow chart showing the construction of a particle identification curve set according to an embodiment of the present invention;

[0051] FIG3 is a visualization diagram of a particle identification curve set constructed according to an embodiment of the present invention;

[0052] FIG4 is a flow chart showing a method for intelligently identifying particle types produced by low-energy heavy ion nuclear reactions according to the present invention executed by a computer;

[0053] FIG5 shows a block diagram of a system structure for intelligently identifying particle categories produced by low-energy heavy ion nuclear reactions, provided by an embodiment of the present invention. Best Mode for Carrying Out the Invention

[0054] The technical solution of the present invention is further described in detail and completely below with reference to the embodiments and drawings. Example

[0055] Referring to FIG. 1 and FIG. 2 , a method for intelligently identifying particle types produced by medium- and low-energy heavy ion nuclear reactions includes the following steps:

[0056] S1) creating a particle library containing all particle categories that may be produced by current low- and medium-energy heavy ion nuclear reactions, wherein the particle library is a nested array consisting of arrays representing the charge and mass numbers of the particle categories. For example, the particle library constructed in this embodiment is [[1, 1], [1, 2], [1, 3], [2, 3], [2, 4], [3, 6], [3, 7], [4, 9], [5, 10], [5, 11]], which is a nested array consisting of arrays of ten particle categories. The particle library is initially created based on known nuclear physics research information and can be continuously updated later based on research progress.

[0057] S2) Using the genetic algorithm and the particle library created in step S1), a set of particle identification curves is constructed, wherein the particle identification curves all conform to the following formula (1):

[0058] (1);

[0059] Where: E and ΔE are the two-dimensional energy spectrum characteristic values ​​of the particle, Z is the charge number of the particle, A is the mass number of the particle, g, λ, ζ, α, β, µ and v are the parameters of the particle identification curve, and all the particle identification curve parameter values ​​are greater than 0 and are obtained by iterative optimization of the genetic algorithm;

[0060] The particle identification curve set is a set of multiple particle identification curves constructed by substituting the particle identification curve parameter values ​​and the charge number and mass number of the corresponding particle category into formula (1). The specific construction process includes the following specific steps (see Figure 2):

[0061] S21) obtaining an existing particle dataset for the same reaction as the current low- to medium-energy heavy ion nuclear reaction, performing a cleaning process to remove redundant data features, and extracting only the acquired data of the two-dimensional energy spectrum features E and ΔE of each particle; assuming that in this embodiment, an existing particle dataset of 21,248 particles is obtained, among which: there are 14,224 particles with a charge number of 1, 5,629 particles with a charge number of 2, 735 particles with a charge number of 3, 180 particles with a charge number of 4, and 480 particles with a charge number of 5;

[0062] S22) Randomly generate a certain number of individuals, and the collection of these individuals is called a population; each individual is determined by the particle recognition curve parameters g, λ, ζ, α, β, µ, v and the integer judgment variable N that determines whether all particle categories in the particle library exist in the acquired existing particle data set.i The value of i is a natural number starting from 1 that is consistent with the order of the particle categories in the particle library. For example, N1 represents the first-order particle category in the particle library [1, 1], and N6 represents the sixth-order particle category in the particle library [3, 6]. i The value is 0 or 1. When N i When the value of is 0, it means that the particle category in the particle library does not exist in the acquired particle data set. i When the value of is 1, it means that the particle category in the particle library exists in the acquired particle data set. For example, if N1 is 0, it means that the first-order particle category [1, 1] in the particle library does not exist in the acquired particle data set. If N3 is 1, it means that the third-order particle category [1, 3] in the particle library exists in the acquired particle data set. Initially, the g, λ, ζ, α, β, µ, v and N of each individual are i The values ​​of are randomly generated by the system;

[0063] S23) Calculate the fitness value y of each individual according to the fitness function shown in the following formula (2):

[0064] (2);

[0065] Where: Nl represents the number of curves, Np i is the number of particles corresponding to the i-th curve, ΔE j is the ΔE calculated by formula (1) for particle j, ΔE is the original collection value for particle j; and Np i Not 0, Nl refers to N i is 1 and Np i The number of curves corresponding to particle categories that are not 0; and ΔE-ΔE j The value of particle j to N i The minimum distance of the curve corresponding to all particle categories is 1;

[0066] The calculation of the fitness y value of each individual includes the following steps:

[0067] S231) traversing the existing particle data set obtained in step S21);

[0068] S232) acquiring collected data of a two-dimensional energy spectrum characteristic E and ΔE of a particle j;

[0069] S233) Press N in the current individual iCalculate ΔE-ΔE for the mass number and charge number of the particle category corresponding to 1 and the particle identification curve parameters g, λ, ζ, α, β, µ, and v in the current individual. j , take the minimum absolute value, and at the same time, obtain the Np of the particle category corresponding to the minimum absolute value i Add one to count the number of particles of this particle type;

[0070] S234) Continue to acquire the data of the two-dimensional energy spectrum characteristics E and ΔE of the next particle, and continue to repeat step S233);

[0071] S24) Based on the calculated fitness value y of each individual, suitable individuals are selected from the population and the next generation is generated, specifically comprising the following steps:

[0072] S241) Selection: Based on the calculated fitness y value of each individual, select individuals with relatively small fitness y values ​​as the next generation population; the core of the selection strategy is survival of the fittest, replacing individuals with relatively large fitness y values ​​with individuals with relatively small fitness y values. The selection algorithm can be any one of the Boltzmann, random traversal, roulette, tournament, and Monte Carlo selection algorithms;

[0073] S242) Mutation: Modify the random data characteristics of some individuals in the population to avoid excessive similarity between individuals in the population and promote population diversity. The mutation algorithm can use any of the following mutation algorithms: bit mutation, random reset, exchange mutation, and uniform mutation.

[0074] S243) Crossover: Randomly crossover some individuals in the population to produce new individuals. The core of crossover is to use parent individuals to create one or more new child individuals. The crossover algorithm can be any of the following: single-point crossover, multi-point crossover, uniform crossover, random crossover, etc.

[0075] S25) adding the next generation generated into the population by replacement or direct addition;

[0076] S26) Repeat steps S21) to S25) until an iteration stop condition is met; the iteration stop condition is a preset maximum number of iterations, a continuous stagnation upper limit, or a fitness threshold; in this embodiment, the individual of the genetic algorithm is set to a 1*17 variable, the maximum number of iterations is set to 2000, and the maximum upper limit of the evolution stagnation counter is set to 20. The genetic algorithm calls the soea_SEGA_templet genetic algorithm interface of geatpy, which supports setting the type of decision variables, wherein the first 7 parameters (particle identification curve parameters) are set to floating-point variables, and the last 10 parameters are set to integer variables;

[0077] S27) After the iteration is completed, the individual with the smallest fitness y value is output; after the iteration is completed, this embodiment outputs [1.067, 0.815, 0.1, 2.9684, 1.009, 0.5242, 58.908, 1, 1, 1, 1, 1, 1, 1, 1, 1], where the first 7 parameters are the particle identification curve parameters g, λ, ζ, α, β, µ, and v in formula (1), and the last 10 parameters represent the 10 particle categories in the particle library, all of which exist in the existing particle data set obtained in step S21);

[0078] S28) N i is 1 and Np i The charge number and mass number of the particle categories that are not 0 are respectively combined with the particle identification curve parameters g, λ, ζ, α, β, µ, and v in the output individuals and substituted into formula (1) to obtain the particle identification curve set;

[0079] S29) grouping the particles in the constructed particle identification curve set according to the charge number, grouping the particles with the same charge number into one group, and then repeating steps S21) to S28) for the particles in each group to perform optimization iterations;

[0080] In this example, the number of particles corresponding to each particle type in the obtained existing particle dataset is [10671, 2678, 875, 867, 4762, 525, 210, 180, 297, 183]. Since there are five types of charge numbers, the particles are divided into five groups, among which:

[0081] The number of particles with charge number 1 (corresponding to particle categories [[1,1],[1,2],[1,3]]) is 10671+2678+875. After optimization iteration, the output is [1.009, 0.7915, 0.1, 3.3762, 1.1616, 0.3171, 51.6997, 1, 1, 1];

[0082] The number of particles with charge number 2 (corresponding to particle categories [[2,3],[2,4]]) is 867+4762. After optimization iterations, the output is [1.418, 0.7085, 0.1, 7.6019, 0.9271, 0.4643, 29.7271, 1, 1];

[0083] The number of particles with charge number 3 (corresponding to particle categories [[3, 6], [3, 7]]) is 525+210. After optimization iteration, the output is [1.0485, 0.7156, 1.4478, 3.0988, 1.2939, 0.9243, 69.4085, 1, 1];

[0084] There are 180 particles with a charge of 4 (corresponding to the particle class [[4,9]]). After the optimization iteration, the output is [0.9369, 0.6325, 1.3739, 11.6925, 0.5317, 0.693, 42.4851, 1];

[0085] The number of particles with a charge of 5 (corresponding to particle categories [[5,10],[5,11]]) is 297+183. After optimization iterations, the output is [1.0054, 0.7096, 1.8058, 6.1572, 1.122, 0.6146, 78.7048, 1, 1];

[0086] A visualization of the constructed particle identification curve set is shown in Figure 3. In the figure, the curve formed by particles with the same charge and mass number (represented by the scattered points in the figure) is a particle identification curve, and the isotope particle identification curves composed of the same charge number but different mass numbers constitute a group of curves. The charge number of the particle identification curve group is arranged from small to large from bottom to top, and the mass number of each particle identification curve group is arranged from small to large from bottom to top.

[0087] S3) cleaning the input particle data generated by the current medium and low energy heavy ion nuclear reaction to be identified, and extracting only the collected data of the two-dimensional energy spectrum characteristics E and ΔE of each particle;

[0088] S4) Substitute the collected data of E corresponding to the particle j to be identified input in step S3) into the formula (1) described in step S2), and sequentially use the particle identification curve parameter value, charge number and mass number corresponding to each particle identification curve in the particle identification curve set constructed in step S2) to calculate the ΔE value respectively, and the calculated ΔE value is simply recorded as ΔE j ; ΔE-ΔE j The absolute value of the difference between the original collected value and the calculated value is taken as the distance between the particle to be identified j and the corresponding particle identification curve, and ΔE-ΔE j The charge number and mass number of the particle identification curve corresponding to the minimum value of is determined as the category of the particle j to be identified;

[0089] S5) Saving the data of outlier particles whose distance from all particle identification curves in the particle identification curve set exceeds a preset threshold (which can be set by the user based on accuracy requirements). When a preset number of outlier particles is reached (which can be determined by the user based on actual needs, usually at least 1000), step S2) is re-executed in combination with the original data to update the particle identification curve set.

[0090] FIG4 shows a flow chart of a method for intelligently identifying particle categories produced by medium- and low-energy heavy ion nuclear reactions provided by the present invention executed by a computer.

[0091] FIG5 is a block diagram of a system structure for intelligently identifying particle types produced by low-energy heavy ion nuclear reactions provided by the present invention. As shown in FIG5 , the system includes:

[0092] The data processing module is used to clean the raw particle data generated by the input medium and low energy heavy ion nuclear reactions to extract the two-dimensional energy spectrum characteristics E and ΔE data of the particles;

[0093] A particle identification curve set construction module is used to create a particle library and construct a particle identification curve set using a genetic algorithm;

[0094] The particle category identification module is used to identify the particle categories produced by current medium and low energy heavy ion nuclear reactions.

[0095] The above-mentioned functional modules generally include routines, programs, objects, elements, data structures, etc. that perform specific tasks or implement specific abstract data types. Each module can exist physically separately, or two or more can be integrated into one module. The modules can be implemented in the form of hardware or in the form of software functional modules. If the physical or integrated modules are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium.

[0096] The present invention also provides a storage medium, which stores one or more programs including execution instructions, and the execution instructions can be read and executed by electronic devices (including but not limited to computers, servers, or network devices, etc.) to execute the above-mentioned method of intelligent identification of particle categories produced by low-energy heavy ion nuclear reactions in the present invention.

[0097] The present invention also provides an electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores program instructions that can be executed by the at least one processor, and the program instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned method of intelligently identifying the particle categories produced by low-energy heavy ion nuclear reactions of the present invention.

[0098] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created based on the use of the system for intelligently identifying chemically unstable natural products. Furthermore, the memory may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state memory device. In some embodiments, the memory may optionally include a memory remotely located relative to the processor, and these remote memories may be connected to the system for intelligently identifying chemically unstable natural products via a network. The network includes, but is not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0099] The electronic device may exist in various forms, including but not limited to:

[0100] (1) Mobile communication devices: These devices are characterized by their mobile communication capabilities and are primarily designed to provide voice and data communications. These terminals include smartphones (e.g., iPhones), multimedia phones, feature phones, and low-end phones.

[0101] (2) Ultra-mobile personal computer devices: These devices fall into the category of personal computers, have computing and processing capabilities, and generally also have mobile Internet access features. These terminals include: PDAs, MIDs, and UMPC devices, such as iPads;

[0102] (3) Portable entertainment devices: These devices can display and play multimedia content. They include audio and video players (such as iPods), handheld game consoles, e-books, smart toys, and portable car navigation devices.

[0103] (4) Server: A device that provides computing services. The server consists of a processor, hard disk, memory, system bus, etc. The server has a similar architecture to a general computer, but because it needs to provide highly reliable services, it has higher requirements in terms of processing power, stability, reliability, security, scalability, and manageability.

[0104] (5) Other electronic devices with data interaction functions.

[0105] The present invention also provides a computer program product, comprising a computer program stored on a storage medium, the computer program including program instructions that, when executed by a computer, enable the computer to perform the method for intelligently identifying particle types produced by low-energy heavy ion nuclear reactions described above. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods described in various embodiments or portions thereof.

[0106] In addition, the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as executable instructions for implementing the logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, device, or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device, or apparatus and execute the instructions), or in conjunction with such instruction execution systems, devices, or apparatuses. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by an instruction execution system, device, or apparatus, or in conjunction with such instruction execution systems, devices, or apparatuses. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection portion having one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0107] It should be understood that the various parts of the present invention can be implemented with hardware, software, firmware, or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented with software or firmware stored in a memory and executed by a suitable instruction execution system. A person skilled in the art will understand that all or part of the steps carried by the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0108] Finally, it is necessary to point out that the above is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or replacements that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the scope of protection of the present invention. In the absence of conflict, the embodiments in this application and the features in the embodiments can be combined with each other. Moreover, for the sake of simplicity of description, the aforementioned method embodiments are all expressed as a combination of a series of actions, but those skilled in the art should know that the present invention is not limited by the order of the actions described, because according to the present invention, certain steps can be performed in other orders or simultaneously; secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments.

Claims

1. A method for intelligently identifying the types of particles produced by medium and low energy heavy ion nuclear reactions, characterized in that: The method comprises the following steps: S1) creating a particle library containing all particle types that may be produced by current medium and low energy heavy ion nuclear reactions, wherein the particle library is a nested array consisting of arrays consisting of charge numbers and mass numbers expressing the particle types; S2) Using the genetic algorithm and the particle library created in step S1), a set of particle identification curves is constructed, wherein the particle identification curves all conform to the following formula (1): (1)； Where: E and ΔE are the two-dimensional energy spectrum characteristic values of the particle, Z is the charge number of the particle, A is the mass number of the particle, g, λ, ζ, α, β, µ and v are the parameters of the particle identification curve, and all the particle identification curve parameter values are greater than 0 and are obtained by iterative optimization of the genetic algorithm; The particle identification curve set is a set of multiple particle identification curves formed by substituting the particle identification curve parameter values and the charge number and mass number of the corresponding particle category into formula (1); S3) cleaning the input particle data generated by the current medium and low energy heavy ion nuclear reaction to be identified, and extracting only the collected data of the two-dimensional energy spectrum characteristics E and ΔE of each particle; S4) Substitute the collected data of E corresponding to the particle j to be identified input in step S3) into the formula (1) described in step S2), and sequentially use the particle identification curve parameter value, charge number and mass number corresponding to each particle identification curve in the particle identification curve set constructed in step S2) to calculate the ΔE value respectively, and the calculated ΔE value is simply recorded as ΔE j ; ΔE-ΔE j The absolute value of is taken as the distance from the particle j to be identified to the corresponding particle identification curve, and ΔE-ΔE j The charge number and mass number of the particle identification curve corresponding to the minimum absolute value of is determined as the category of the particle j to be identified.

2. The method according to claim 1, characterized in that The process of constructing the particle identification curve set described in step S2) includes the following specific steps: S21) obtaining an existing particle data set for the same reaction as the current low- to medium-energy heavy ion nuclear reaction, performing a cleaning process to remove redundant data features, and extracting only the acquired data of the two-dimensional energy spectrum features E and ΔE of each particle; S22) Randomly generate a certain number of individuals, and the collection of these individuals is called a population; each individual is determined by the particle recognition curve parameters g, λ, ζ, α, β, µ, v and the integer judgment variable N that determines whether all particle categories in the particle library exist in the acquired existing particle data set. i The value of i is a natural number starting from 1 that is consistent with the order of the particle categories in the particle library, and N i The value is 0 or 1. When N i When the value of is 0, it means that the particle category in the particle library does not exist in the acquired particle data set. i When the value is 1, it means that the particle category in the particle library exists in the acquired particle data set; at the initial stage, g, λ, ζ, α, β, µ, v and N constitute each individual i The values of are randomly generated by the system; S23) Calculate the fitness value y of each individual according to the fitness function shown in the following formula (2): (2)； Where: Nl represents the number of curves, Np i is the number of particles corresponding to the i-th curve, ΔE j is the ΔE calculated by formula (1) for particle j, ΔE is the original collection value for particle j; and Np i Not 0, Nl refers to N i is 1 and Np i The number of curves corresponding to particle categories that are not 0; and ΔE-ΔE j The value of particle j to N i The minimum distance of the curve corresponding to all particle categories is 1; S24) selecting suitable individuals from the population and generating the next generation based on the calculated fitness value y of each individual; S25) adding the next generation generated into the population by replacement or direct addition; S26) Repeat steps S21) to S25) until the iteration stop condition is met; S27) After completing the iteration, output the individual with the smallest fitness y value; S28) N i is 1 and Np i The charge number and mass number of the particle categories that are not zero are respectively combined with the particle identification curve parameters g, λ, ζ, α, β, µ, and v in the output individuals and substituted into formula (1) to obtain the particle identification curve set.

3. The method according to claim 2, characterized in that The step S2) further includes the following optimization iteration steps: S29) Grouping the particles in the constructed particle identification curve set according to the charge number, grouping particles with the same charge number into one group, and then repeating steps S21) to S28) for the particles in each group.

4. The method according to claim 2, characterized in that The step S23) includes the following specific steps: S231) traversing the existing particle data set obtained in step S21); S232) acquiring collected data of a two-dimensional energy spectrum characteristic E and ΔE of a particle j; S233) Press N in the current individual i Calculate ΔE-ΔE for the mass number and charge number of the particle category corresponding to 1 and the particle identification curve parameters g, λ, ζ, α, β, µ, and v in the current individual. j , take the minimum absolute value, and at the same time, obtain the Np of the particle category corresponding to the minimum absolute value i Add one to count the number of particles in this particle category; S234) Continue to acquire the collected data of the two-dimensional energy spectrum characteristics E and ΔE of the next particle, and continue to repeat step S233).

5. The method according to claim 2, characterized in that The step S24) includes the following specific steps: S241) Selection: Based on the calculated fitness y value of each individual, select some individuals with relatively small fitness y values as the next generation population; S242) Mutation: Changing the random data characteristics of some individuals in a population to avoid excessive similarity between individuals in the population and promote population diversity; S243) Crossover: Randomly crossover some individuals in the population to produce new individuals.

6. The method according to claim 1, characterized in that The method further comprises the steps of: S5) saving the outlier particle data whose distances from all particle identification curves in the particle identification curve set exceed a preset threshold. When the preset number is reached, re-execute step S2) in combination with the original data to update the particle identification curve set.

7. A system for intelligently identifying the types of particles produced by medium and low energy heavy ion nuclear reactions, characterized in that: The system comprises: The data processing module is used to clean the raw particle data generated by the input medium and low energy heavy ion nuclear reactions to extract the collected data of the two-dimensional energy spectrum characteristics E and ΔE of the particles; A particle identification curve set construction module is used to create a particle library and construct a particle identification curve set using a genetic algorithm; The particle category identification module is used to identify the particle categories produced by current medium and low energy heavy ion nuclear reactions.

8. A storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 can be implemented.

9. An electronic device comprising at least one processor and a memory communicatively connected to the at least one processor, wherein: The memory stores program instructions that can be executed by the at least one processor, and the program instructions are executed by the at least one processor; it is characterized in that: the at least one processor can execute the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program stored on a storage medium, the computer program comprising program instructions, characterized in that: When the program instructions are executed by a processor, the method according to any one of claims 1 to 6 can be implemented.

Images