Self-adaptive carbon nanotube growth control scheme and system based on AI deep learning

Abstract

The invention discloses a self-adaptive carbon nanotube growth control scheme and system based on AI deep learning, and relates to the technical field of nano material manufacturing and regulation. Comprising the following steps: information acquisition: acquiring variable information of carbon nanotube growth and user requirements; and reference construction: generating carbon nanotube growth parameters under different lithium ion battery performance indexes through a reference library generation method to obtain a reference library. The reference library for storing the basic growth parameters and the basic battery performance is generated through the set reference library generation method, and the target relation between the single variable of the basic growth parameters and the basic battery performance is judged through the set recognition method. And matching the target growth parameters meeting the user requirements for the user according to the user requirements and the target relationship by matching the set matching adjustment method with the reference library, and adaptively formulating the target growth parameters meeting the user requirements for the user so as to reduce the workload of the user and improve the production and preparation efficiency of the carbon nanotubes.

Description

Technical Field

[0001] The present invention relates to the technical field of nanomaterial manufacturing and regulation, and specifically to an adaptive carbon nanotube growth control scheme and system based on AI deep learning. Background Art

[0002] Carbon nanotubes are nanoscale tubular structures composed of carbon atoms. They are widely used in materials science, electronic technology, drug delivery and other fields due to their unique physical, chemical and mechanical properties. The growth process of carbon nanotubes is usually carried out by chemical vapor deposition. In the field of new energy, lithium-ion batteries are widely used as high-efficiency storage devices. Carbon nanotubes are regarded as ideal candidates for negative electrode materials of lithium-ion batteries due to their excellent conductivity and specific surface area.

[0003] The carbon nanotube manufacturing device and carbon nanotube manufacturing method with patent publication number CN116600884A include a cylindrical reactor body, in which there is a containing part, which is a space where a reaction occurs; and a distribution plate, which is located below the containing part of the reactor body to distribute the reaction gas supplied to the containing part, wherein the reactor body includes: a lower reactor; an upper reactor, which is formed so that its diameter is larger than that of the lower reactor; and an expansion part, which connects the upper reactor to the lower reactor and has a gradually expanding diameter.

[0004] In the customized production scenario of negative electrode materials in high-performance lithium-ion batteries, the customization technology in the preparation and growth process of carbon nanotubes in the prior art is relatively cumbersome, and workers are often required to set parameters according to their needs, which leads to low efficiency in the preparation of customized carbon nanotubes. If the growth parameters cannot be customized, the diameter, length and structure of the produced carbon nanotubes are all difficult to adjust and cannot be optimized for specific applications. This may cause the produced carbon nanotubes to fail to meet specific performance requirements and reduce the market competitiveness of the products. At the same time, the prior art lacks real-time monitoring and optimization feedback mechanisms, and the data of carbon nanotube products cannot be effectively used to adjust the growth parameters, which leads to low customized adaptability, and thus the present invention is proposed. Summary of the invention

[0005] The purpose of the present invention is to provide an adaptive carbon nanotube growth control solution and system based on AI 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 solutions: an adaptive carbon nanotube growth control solution based on AI deep learning, the solution comprising: Information acquisition: Obtain variable information and user needs for carbon nanotube growth; Reference construction: Generate a reference library of carbon nanotube growth parameters under different lithium-ion battery performance indicators through a reference library generation method, and the reference library includes basic battery performance and basic growth parameters; Information processing: The relationship between the variables in the basic growth parameters and the performance in the basic battery performance is determined by the identification method to obtain the target relationship, which includes a first target relationship reflecting the relationship between a single variable and the performance and a second target relationship reflecting the relationship between multiple variables and the performance. The variables in the basic growth parameters are consistent with the variable information, and the corresponding relationship between the basic battery performance and the basic growth parameters is established; Configuration selection: Use the matching adjustment method to find the basic battery performance corresponding to the user's needs in the reference library and extract the basic growth parameters according to the corresponding relationship to optimize and adjust the target growth parameters and adjustment direction. The adjustment direction includes the final relationship, target difference and added value; Information output: growing carbon nanotubes based on target growth parameters; Monitoring feedback: Based on the adjustment direction, the judgment method is used to judge whether the carbon nanotubes under the target growth parameters meet the user's needs, and the target growth parameters that do not meet the user's needs are continuously optimized to obtain the optimized growth parameters and result performance, and the result performance and optimized growth parameters are stored in the reference library; The reference library generation method includes: presetting benchmark growth parameters, producing carbon nanotubes based on the benchmark growth parameters and assembling them into lithium-ion batteries to obtain benchmark lithium-ion batteries, obtaining the performance of the benchmark lithium-ion batteries to obtain benchmark performance, adjusting a single or multiple variables in the benchmark growth parameters by a numerical addition method to obtain different growth parameters to obtain a number of derived growth parameters, producing carbon nanotubes based on the several derived growth parameters and assembling them into lithium-ion batteries to obtain a target lithium-ion battery, obtaining the performance of the benchmark lithium-ion batteries to obtain a target performance, the benchmark growth parameters and the derived growth parameters are basic growth parameters, the benchmark performance and the target performance are basic battery performance, and establishing a reference library for storing basic growth parameters and basic battery performance.

[0007] Furthermore, the numerical addition method includes: presetting a fixed value and an adjustment factor, the fixed value includes a positive value and a negative value, adjusting a single variable to be adjusted in the benchmark growth parameter through a numerical addition formula based on the fixed value, the adjustment factor and the benchmark growth parameter to obtain a plurality of adjustment variables, and replacing a single variable or multiple variables in the benchmark growth parameter with the adjustment variable to obtain a derived growth parameter, and the numerical addition formula is: , is the adjustment variable, is a single variable to be adjusted for the baseline growth parameter, is the regulating factor, is a fixed value.

[0008] Furthermore, the identification method includes: taking the baseline growth parameters and basic battery performance as the baseline, extracting the basic growth parameters for single variable adjustment in the reference library to obtain the first analysis growth parameters, extracting the basic battery performance corresponding to the first analysis growth parameters in the reference library based on the corresponding relationship to obtain the first analysis battery performance, comparing the first analysis battery performance with the baseline battery performance to obtain the first difference value, comparing the baseline growth parameters with the first analysis growth parameters to obtain the first variable value, integrating the first difference value and the first variable value to obtain the first target relationship, extracting the basic growth parameters for multiple variable adjustment in the reference library to obtain the second analysis growth parameters, extracting the basic battery performance corresponding to the second analysis growth parameters in the reference library based on the corresponding relationship to obtain the second analysis battery performance, comparing the second analysis battery performance with the baseline battery performance to obtain the second difference value, comparing the baseline growth parameters with the second analysis growth parameters to obtain the second variable value, integrating the second difference value and the second variable value to obtain the second target relationship, and integrating the first target relationship and the second target relationship to obtain the target relationship.

[0009] Furthermore, the matching adjustment method includes: determining the required battery performance or the required growth parameter based on user needs, when the user demand is the required growth parameter, the target growth parameter is the required growth parameter, when the user demand is the required battery performance, traversing the basic battery performance in the reference library based on the required battery performance to obtain a matching result, the matching result is a successful match and a failed match, when the matching result is a successful match, extracting the basic battery performance consistent with the required battery performance in the reference library to obtain the target battery performance, extracting the basic growth parameters corresponding to the target battery performance in the reference library based on the corresponding relationship to obtain the target growth parameters, when the matching result is a failed match, extracting two basic battery performances containing the required battery performance in the reference library to obtain two endpoint battery performances, extracting the basic growth parameters corresponding to the two endpoint battery performances in the reference library based on the corresponding relationship to obtain two endpoint growth parameters, and optimizing and adjusting the two endpoint growth parameters through the adjustment method based on the target relationship to obtain the target growth parameters.

[0010] Furthermore, the adjustment method includes: presetting a growth parameter threshold, subtracting the two endpoint battery performance from the required battery performance to obtain two differences, selecting the difference with the smallest value in the two differences to obtain a target difference, determining the number of sub-performances in the target difference whose performance values ​​are not 0 to obtain a target number, locking the performance relationship between a single or multiple variables and the target number in the target relationship based on the target number to obtain several sub-target relationships, extracting sub-target relationships that match the sub-performance in the target difference from the several sub-target relationships to obtain a final relationship, obtaining an added value by calculating a proportional relationship based on the final relationship and the target difference, adding the added value to the endpoint growth parameter corresponding to the target difference to obtain the target growth parameter, and recording the final relationship, the target difference and the added value to obtain the adjustment direction.

[0011] Furthermore, the judgment method includes: monitoring the performance of the finished lithium-ion battery composed of carbon nanotubes to obtain the result performance, judging whether the result performance is consistent with the user demand, when the result performance is inconsistent with the user demand, optimizing the target growth parameters by the optimization method to obtain the optimized growth parameters, growing carbon nanotubes based on the optimized growth parameters, and continuing to monitor the performance of the finished lithium-ion battery composed of the optimized carbon nanotubes to obtain the final performance, judging whether the final performance is consistent with the user demand, when the final performance is inconsistent with the user demand, optimizing the optimized growth parameters by the optimization method until the performance of the finished lithium-ion battery composed of the optimized carbon nanotubes is consistent with the user demand.

[0012] Furthermore, the optimization method includes: presetting a difference range and a reduction number, obtaining feedback address information, dynamically accumulating and reducing the added value after optimizing the number of times based on the reduction number to obtain a dynamic value, obtaining the difference between the result performance and the required battery performance to obtain a finished product difference, judging whether the finished product difference is within the difference range, and when the finished product difference is within the difference range, the finished product difference is fed back to the user based on the feedback address information, and the user decides whether to optimize, and when the finished product difference is outside the difference range or the user decides to optimize, judging the relationship between the finished product difference and the target difference, and when the finished product difference is greater than the target difference, increasing the endpoint growth parameter corresponding to the target difference based on the dynamic value to obtain the optimized growth parameter, and when the finished product difference is less than the target difference, reducing the endpoint growth parameter corresponding to the target difference based on the dynamic value to obtain the optimized growth parameter, and obtaining the optimized growth parameter. The final performance is obtained by obtaining the performance of the finished lithium-ion battery composed of carbon nanotubes with the required parameters, the difference between the final performance and the required battery performance is obtained, and the final difference is determined whether the final difference is within the difference range. When the final difference is within the difference range, the final difference is fed back to the user based on the feedback address information, and the user decides whether to optimize. When the final difference is outside the difference range or the user decides to optimize, the relationship between the final difference and the target difference is determined. When the final difference is greater than the target difference, the final growth parameters are obtained based on the optimized growth parameters corresponding to the finished product difference when the dynamic numerical value is reduced. When the final difference is less than the target difference, the final growth parameters are obtained based on the target growth parameters corresponding to the finished product difference when the dynamic numerical value is increased. When the performance of the finished lithium-ion battery composed of carbon nanotubes with the optimized growth parameters is consistent with the user's needs, the optimization is stopped.

[0013] An adaptive carbon nanotube growth control system based on AI deep learning uses the above-mentioned adaptive carbon nanotube growth control scheme based on AI deep learning.

[0014] Compared with the prior art, the present invention has the following beneficial effects: This adaptive carbon nanotube growth control scheme and system based on AI deep learning generates a reference library for storing basic growth parameters and basic battery performance through a set reference library generation method, determines the target relationship between a single variable of the basic growth parameter and the basic battery performance through a set identification method, matches target growth parameters that meet user needs for users based on user needs and the target relationship through a set matching adjustment method in conjunction with the reference library, and adaptively formulates target growth parameters that meet user needs for users, so as to reduce the user's workload and improve the production and preparation efficiency of carbon nanotubes.

[0015] At the same time, through the set judgment method, a feedback interface can be added to obtain the performance of the finished lithium-ion battery composed of carbon nanotubes under the target growth parameter conditions to obtain the result performance. The process of obtaining the result performance can be obtained through user feedback to facilitate monitoring whether the result performance is consistent with user needs. When it is inconsistent, the target growth parameters are continuously optimized through the optimization method until the performance of the finished lithium-ion battery composed of carbon nanotubes is consistent with user needs, and the optimized growth parameters and the resulting performance are stored in the reference library to expand the reference range of the reference library.

[0016] At the same time, by setting the numerical addition method, different target growth parameters can be obtained regularly, which can facilitate users to judge the relationship between the change of target growth parameters and battery performance, and the rules are formulated by users according to actual usage. By setting dynamic numerical values, the number of adjustments each time can be continuously reduced during the optimization process to increase the probability of accurately obtaining the final growth parameters consistent with user needs. By setting the difference range, users can choose whether to optimize or not, so as to improve the preparation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic diagram of the reference construction and information processing structure of the present invention; Figure 2 It is a schematic diagram of the configuration selection, information output and monitoring feedback structure of the present invention; Figure 3 It is a structural schematic diagram of the matching adjustment method of the present invention; Figure 4 It is a structural schematic diagram of the demand battery performance matching process of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0019] In the customized production scenario of negative electrode materials in high-performance lithium-ion batteries, carbon nanotubes of different diameters, shapes and structures can be customized by precisely controlling the growth conditions of carbon nanotubes to improve the capacity, charging speed and cycle life of the battery. The present invention adaptively provides growth parameters of carbon nanotubes corresponding to user needs according to user needs, so as to facilitate the production of required carbon nanotubes, and thus facilitate the customization of negative electrode materials for lithium-ion batteries.

[0020] like Figure 1-Figure 4 As shown, the present invention provides a technical solution: an adaptive carbon nanotube growth control solution based on AI deep learning, the solution comprising: Information acquisition: Obtain variable information and user needs for carbon nanotube growth; Reference construction: Generate a reference library of carbon nanotube growth parameters under different lithium-ion battery performance indicators through a reference library generation method, and the reference library includes basic battery performance and basic growth parameters; Information processing: The relationship between the variables in the basic growth parameters and the performance in the basic battery performance is determined by the identification method to obtain the target relationship, which includes a first target relationship reflecting the relationship between a single variable and the performance and a second target relationship reflecting the relationship between multiple variables and the performance. The variables in the basic growth parameters are consistent with the variable information, and the corresponding relationship between the basic battery performance and the basic growth parameters is established; Configuration selection: Use the matching adjustment method to find the basic battery performance corresponding to the user's needs in the reference library and extract the basic growth parameters according to the corresponding relationship to optimize and adjust the target growth parameters and adjustment direction. The adjustment direction includes the final relationship, target difference and added value; Information output: growing carbon nanotubes based on target growth parameters; Monitoring feedback: Based on the adjustment direction, the judgment method is used to judge whether the carbon nanotubes under the target growth parameters meet the user's needs, and the target growth parameters that do not meet the user's needs are continuously optimized to obtain the optimized growth parameters and result performance, and the result performance and optimized growth parameters are stored in the reference library; It should be noted that, in the information acquisition stage, variable information of carbon nanotube growth can be obtained through online retrieval, for example, carbon nanotubes are prepared by chemical vapor deposition method, wherein the variable information of carbon nanotube growth includes reaction gas concentration ratio, temperature, catalyst, reaction time, pressure and oxygen concentration, etc., the variable information of carbon nanotube growth is the variable information in carbon nanotube growth parameters, and the user demand is the preparation demand of the user, such as the need to prepare lithium-ion batteries with specific performance indicators or the need to prepare carbon nanotubes under specific growth parameter conditions. In the reference construction stage, the reference library generation method set can be used to generate carbon nanotube growth parameters under different lithium-ion battery performance indicators to obtain a reference library, and the reference library stores basic battery performance and basic growth parameters. The reference library generation method set can be used to collect and obtain basic battery performance of different battery performance and basic growth parameters corresponding to the basic battery performance, so that the basic growth parameters can be directly referenced through the reference library according to user needs to obtain the target growth parameters, which plays a reference role. In the information processing stage, the relationship between the variables in the basic growth parameters and the performance in the basic battery performance is judged by the set recognition method, so that the relationship between the variables in the basic growth parameters and the performance in the basic battery performance can be determined according to the user needs. The target relationship cooperates with the reference library to adjust the growth parameters of user needs. By establishing a corresponding relationship, it is convenient to extract the corresponding basic growth parameters according to the basic battery performance or extract the corresponding basic battery performance according to the basic growth parameters. In the configuration selection stage, the corresponding basic battery performance can be found in the reference library according to the user's needs through the set matching adjustment method, and the basic growth parameters are optimized and adjusted according to the target relationship to obtain the target growth parameters required by the user. By generating the adjustment direction, it is convenient to optimize the target growth parameters in the future. In the information output stage, carbon nanotubes are prepared according to the provided target growth parameters. In the monitoring feedback stage, the judgment method is used to detect whether the carbon nanotubes produced under the target growth parameters meet the user's needs, and the target growth parameters of the carbon nanotubes that do not meet the user's needs are optimized to obtain the optimized growth parameters. In the carbon nanotube production process, a single or several sample carbon nanotubes can be produced under the target growth parameters. By analyzing the sample carbon nanotubes, it is determined whether it meets the user's needs. If it does not meet the user's needs, it will not be optimized, and if it does not meet the user's needs, it will be optimized. At the same time, the optimized growth parameters and the result performance are stored in the reference library to expand the reference range of the reference library for easy use.

[0021] The reference library generation method includes: presetting benchmark growth parameters, producing carbon nanotubes based on the benchmark growth parameters and assembling them into lithium-ion batteries to obtain benchmark lithium-ion batteries, obtaining the performance of the benchmark lithium-ion batteries to obtain benchmark performance, adjusting a single or multiple variables in the benchmark growth parameters by a numerical addition method to obtain different growth parameters to obtain a number of target growth parameters, producing carbon nanotubes based on a number of derived growth parameters and assembling them into lithium-ion batteries to obtain a target lithium-ion battery, obtaining the performance of the benchmark lithium-ion batteries to obtain target performance, the benchmark growth parameters and the derived growth parameters are basic growth parameters, the benchmark performance and the target performance are basic battery performance, and establishing a reference library for storing basic growth parameters and basic battery performance.

[0022] It should be noted that the baseline growth parameters are set by the user, and their specific role is to serve as the most basic growth parameter carrier. Usually, the middle growth parameter between the maximum growth parameter and the minimum growth parameter is selected, and the single or multiple variables in the baseline growth parameters are adjusted through the set numerical addition method to obtain the target growth parameters different from the baseline growth parameters, and obtain the carbon nanotubes under the target growth parameters and assemble them into lithium-ion batteries to obtain the target performance of the target lithium-ion battery. Through multiple adjustments and multiple performance acquisitions, the reference range of the reference library can be expanded. The more extensive the data in the reference library, the more accurate the subsequent matching process according to user needs. At the same time, the growth parameters and performance of previous lithium-ion batteries can also be obtained as basic growth parameters and basic battery performance and stored in the reference library.

[0023] The numerical addition method includes: presetting a fixed value and an adjustment factor, wherein the fixed value includes positive and negative values, adjusting a single variable to be adjusted in the baseline growth parameter through a numerical addition formula based on the fixed value, the adjustment factor and the baseline growth parameter to obtain a plurality of adjustment variables, and replacing a single variable or multiple variables in the baseline growth parameter with the adjustment variable to obtain a derived growth parameter, and the numerical addition formula is: , is the adjustment variable, is a single variable to be adjusted for the baseline growth parameter, is the regulating factor, is a fixed value.

[0024] It should be noted that the fixed value and the adjustment factor are determined according to the actual usage. The fixed value is a specific number, and the adjustment factor is a variable number, such as 1, 2, 3, etc. By changing the adjustment factor, more adjustment variables can be obtained to expand the reference range of the reference library. For example, when the temperature variable is adjusted, the adjustment variable is T. When the single variable to be adjusted of the benchmark growth parameter is 900°C, the fixed value is 10°C and -10°C, and the adjustment factor is 1, 2, 3, there are multiple adjustment variables at this time, specifically T=900-1×10 and T=900-1×(-10), T=900-2×10 and T=900-2×(-10), and T=900-3×10 and T=900-3×(-10). By setting the numerical addition method, different target growth parameters can be obtained regularly, which can facilitate users to judge the relationship between the change of the target growth parameter and the battery performance, and the rules are set by users according to actual usage.

[0025] like Figure 1 As shown, the identification method includes: taking the baseline growth parameters and the basic battery performance as the baseline, extracting the basic growth parameters for single variable adjustment in the reference library to obtain the first analysis growth parameters, extracting the basic battery performance corresponding to the first analysis growth parameters in the reference library based on the corresponding relationship to obtain the first analysis battery performance, comparing the first analysis battery performance with the baseline battery performance to obtain the first difference value, comparing the baseline growth parameters with the first analysis growth parameters to obtain the first variable value, integrating the first difference value and the first variable value to obtain the first target relationship, extracting the basic growth parameters for multiple variable adjustments in the reference library to obtain the second analysis growth parameters, extracting the basic battery performance corresponding to the second analysis growth parameters in the reference library based on the corresponding relationship to obtain the second analysis battery performance, comparing the second analysis battery performance with the baseline battery performance to obtain the second difference value, comparing the baseline growth parameters with the second analysis growth parameters to obtain the second variable value, integrating the second difference value and the second variable value to obtain the second target relationship, and integrating the first target relationship and the second target relationship to obtain the target relationship.

[0026] It should be noted that, through the set identification method, a first target relationship reflecting the impact of adjusting a single variable on battery performance and a second target relationship reflecting the impact of adjusting multiple variables on battery performance can be obtained, and the first analysis battery performance is compared with the benchmark battery performance to obtain the first difference value, and the second analysis battery performance is compared with the benchmark battery performance to obtain the second difference value, that is, the first analysis battery performance and the second analysis battery performance are subtracted from the benchmark battery information to obtain the first difference value and the second difference value. The specific process is to subtract the corresponding variable data items. Similarly, the comparison of the benchmark growth parameters with the first analysis growth parameters to obtain the first variable value and the comparison of the benchmark growth parameters with the second analysis growth parameters to obtain the second variable value are the same. By obtaining the difference value and the variable value, it is convenient to adjust the growth parameters to the target growth parameters required by the user according to the target relationship.

[0027] like Figure 2-Figure 4 As shown, the matching adjustment method includes: determining the required battery performance or the required growth parameter based on the user demand, when the user demand is the required growth parameter, the target growth parameter is the required growth parameter, when the user demand is the required battery performance, traversing the basic battery performance in the reference library based on the required battery performance to obtain a matching result, the matching result is a successful match and a failed match, when the matching result is a successful match, extracting the basic battery performance consistent with the required battery performance in the reference library to obtain the target battery performance, extracting the basic growth parameters corresponding to the target battery performance in the reference library based on the corresponding relationship to obtain the target growth parameters, when the matching result is a failed match, extracting two basic battery performances containing the required battery performance in the reference library to obtain two endpoint battery performances, extracting the basic growth parameters corresponding to the two endpoint battery performances in the reference library based on the corresponding relationship to obtain two endpoint growth parameters, optimizing and adjusting the two endpoint growth parameters through the adjustment method based on the target relationship to obtain the target growth parameters, Figure 4 The size of the middle circle represents the overall size of the battery performance.

[0028] It should be noted that user needs are divided into multiple types, specifically required battery performance or required growth parameters. When the user demand is the required growth parameter, that is, the user provides the target growth parameter by himself, and the required growth parameter is the target growth parameter. When the user demand is the required battery performance, the matching result is obtained by matching the basic battery performance in the reference library, and the next step is indicated according to the matching result. When the matching result feedback is a successful match, it means that there is a basic battery performance in the reference library that is consistent with the required battery performance. At this time, the basic growth parameter of the consistent basic battery performance is the target growth parameter. When the matching result feedback is a failed match, it means that there is no basic battery performance in the reference library that is consistent with the required battery performance. At this time, two basic battery performances including the required battery performance are extracted, that is, the required battery performance is between the battery performance range of the combination of the two basic battery performances, and the endpoint growth parameters of the endpoint battery performance are optimized and adjusted by the adjustment method to obtain the target growth parameters. Through the set matching adjustment method, the user's needs can be judged and analyzed, and different target growth parameters can be provided according to the user's needs. Through the set adjustment method, the target growth parameters that meet the user's needs can be adaptively formulated for the user to reduce the user's workload and improve the production and preparation efficiency of carbon nanotubes.

[0029] The adjustment method includes: presetting a growth parameter threshold, subtracting the two endpoint battery performance from the required battery performance to obtain two differences, selecting the difference with the smallest value in the two differences to obtain a target difference, determining the number of sub-performances whose performance values ​​in the target difference are not 0 to obtain a target number, locking the performance relationship between a single or multiple variables and the target number in a target relationship based on the target number to obtain several sub-target relationships, extracting sub-target relationships that match the sub-performance in the target difference from the several sub-target relationships to obtain a final relationship, obtaining an added value by calculating a proportional relationship based on the final relationship and the target difference, adding the added value to the endpoint growth parameter corresponding to the target difference to obtain the target growth parameter, and recording the final relationship, the target difference and the added value to obtain the adjustment direction.

[0030] It should be noted that the growth parameter threshold is determined according to actual usage, specifically the maximum growth parameter threshold, that is, when the target growth parameter exceeds the growth parameter threshold, the produced carbon nanotubes cannot be put into use or have a large number of defects, etc. By comparing the target growth parameter with the preset growth parameter threshold, a barrier can be provided for adjusting the target growth parameter so that the target growth parameter is within the normal range. The target difference is obtained by subtracting the smallest value of the two endpoint battery performance from the required battery performance. When there is an item with a value of 0 in the target difference, it means that a sub-performance of the endpoint battery performance is the same as a sub-performance of the required battery performance, and the sub-performance is not considered to reduce system occupancy. By judging the target difference The number of sub-performances whose performance values ​​are not 0 is used to obtain the target number. According to the target number, the performance relationship between a single or multiple variables and the target number is locked in the target relationship to obtain several sub-target relationships, so as to narrow the scope in advance for subsequent precise search and reduce the system occupancy of the search process. The sub-target relationship that matches the sub-performance in the target difference is extracted from several sub-target relationships to obtain the final relationship, that is, the target relationship whose sub-performance is consistent with the performance in the target difference is found in several sub-target relationships to obtain the final relationship. The process of adding the value by calculating the proportional relationship through the final relationship and the target difference includes the variable value and the difference value. By combining the target difference, the specific value for adjusting the variable, that is, the added value, can be calculated.

[0031] like Figure 2 As shown, the judgment method includes: monitoring the performance of the finished lithium-ion battery composed of carbon nanotubes to obtain the result performance, judging whether the result performance is consistent with the user demand, when the result performance is inconsistent with the user demand, optimizing the target growth parameters through the optimization method to obtain the optimized growth parameters, growing carbon nanotubes based on the optimized growth parameters, and continuing to monitor the performance of the finished lithium-ion battery composed of the optimized carbon nanotubes to obtain the final performance, judging whether the final performance is consistent with the user demand, when the final performance is inconsistent with the user demand, optimizing the optimized growth parameters through the optimization method until the performance of the finished lithium-ion battery composed of the optimized carbon nanotubes is consistent with the user demand.

[0032] It should be noted that, by setting the judgment method, a feedback interface can be added to obtain the performance of the finished lithium-ion battery composed of carbon nanotubes under the target growth parameter conditions to obtain the result performance. The process of obtaining the result performance can be obtained through user feedback to facilitate monitoring whether the result performance is consistent with user needs. When inconsistent, the target growth parameters are continuously optimized through the optimization method until the performance of the finished lithium-ion battery composed of carbon nanotubes is consistent with user needs.

[0033] The optimization method includes: presetting a difference range and a reduction number, obtaining a feedback address information, dynamically accumulating and reducing the added value after optimizing the number of times based on the reduction number to obtain a dynamic value, obtaining the difference between the result performance and the required battery performance to obtain a finished product difference, judging whether the finished product difference is within the difference range, and when the finished product difference is within the difference range, the finished product difference is fed back to the user based on the feedback address information, and the user decides whether to optimize, and when the finished product difference is outside the difference range or the user decides to optimize, judging the relationship between the finished product difference and the target difference, and when the finished product difference is greater than the target difference, based on the dynamic value, increasing the endpoint growth parameter corresponding to the target difference to obtain the optimized growth parameter, and when the finished product difference is less than the target difference, based on the dynamic value, reducing the endpoint growth parameter corresponding to the target difference to obtain the optimized growth parameter, and obtaining the carbon of the optimized growth parameter. The final performance is obtained based on the performance of the finished lithium-ion battery composed of nanotubes, the difference between the final performance and the required battery performance is obtained to obtain the final difference, and it is determined whether the final difference is within the difference range. When the final difference is within the difference range, the final difference is fed back to the user based on the feedback address information, and the user decides whether to optimize. When the final difference is outside the difference range or the user decides to optimize, the relationship between the final difference and the target difference is determined. When the final difference is greater than the target difference, the final growth parameters are obtained based on the optimized growth parameters corresponding to the finished product difference and the dynamic numerical reduction. When the final difference is less than the target difference, the final growth parameters are obtained based on the target growth parameters corresponding to the finished product difference and the dynamic numerical increase. When the performance of the finished lithium-ion battery composed of carbon nanotubes with the optimized growth parameters is consistent with the user's needs, the optimization is stopped.

[0034] It should be noted that the difference range and the reduction number are set by the user according to actual usage. The size of the reduction number should be as small as possible to facilitate more accurate optimization to obtain the final growth parameters consistent with user needs. The dynamic value is obtained by reducing the reduction number of the added value by the number of optimization times. Specifically, when the optimization number is the first time, the dynamic value is the added value minus the reduction number. When the optimization number is the second time, the dynamic value is the added value minus 2×the reduction number, and so on. By setting the dynamic value, the number of adjustments each time can be continuously reduced during the optimization process to increase the probability of accurately obtaining the final growth parameters consistent with user needs, which is convenient for use. The feedback address information is the user's address information, specifically the user's email, IP address, and telephone number. By setting the difference range, the user can choose whether to optimize or not, so as to improve the efficiency of preparation and facilitate use.

[0035] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is limited by the attached embodiments and their equivalents.

Claims

1. An adaptive carbon nanotube growth control scheme based on AI deep learning, characterized by: The scheme includes: Information acquisition: Obtain variable information and user needs for carbon nanotube growth; Reference construction: Generate a reference library of carbon nanotube growth parameters under different lithium-ion battery performance indicators through a reference library generation method, and the reference library includes basic battery performance and basic growth parameters; Information processing: The relationship between the variables in the basic growth parameters and the performance in the basic battery performance is determined by the identification method to obtain the target relationship, which includes a first target relationship reflecting the relationship between a single variable and the performance and a second target relationship reflecting the relationship between multiple variables and the performance. The variables in the basic growth parameters are consistent with the variable information, and the corresponding relationship between the basic battery performance and the basic growth parameters is established; Configuration selection: Use the matching adjustment method to find the basic battery performance corresponding to the user's needs in the reference library and extract the basic growth parameters according to the corresponding relationship to optimize and adjust the target growth parameters and adjustment direction. The adjustment direction includes the final relationship, target difference and added value; Information output: growing carbon nanotubes based on target growth parameters; Monitoring feedback: Based on the adjustment direction, the judgment method is used to judge whether the carbon nanotubes under the target growth parameters meet the user's needs, and the target growth parameters that do not meet the user's needs are continuously optimized to obtain the optimized growth parameters and result performance, and the result performance and optimized growth parameters are stored in the reference library; The reference library generation method includes: presetting benchmark growth parameters, producing carbon nanotubes based on the benchmark growth parameters and assembling them into lithium-ion batteries to obtain benchmark lithium-ion batteries, obtaining the performance of the benchmark lithium-ion batteries to obtain benchmark performance, adjusting a single or multiple variables in the benchmark growth parameters by a numerical addition method to obtain different growth parameters to obtain a number of derived growth parameters, producing carbon nanotubes based on the several derived growth parameters and assembling them into lithium-ion batteries to obtain a target lithium-ion battery, obtaining the performance of the benchmark lithium-ion batteries to obtain a target performance, the benchmark growth parameters and the derived growth parameters are basic growth parameters, the benchmark performance and the target performance are basic battery performance, and establishing a reference library for storing basic growth parameters and basic battery performance.

2. The adaptive carbon nanotube growth control scheme based on AI deep learning according to claim 1 is characterized in that: The numerical value addition method includes: presetting a fixed value and an adjustment factor, wherein the fixed value includes a positive value and a negative value, adjusting a single variable to be adjusted in the benchmark growth parameter through a numerical value addition formula based on the fixed value, the adjustment factor and the benchmark growth parameter to obtain a plurality of adjustment variables, and replacing a single variable or multiple variables in the benchmark growth parameter with the adjustment variable to obtain a derived growth parameter, wherein the numerical value addition formula is: , is the adjustment variable, is a single variable to be adjusted for the baseline growth parameter, is the regulating factor, is a fixed value.

3. The adaptive carbon nanotube growth control scheme based on AI deep learning according to claim 1 is characterized in that: The identification method includes: taking a benchmark growth parameter and a basic battery performance as a benchmark, extracting a basic growth parameter for single variable adjustment in a reference library to obtain a first analysis growth parameter, extracting a basic battery performance corresponding to the first analysis growth parameter in the reference library based on a corresponding relationship to obtain a first analysis battery performance, comparing the first analysis battery performance with the benchmark battery performance to obtain a first difference value, comparing the benchmark growth parameter with the first analysis growth parameter to obtain a first variable value, integrating the first difference value and the first variable value to obtain a first target relationship, extracting a basic growth parameter for multiple variable adjustments in the reference library to obtain a second analysis growth parameter, extracting a basic battery performance corresponding to the second analysis growth parameter in the reference library based on a corresponding relationship to obtain a second analysis battery performance, comparing the second analysis battery performance with the benchmark battery performance to obtain a second difference value, comparing the benchmark growth parameter with the second analysis growth parameter to obtain a second variable value, integrating the second difference value and the second variable value to obtain a second target relationship, and integrating the first target relationship and the second target relationship to obtain a target relationship.

4. The adaptive carbon nanotube growth control scheme based on AI deep learning according to claim 1 is characterized in that: The matching and adjustment method includes: determining the required battery performance or the required growth parameter based on the user demand; when the user demand is the required growth parameter, the target growth parameter is the required growth parameter; when the user demand is the required battery performance, traversing the basic battery performance in the reference library based on the required battery performance to obtain a matching result, and the matching result is a successful match and a failed match; when the matching result is a successful match, extracting the basic battery performance consistent with the required battery performance in the reference library to obtain the target battery performance; based on the corresponding relationship, extracting the basic growth parameters corresponding to the target battery performance in the reference library to obtain the target growth parameters; when the matching result is a failed match, extracting two basic battery performances including the required battery performance in the reference library to obtain two endpoint battery performances; based on the corresponding relationship, extracting the basic growth parameters corresponding to the two endpoint battery performances in the reference library to obtain two endpoint growth parameters; and optimizing and adjusting the two endpoint growth parameters through the adjustment method based on the target relationship to obtain the target growth parameters.

5. The adaptive carbon nanotube growth control scheme based on AI deep learning according to claim 4 is characterized in that: The adjustment method includes: presetting a growth parameter threshold, subtracting two endpoint battery performances from the required battery performance to obtain two differences, selecting the difference with the smallest value in the two differences to obtain a target difference, determining the number of sub-performances whose performance values ​​in the target difference are not 0 to obtain a target number, locking a performance relationship between a single or multiple variables and the target number in a target relationship based on the target number to obtain a plurality of sub-target relationships, extracting a sub-target relationship that matches the sub-performance in the target difference from the plurality of sub-target relationships to obtain a final relationship, obtaining an added value by calculating a proportional relationship based on the final relationship in combination with the target difference, adding the added value to the endpoint growth parameter corresponding to the target difference to obtain a target growth parameter, and recording the final relationship, the target difference, and the added value to obtain an adjustment direction.

6. The adaptive carbon nanotube growth control scheme based on AI deep learning according to claim 1, characterized in that: The judgment method includes: monitoring the performance of a finished lithium-ion battery composed of carbon nanotubes to obtain result performance, judging whether the result performance is consistent with user requirements, and when the result performance is inconsistent with the user requirements, optimizing the target growth parameters through an optimization method to obtain optimized growth parameters, growing carbon nanotubes based on the optimized growth parameters, and continuing to monitor the performance of the finished lithium-ion battery composed of the optimized carbon nanotubes to obtain final performance, judging whether the final performance is consistent with user requirements, and when the final performance is inconsistent with user requirements, optimizing the optimized growth parameters through an optimization method until the performance of the finished lithium-ion battery composed of the optimized carbon nanotubes is consistent with user requirements.

7. The adaptive carbon nanotube growth control scheme based on AI deep learning according to claim 6 is characterized by: The optimization method includes: presetting a difference range and a reduction number, obtaining feedback address information, dynamically accumulating and reducing the added value after optimizing the number of times based on the reduction number to obtain a dynamic value, obtaining the difference between the result performance and the required battery performance to obtain a finished product difference, judging whether the finished product difference is within the difference range, and when the finished product difference is within the difference range, feeding back the finished product difference to the user based on the feedback address information, and the user decides whether to optimize, and when the finished product difference is outside the difference range or the user decides to optimize, judging the relationship between the finished product difference and the target difference, and when the finished product difference is greater than the target difference, increasing the endpoint growth parameter corresponding to the target difference based on the dynamic value to obtain the optimized growth parameter, and when the finished product difference is less than the target difference, reducing the endpoint growth parameter corresponding to the target difference based on the dynamic value to obtain the optimized growth parameter, and obtaining the optimized growth parameter. The final performance is obtained based on the performance of the finished lithium-ion battery composed of carbon nanotubes, and the difference between the final performance and the required battery performance is obtained to obtain the final difference. It is determined whether the final difference is within the difference range. When the final difference is within the difference range, the final difference is fed back to the user based on the feedback address information, and the user decides whether to optimize. When the final difference is outside the difference range or the user decides to optimize, the relationship between the final difference and the target difference is determined. When the final difference is greater than the target difference, the final growth parameters are obtained based on the optimized growth parameters corresponding to the finished product difference and the dynamic numerical reduction. When the final difference is less than the target difference, the final growth parameters are obtained based on the target growth parameters corresponding to the finished product difference and the dynamic numerical increase. When the performance of the finished lithium-ion battery composed of carbon nanotubes with the optimized growth parameters is consistent with the user's needs, the optimization is stopped.

8. An adaptive carbon nanotube growth control system based on AI deep learning, characterized in that: An adaptive carbon nanotube growth control scheme based on AI deep learning as described in any one of claims 1-7 is used.

Images