Nanotube growth parameter optimization control method and system based on deep learning

Abstract

The invention discloses a nanotube growth parameter optimization control method and system based on deep learning, and relates to the technical field of nanotube production. Comprising the following steps: information acquisition: previous nanotube growth information and user demands are acquired, and the previous nanotube growth information comprises previous growth process information and nanotube performance information; according to the method, the difference between the real-time environment parameters and the parameters in the target growth information is explored to obtain the difference result, and the difference result is analyzed through the set analysis method to obtain the influence on the nanotube caused by the representative parameter difference, namely the difference consequence; the target growth information of the nanotube is optimized and adjusted according to the difference result through the set optimization method to obtain the optimized target growth information, so that the nanotube meeting the user requirement is produced, and the probability that the search speed is low and local optimum is likely to happen due to huge parameter space in the adjustment and optimization process is reduced; and improvement of the overall optimization efficiency is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of nanotube production, and in particular to a method and system for optimizing and controlling nanotube growth parameters based on deep learning. Background Art

[0002] Nanotubes, as a nanomaterial with unique physical and chemical properties, are widely used in electronic devices, sensors, composite materials and other fields. Their performance is highly dependent on the control of parameters during the growth process. Therefore, optimizing these parameters is crucial to the quality and performance of nanotubes.

[0003] Patent publication number CN119361030A discloses an AI-assisted carbon nanotube growth control method and system, which includes a three-dimensional AI virtual platform that collects carbon nanotube growth data and environmental data per unit time to construct a carbon nanotube model. The growth data includes growth rate, direction, and diameter, while the environmental data involves gas flow and electric field strength. The carbon nanotube model is mapped to a three-dimensional coordinate system, where the X-axis, Y-axis, and Z-axis represent the length, width, and height of the carbon nanotube, respectively, and the initial coordinates are recorded. By using a three-dimensional AI virtual platform and real-time data acquisition technology, the present invention can accurately capture environmental changes during the growth of carbon nanotubes. In combination with growth data, the environmental parameters are dynamically adjusted during the growth process, allowing for rapid response to environmental changes during actual control, avoiding growth instability or deviations caused by the inability to make timely adjustments in traditional methods.

[0004] In the prior art, in the process of optimizing and controlling nanotube growth parameters, multiple parameters are often adjusted to obtain optimal performance, and the adjustment process adopts progressive experiments and response surface methodology. In this case, there are disadvantages such as a large parameter space resulting in a slow search speed and a tendency to fall into local optimality, resulting in limited overall efficiency and effect. This is not conducive to optimizing nanotube growth according to actual demand information. At the same time, since errors caused by adjusting parameters of production machines cannot be addressed in a timely manner, it is impossible to produce nanotubes with corresponding performance according to user needs. Therefore, the present invention is proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for optimizing and controlling nanotube growth parameters based on deep learning to solve the problems raised in the above background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for optimizing and controlling nanotube growth parameters based on deep learning, comprising: Information acquisition: Obtaining past nanotube growth information and user needs. Past nanotube growth information includes past growth process information and nanotube performance information; Information processing: Establish an information database to store past nanotube growth information, establish the correlation between past growth process information and nanotube performance information, and recommend target nanotube growth information to users based on user needs and in conjunction with the information database; include: Growth information determination: determining whether the user needs to generate nanotube growth information to obtain a determination result. When the determination result indicates that the user needs to generate nanotube growth information, generating nanotube growth information that meets the user's needs based on the user's needs and the information database through a demand matching method to obtain target growth information; Monitoring status: monitor the real-time environmental parameters of nanotube growth, unify the time point, obtain the difference between the real-time environmental parameters and the parameters in the target growth information at the same time point, and obtain the difference results based on the results through analysis methods; Parameter optimization: Based on the difference consequences, the subsequent parameters in the target growth information are optimized and controlled by the optimization method to obtain the optimized target growth information; Information output: Nanotube growth is performed based on the optimized target growth information; Feedback update: Based on the optimized target growth information, the information in the information database is supplemented through the update method to obtain an updated information database.

[0007] Furthermore, the process of obtaining difference information based on the difference between the real-time environmental parameters and the parameters in the target growth information at the same time point is: splitting the real-time environmental parameters to obtain several first parameter items, splitting the target growth information to obtain several second parameter items, comparing the first parameter items and the second parameter items to obtain comparison results, extracting the comparison results and feeding them back as the second parameter items in the second parameter items that are different from the first parameter items and the size of the difference to obtain difference information.

[0008] Furthermore, the analysis method includes: splitting the difference results to obtain difference items and difference sizes, exploring the performance impact caused by differences in different growth parameters through a relationship acquisition method based on the information library to obtain consequence information, the consequence information includes difference information and impact information corresponding to the difference information, performing information matching in the difference information based on the difference items to obtain matching results, extracting the corresponding impact information based on the matching results to obtain target impact information, judging the specific details of the target impact information based on the difference size and the target impact information through a deep acquisition method to obtain specific impact information, and the specific impact information is the difference consequence.

[0009] Furthermore, the relationship acquisition method includes: presetting the number of parts with the same parameters to obtain the processing number, extracting the past growth process information with the same corresponding parameters in the past growth process information in the information library to obtain a number of growth information to be processed, classifying the several growth information to be processed based on the processing number to obtain the target category and the processing growth information corresponding to the target category, extracting the nanotube performance information of the processing growth information based on the correlation in the information library to obtain the processing performance, extracting the processing growth information in the target category to obtain the reference growth information, extracting the nanotube performance information of the reference growth information to obtain the reference performance, obtaining the difference between the several reference growth information to obtain the difference information, obtaining the difference between the processing performance of the reference growth information that generates the difference information to obtain the impact information, and integrating the difference information and the impact information to obtain the consequence information.

[0010] Furthermore, the depth acquisition method includes: splitting the target influence information to obtain a number of sub-influence information, determining the corresponding previous nanotube growth information based on the sub-influence information to obtain two boundary growth information, obtaining the parameter difference in the two boundary growth information to obtain the target size, integrating all target sizes to obtain a target set, traversing the target set with the difference size to find the target size closest to the difference size to obtain the selected size, and determining the sub-influence information based on the selected size to obtain specific influence information.

[0011] Furthermore, the optimization method includes: determining solution information based on differential consequences, determining real-time growth progress, eliminating real-time production progress from target growth information to obtain subsequent growth information, judging whether there are adjustable parameters in the subsequent growth information that are associated with the solution information to obtain optimization results, when the optimization result feedback is that there are adjustable parameters in the subsequent growth information that are associated with the solution information, extracting the adjustable parameters associated with the solution information in the subsequent growth information to obtain target parameters, optimizing and adjusting the target parameters based on the impact information and the target parameters to obtain optimized parameters, adjusting the target parameters in the subsequent growth information to the optimized parameters to obtain optimized target growth information, and when the optimization result feedback is that there are no adjustable parameters in the subsequent growth information that are associated with the solution information, extracting the solution information and real-time growth progress to generate feedback information.

[0012] Furthermore, the updating method includes: recording the optimized target growth information and the nanotube performance produced by the optimized target growth information to obtain real-time nanotube growth information, storing the real-time nanotube growth information in an information library, recording the process of optimizing the target growth information to obtain an optimization process, and storing the optimization process in the information library.

[0013] Furthermore, the demand matching method includes: determining target performance based on user needs, traversing the information library based on the target performance to obtain a traversal result, when the traversal result feedback is that nanotube performance information corresponding to the target performance exists in the information library, extracting past nanotube growth information of the nanotube performance information corresponding to the target performance from the information library based on the correlation to obtain the target growth information, when the traversal result feedback is that nanotube performance information corresponding to the target performance does not exist in the information library, extracting nanotube performance information that exceeds the target performance from the information library based on the correlation to obtain selected nanotube performance information, and extracting past nanotube growth information of the nanotube performance information corresponding to the selected nanotube performance information from the information library based on the correlation to obtain the target growth information.

[0014] A nanotube growth parameter optimization control system based on deep learning uses the above-mentioned nanotube growth parameter optimization control method based on deep learning.

[0015] Compared with the prior art, the present invention has the following beneficial effects: This deep learning-based nanotube growth parameter optimization control method and system explores the difference between real-time environmental parameters and parameters in target growth information to obtain difference results. The difference results are analyzed by a set analysis method to obtain the impact on the nanotube caused by the representative parameter difference, that is, the difference consequence. The target growth information of the nanotube is optimized and adjusted according to the difference consequence by a set optimization method to obtain optimized target growth information, so as to facilitate the production of nanotubes that meet user needs. The adjustment and optimization process reduces the probability of slow search speed and easy falling into local optimum due to a huge parameter space, which is conducive to improving the overall efficiency of optimization. At the same time, the actual demand information and real-time environmental information are combined to make the nanotube growth parameter adjustment optimization meet user needs.

[0016] At the same time, based on the difference between the real-time environmental parameters and the target growth information, the error of the specific parameter equipment can be understood, so that the staff can further judge whether the parameter equipment is damaged. Through the set demand coordination method, the user can find the nanotube growth information corresponding to the user's needs in the information database to obtain the target growth information, so that when the user only has nanotube performance requirements, the user can be recommended a suitable growth process and parameters. When the user has his own nanotube growth information, the user's own nanotube growth information is extracted to obtain the target growth information. Through the set update method, the optimized target growth information and the performance information of the nanotubes produced are collected in real time and added to the information database to expand the resources in the information database and enrich the amount of information in the information database, so as to make more reasonable optimization and analysis.

[0017] At the same time, through the set depth acquisition method, the corresponding values of specific performance items affected by different parameter items can be determined to facilitate better optimization. The optimization method optimizes the growth information of nanotubes under the premise that optimization is possible so that the growth of nanotubes meets user needs. Under the premise that optimization is not possible, feedback information is generated, which can be specifically fed back to the user through the user's address information so that the user can understand the specific situation of nanotube production, and optimize the subsequent nanotube growth based on the information that cannot be optimized, so as to improve the efficiency of nanotube production and comprehensively optimize the production of nanotubes. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of the overall process structure of the present invention; Figure 2 Schematic diagram of the structure of the analysis method of the present invention; Figure 3 This is a structural diagram of embodiment 2 of the present invention; Figure 4 Schematic diagram of the depth acquisition method of the present invention. DETAILED DESCRIPTION

[0019] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0020] Different application scenarios have different performance requirements for nanotubes. For example, electronic devices require high conductivity, while composite materials require good mechanical properties. By optimizing parameters such as tube diameter, number of wall layers, and axial arrangement, the electronic band structure and conductivity of nanotubes can be controlled. For example, small-diameter carbon nanotubes have higher electron mobility, while axially arranged nanotubes exhibit excellent conductivity. Optimizing process parameters (such as low-temperature growth technology) can reduce energy consumption and defect density. For example, microwave plasma CVD can achieve efficient growth at around 600°C, while traditional methods require higher temperatures.

[0021] like Figure 1-Figure 4 As shown, the present invention provides a technical solution: a method for optimizing and controlling nanotube growth parameters based on deep learning, comprising: Information acquisition: Obtaining past nanotube growth information and user needs. Past nanotube growth information includes past growth process information and nanotube performance information; It should be noted that the past growth process information includes specific parameters and processes for producing nanotube growth information. The specific parameters may include temperature, air pressure, gas composition, atmosphere flow rate, catalyst concentration, etc. The nanotube performance information refers to the performance of the nanotubes, which may specifically include mechanical properties, electrical properties, thermal properties, and optical properties. User requirements refer to the user's specific demand information for producing nanotubes.

[0022] Information processing: Establish an information database to store past nanotube growth information, establish the correlation between past growth process information and nanotube performance information, and recommend target nanotube growth information to users based on user needs and in conjunction with the information database; It should be noted that by establishing an information database for storing past nanotube growth information, it is possible to provide storage for past nanotube growth information to facilitate subsequent information matching and information search operations. At the same time, by establishing correlations, it is possible to easily find nanotube performance information and past growth process information through past growth process information or nanotube performance information.

[0023] The invention is characterized by comprising: Growth information determination: determining whether the user needs to generate nanotube growth information to obtain a determination result. When the determination result indicates that the user needs to generate nanotube growth information, generating nanotube growth information that meets the user's needs based on the user's needs and the information database through a demand matching method to obtain target growth information; It should be noted that the set demand coordination method allows users to search for nanotube growth information corresponding to their needs in the information database to obtain target growth information, so that when the user only has nanotube performance requirements, the user can be recommended a suitable growth process and parameters. When the user has his own nanotube growth information, the user's own nanotube growth information is extracted to obtain the target growth information.

[0024] Monitoring status: monitor the real-time environmental parameters of nanotube growth, unify the time point, obtain the difference between the real-time environmental parameters and the parameters in the target growth information at the same time point, and obtain the difference results based on the difference results through analysis methods to obtain the difference consequences; It should be noted that the real-time environmental parameters for nanotube growth include multiple types, and the specific sub-items of the real-time environmental parameters correspond to the parameters in the nanotube growth process. Based on the same time point, the environmental parameters of the real-time growing nanotubes and the specific growth parameters are aligned. After alignment, the deviations due to the environmental parameters are found to obtain the difference results. The difference information is specifically analyzed through the set analysis method to obtain the difference consequences. At the same time, through this stage, the real-time environmental parameters can be compared with the nanotube growth process information to determine whether there are deviations in the specific parameter equipment, so that the staff can adjust the parameter equipment in time.

[0025] Parameter optimization: Based on the difference consequences, the subsequent parameters in the target growth information are optimized and controlled by the optimization method to obtain the optimized target growth information; It should be noted that, according to the existing difference consequences, the subsequent parameters in the target growth information are optimized and controlled and adjusted by the set optimization method to obtain the optimized target growth information, so as to make the performance information of the produced nanotubes consistent with user needs.

[0026] Information output: Nanotube growth is performed based on the optimized target growth information; Feedback update: Based on the optimized target growth information, the information in the information database is supplemented through the update method to obtain an updated information database.

[0027] It should be noted that, through the set update method, the optimized target growth information and the performance information of the produced nanotubes are collected in real time and added to the information database to expand the resources in the information database and enrich the amount of information in the information database, so as to make more reasonable optimization and analysis.

[0028] Example 1: In a nanotube production line that requires the use of a nanotube growth parameter optimization control method, chemical vapor deposition is used to produce nanotubes. Past nanotube growth information can be obtained by collecting past production information of the nanotube production line. An information receiving interface is established to receive user demand information through the information receiving interface. An information repository is established to store past nanotube growth information. Before storage, a correlation between past growth process information and nanotube performance information is established based on the production system of the nanotube production line. During the operation of the method, it is determined whether the demand information in the information receiving interface is target growth information that needs to be recommended. If not, the target growth information is obtained directly based on the production information provided by the user. If required, the target growth information is obtained by searching the information repository for growth information corresponding to the user's demand based on the user's demand and the method.

[0029] The process of obtaining difference information based on the difference between the real-time environmental parameters and the parameters in the target growth information at the same time point is as follows: splitting the real-time environmental parameters to obtain several first parameter items, splitting the target growth information to obtain several second parameter items, comparing the first parameter items and the second parameter items to obtain comparison results, extracting the comparison results and feeding them back as the second parameter items in the second parameter items that are different from the first parameter items and the size of the difference to obtain difference information.

[0030] It should be noted that the difference information specifically refers to the parameter differences between the two at the same time point. For example, the parameter temperature needs to be set to 750°C, but the measured real-time environmental parameter is that the reaction chamber temperature is 742°C. At this time, the parameter item that differs between the two is temperature, and the difference is 8°C.

[0031] like Figure 2 As shown, the analysis method includes: splitting the difference results to obtain difference items and difference sizes, exploring the performance impact caused by differences in different growth parameters through a relationship acquisition method based on the information library to obtain consequence information, the consequence information includes difference information and impact information corresponding to the difference information, performing information matching in the difference information based on the difference items to obtain a matching result, extracting the corresponding impact information based on the matching result to obtain target impact information, judging the specific details of the target impact information through a deep acquisition method based on the difference size and the target impact information to obtain specific impact information, and the specific impact information is the difference consequence.

[0032] It should be noted that the performance impact caused by differences in different growth parameters is explored through the set relationship acquisition method to obtain consequence information. Specifically, it can be understood as obtaining information on several past growth processes with differences in single or multiple parameters, judging the differences in the nanotube performance information, and obtaining the impact of specific parameters on specific performance items in the nanotube performance information. By obtaining the consequence information, it is convenient to obtain specific detailed impact information through the subsequent set depth acquisition method, so that the optimization method can be better carried out. Through the set depth acquisition method, the specific impact details are obtained in combination with the specific difference size to obtain specific impact information. It can be understood as obtaining the specific performance items affected by the parameter items with differences through the upper half of the analysis method, and through the set depth acquisition method, the corresponding values of the specific performance items affected by the parameter items with differences can be judged to facilitate better optimization.

[0033] like Figure 2 As shown, the relationship acquisition method includes: presetting the number of parts with the same parameters to obtain the processing number, extracting the past growth process information with the same corresponding parameters in the past growth process information in the information library to obtain a number of growth information to be processed, classifying the several growth information to be processed based on the processing number to obtain the target category and the processing growth information corresponding to the target category, extracting the nanotube performance information of the processing growth information based on the correlation in the information library to obtain the processing performance, extracting the processing growth information in the target category to obtain the reference growth information, extracting the nanotube performance information of the reference growth information to obtain the reference performance, obtaining the difference between the several reference growth information to obtain the difference information, obtaining the difference between the processing performance of the reference growth information that generates the difference information to obtain the impact information, and integrating the difference information and the impact information to obtain the consequence information.

[0034] Example 2: The processing quantity is 1, 2, 3, 4, 5, 6 and 7. Any previous growth process information in the information library is selected as the original matching object. The original matching object is traversed through the information library to find the previous growth process information with the same parameter part and the same parameter value to obtain the growth information to be processed. When there is a single same parameter part in the growth information to be processed, and the specific value of the single same parameter part is the same, it is the target analogy with the processing quantity of 1. And so on, such as Figure 3 As shown, Figure 3 a represents the target category where the growth information to be processed is classified into 1. Figure 3 b represents the target category of the growth information to be processed, which is 2 in number of processing. Figure 3 The corresponding upper and lower blocks represent the same parameters, and their shaded parts are specific values. The corresponding upper and lower shaded parts are the same values.

[0035] It should be noted that the processing quantity is specific quantity information, specifically including single or multiple. The specific processing quantity can be obtained according to the specific quantity of parameters. For example, the processing quantity can be 1, 2, 3, 4, etc. The process of extracting the past nanotube growth information with the same corresponding parameters in the information library to obtain several growth information to be processed is to select the past nanotube growth information with the same parameters and the same specific values of the same parameters to obtain the growth information to be processed, and classify the growth information to be processed according to the processing quantity. The classification processing can facilitate multi-threaded processing of data information to improve the efficiency of information processing. The specific process is to classify the past nanotube growth information with the same parameters and the same specific values of the same parameters according to the number of their same parameters. The number of specific target categories is consistent with the processing quantity. By obtaining the differences between the growth information and the differences in its nanotube performance, the impact information caused by the differences in the reaction can be obtained.

[0036] like Figure 4 As shown, the depth acquisition method includes: splitting the target influence information to obtain several sub-influence information, determining the corresponding previous nanotube growth information based on the sub-influence information to obtain two boundary growth information, obtaining the parameter difference between the two boundary growth information to obtain the target size, integrating all target sizes to obtain a target set, traversing the target set with the difference size to find the target size closest to the difference size to obtain the selected size, and determining the sub-influence information based on the selected size to obtain specific influence information.

[0037] It should be noted that the number of target impact information is single or multiple. The nanotube growth information that generates the sub-influence information is determined based on the sub-influence information to obtain two boundary growth information. The sub-influence information is the result of the performance comparison of the two growth information. The parameter gap between the two boundary growth information is obtained to obtain the target size. The target size here includes the specific name and specific value of its parameter. The target set includes multiple target sizes and may also include a single target size. The sub-influence information is determined based on the selected size to obtain the specific impact information. This process, that is, the target size closest to the difference size is selected in the target set through the difference size to obtain the selected size. By determining the selected size, the specific impact information can be estimated, that is, the specific difference between the subsequent growth of the nanotube and the user's required performance.

[0038] like Figure 1 As shown, the optimization method includes: determining solution information based on differential consequences, determining real-time growth progress, eliminating real-time production progress from target growth information to obtain subsequent growth information, judging whether there are adjustable parameters in the subsequent growth information that are associated with the solution information to obtain optimization results, when the optimization result feedback is that there are adjustable parameters in the subsequent growth information that are associated with the solution information, extracting the adjustable parameters associated with the solution information in the subsequent growth information to obtain target parameters, optimizing and adjusting the target parameters based on the impact information and the target parameters to obtain optimized parameters, adjusting the target parameters in the subsequent growth information to the optimized parameters to obtain optimized target growth information, and when the optimization result feedback is that there are no adjustable parameters in the subsequent growth information that are associated with the solution information, extracting the solution information and the real-time growth progress to generate feedback information.

[0039] Example 3: A differential consequence identification model is established. The function of the differential consequence identification model is to output information on solving differential consequences according to specific differential consequences to obtain solution information. Specifically, performance item differences and parameter differences are collected to obtain training data, parameter differences in the training data are marked, and a deep learning model is selected as the model matrix. The training data is imported into the model matrix for model training to obtain an initial model, and verification information is determined. The verification information includes verification performance item differences and verification parameter differences. The verification performance item differences are imported into the deep learning model to obtain exported results, and the exported results are compared with the verification parameters to obtain comparison results. According to the comparison results, the initial model is optimized and adjusted to obtain a differential consequence identification model.

[0040] It should be noted that the process of determining solution information based on differential consequences, that is, obtaining solution information based on parameters associated with the consequences according to the specific consequences determined in the differential consequences, can be specifically determined by training a dedicated training model based on the differential consequences. Through the set optimization method, the growth information of the nanotubes is optimized under the premise that it can be optimized, so that the growth of the nanotubes meets the user's needs. Under the premise that it cannot be optimized, feedback information is generated, which can be specifically fed back to the user through the user's address information, so that the user can understand the specific situation of the nanotube production, and the subsequent nanotube growth is optimized according to the information that cannot be optimized, so as to improve the efficiency of nanotube production and comprehensively optimize the production of nanotubes.

[0041] Example 4: The influence of specific parameters and performance is explored through the relationship acquisition method. Increasing the temperature can increase the deposition rate and diameter. Increasing the NH3 flow rate can improve the nucleation of metal nickel and increase the diameter. Adjusting the pressure can change the gas diffusion rate and affect the deposition rate. When the real-time environmental parameters are measured as follows: temperature: 700°C, gas flow rate: O250sccm, NH330sccm, pressure: 5Torr, real-time diameter measured: 45nm (deviation 5nm), real-time length: 8μm (deviation 2μm), nucleation rate: 2 per second, growth rate: 0.8μm / h, the parameters in the target growth information are adjusted to: temperature: 73 ... Speed: O250sccm, NH340sccm, pressure: 5Torr. The difference between the parameters and the growth information is temperature and gas flow rate. According to the difference in parameter items, the impact information of the difference information is locked. The impact information of temperature and gas flow rate is the growth rate and diameter. The subsequent specific optimization process goals are: increase the temperature (recommended range: 700-750°C), adjust the gas flow rate (increase the NH3 flow to 40sccm), or adjust the pressure. Increasing the temperature and adjusting the gas flow rate are the optimized parameters, that is, the optimized target growth information. The optimized target growth information is used to improve the diameter and growth rate of the nanotubes.

[0042] like Figure 1 As shown, the updating method includes: recording the optimized target growth information and the nanotube performance produced by the optimized target growth information to obtain real-time nanotube growth information, storing the real-time nanotube growth information in an information library, recording the process of optimizing the target growth information to obtain an optimization process, and storing the optimization process in the information library.

[0043] It should be noted that by recording the optimized target growth information and the performance of the optimized nanotubes to obtain real-time nanotube growth information, and storing the real-time nanotube growth information in the information database, the information richness of the information database can be improved to achieve the effect of continuous learning, and the presence of different parameters with the same difference consequences in the impact information can be added to improve the accuracy of subsequent optimization and determination of impact information. By recording the optimization process in the information database, corresponding matching can be performed directly in the future. When the same target growth information and the same difference information are available, the optimization process can be directly output for optimization.

[0044] like Figure 1 As shown, the demand matching method includes: determining the target performance based on user demand, traversing the information library based on the target performance to obtain a traversal result, when the traversal result feedback is that the information library contains nanotube performance information corresponding to the target performance, extracting the previous nanotube growth information of the nanotube performance information corresponding to the target performance from the information library based on the correlation to obtain the target growth information, when the traversal result feedback is that the information library does not contain the nanotube performance information corresponding to the target performance, extracting the nanotube performance information exceeding the target performance from the information library based on the correlation to obtain the selected nanotube performance information, and extracting the previous nanotube growth information of the nanotube performance information corresponding to the selected nanotube performance information from the information library based on the correlation to obtain the target growth information.

[0045] It should be noted that, by setting the demand matching method, the performance information of the nanotubes to be produced is determined according to the user's needs to obtain the target performance, and the traversal result is obtained by traversing the information library according to the target performance. Based on the traversal result, it is determined whether the corresponding target growth information can be generated according to the user's needs. At the same time, the process of generating the target growth information can also be determined by a dedicated model. By inputting the nanotube performance requirements and outputting the corresponding nanotube growth information, the efficiency of the user in determining the target growth information can be improved by setting the demand matching method.

[0046] Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is limited by the accompanying embodiments and their equivalents.

Claims

1. A method for optimizing and controlling nanotube growth parameters based on deep learning, comprising: Information acquisition: Obtaining past nanotube growth information and user needs. Past nanotube growth information includes past growth process information and nanotube performance information; Information processing: Establish an information database to store past nanotube growth information, establish the correlation between past growth process information and nanotube performance information, and recommend target nanotube growth information to users based on user needs and in conjunction with the information database; The invention is characterized by comprising: Growth information determination: determining whether the user needs to generate nanotube growth information to obtain a determination result. When the determination result indicates that the user needs to generate nanotube growth information, generating nanotube growth information that meets the user's needs based on the user's needs and the information database through a demand matching method to obtain target growth information; Monitoring status: monitor the real-time environmental parameters of nanotube growth, unify the time point, obtain the difference between the real-time environmental parameters and the parameters in the target growth information at the same time point, and obtain the difference results based on the results through analysis methods; Parameter optimization: Based on the difference consequences, the subsequent parameters in the target growth information are optimized and controlled by the optimization method to obtain the optimized target growth information; Information output: Nanotube growth is performed based on the optimized target growth information; Feedback update: Based on the optimized target growth information, the information in the information database is supplemented through the update method to obtain an updated information database.

2. The method for optimizing and controlling nanotube growth parameters based on deep learning according to claim 1, characterized in that: The process of obtaining difference information based on the difference between the real-time environmental parameters and the parameters in the target growth information at the same time point is as follows: splitting the real-time environmental parameters to obtain several first parameter items, splitting the target growth information to obtain several second parameter items, comparing the first parameter items and the second parameter items to obtain comparison results, extracting the comparison results and feeding them back as the second parameter items in the second parameter items that are different from the first parameter items and the size of the difference to obtain difference information.

3. The method for optimizing and controlling nanotube growth parameters based on deep learning according to claim 1, characterized in that: The analysis method includes: splitting the difference results to obtain difference items and difference sizes, exploring the performance impact caused by differences in different growth parameters through a relationship acquisition method based on an information library to obtain consequence information, the consequence information includes difference information and impact information corresponding to the difference information, performing information matching in the difference information based on the difference items to obtain a matching result, extracting the corresponding impact information based on the matching result to obtain target impact information, judging the specific details of the target impact information through a deep acquisition method based on the difference size and the target impact information to obtain specific impact information, and the specific impact information is the difference consequence.

4. The method for optimizing and controlling nanotube growth parameters based on deep learning according to claim 3, characterized in that: The relationship acquisition method includes: presetting the number of parts with the same parameters to obtain the processing number, extracting the past growth process information with the same corresponding parameters in the past growth process information in the information library to obtain a number of growth information to be processed, classifying the several growth information to be processed based on the processing number to obtain the target category and the processing growth information corresponding to the target category, extracting the nanotube performance information of the processing growth information based on the correlation in the information library to obtain the processing performance, extracting the processing growth information in the target category to obtain the reference growth information, extracting the nanotube performance information of the reference growth information to obtain the reference performance, obtaining the differences between the several reference growth information to obtain the difference information, obtaining the differences between the processing performances of the reference growth information that generated the difference information to obtain the impact information, and integrating the difference information and the impact information to obtain the consequence information.

5. The method for optimizing and controlling nanotube growth parameters based on deep learning according to claim 3, characterized in that: The depth acquisition method includes: splitting the target influence information to obtain a plurality of sub-influence information, determining the corresponding previous nanotube growth information based on the sub-influence information to obtain two boundary growth information, obtaining the parameter difference between the two boundary growth information to obtain the target size, integrating all target sizes to obtain a target set, traversing the target set with the difference size to find the target size closest to the difference size to obtain the selected size, and determining the sub-influence information based on the selected size to obtain specific influence information.

6. The method for optimizing and controlling nanotube growth parameters based on deep learning according to claim 1, characterized in that: The optimization method includes: determining solution information based on differential consequences, determining real-time growth progress, eliminating real-time production progress from target growth information to obtain subsequent growth information, judging whether there are adjustable parameters in the subsequent growth information that are associated with the solution information to obtain optimization results, when the optimization result feedback shows that there are adjustable parameters in the subsequent growth information that are associated with the solution information, extracting the adjustable parameters associated with the solution information in the subsequent growth information to obtain target parameters, optimizing and adjusting the target parameters based on the impact information and the target parameters to obtain optimized parameters, adjusting the target parameters in the subsequent growth information to the optimized parameters to obtain optimized target growth information, and when the optimization result feedback shows that there are no adjustable parameters in the subsequent growth information that are associated with the solution information, extracting the solution information and the real-time growth progress to generate feedback information.

7. The method for optimizing and controlling nanotube growth parameters based on deep learning according to claim 1, characterized in that: The updating method includes: recording optimized target growth information and nanotube performance produced by the optimized target growth information to obtain real-time nanotube growth information, storing the real-time nanotube growth information in an information library, recording the process of optimizing the target growth information to obtain an optimization process, and storing the optimization process in the information library.

8. The method for optimizing and controlling nanotube growth parameters based on deep learning according to claim 1, characterized in that: The demand matching method includes: determining target performance based on user needs, traversing an information database based on the target performance to obtain a traversal result; when the traversal result feedback indicates that nanotube performance information corresponding to the target performance exists in the information database, extracting past nanotube growth information of the nanotube performance information corresponding to the target performance from the information database based on correlation to obtain target growth information; when the traversal result feedback indicates that nanotube performance information corresponding to the target performance does not exist in the information database, extracting nanotube performance information exceeding the target performance from the information database based on correlation to obtain selected nanotube performance information; and extracting past nanotube growth information of the nanotube performance information corresponding to the selected nanotube performance information from the information database based on correlation to obtain target growth information.

9. A nanotube growth parameter optimization control system based on deep learning, characterized by: A nanotube growth parameter optimization control method based on deep learning as described in any one of claims 1 to 8 is used.

Images