An AI-assisted carbon nanotube growth control method and system

Abstract

The present invention discloses an AI-assisted carbon nanotube growth control method and system, which relates to the field of control system technology. It includes a three-dimensional AI virtual platform that collects carbon nanotube growth data and environmental data within a unit time to construct a carbon nanotube model. The growth data includes growth rate, direction and diameter size, while the environmental data involves gas flow and electric field strength. The carbon nanotube model is mapped to a three-dimensional coordinate system, in which 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. The present invention can accurately capture environmental changes during the growth of carbon nanotubes by using a three-dimensional AI virtual platform and real-time data acquisition technology, and dynamically adjust environmental parameters during the growth process in combination with growth data, so that environmental changes can be quickly responded to during actual control, avoiding growth instability or deviation caused by the inability to adjust in time in traditional methods.

Description

Technical Field

[0001] The present invention relates to the technical field of control systems, and in particular to an AI-assisted carbon nanotube growth control method and system. Background Art

[0002] With the development of nanotechnology, carbon nanotubes have shown broad application prospects in electronics, energy, materials science and other fields due to their unique physical and chemical properties. However, the growth process of carbon nanotubes is complicated, and traditional control methods are difficult to achieve precise control, which affects their performance and application. Therefore, it is particularly important to develop a method that can accurately control the growth process of carbon nanotubes.

[0003] After searching, the Chinese invention patent with publication number "CN11652368 A" discloses "a data processing method and related products". This application uses the technical solution of the present disclosure to determine the quantization parameters during quantization in the process of neural network operation. The quantization parameters are used by the artificial intelligence processor to quantize the data in the process of neural network operation, converting high-precision data into low-precision fixed-point numbers, which can reduce the size of all data storage space involved in the neural network operation process, so that the on-chip memory on the artificial intelligence processor chip can accommodate more data, reducing the memory access data of the artificial intelligence processor chip and improving computing performance.

[0004] In addition, the Chinese invention patent with publication number "CN118966277A" discloses "an air purification detection method and system based on deep learning". The application uses a training set to pre-train the air purification detection model; uses the optimized air purification detection model to detect the purified air; constructs an adaptive adjustment model to intelligently adjust the operation of the molecular sieve adsorber; constructs an air purification prediction model, and uses the air purification prediction model to predict the future working state and adsorption efficiency of the molecular sieve adsorber and the failures that may occur in the future air purification process.

[0005] However, the growth of carbon nanotubes is related to a number of external variables to a certain extent. In the CVD (chemical vapor deposition) method, when gaseous hydrocarbons pass through a template to which catalyst particles are attached, it is necessary to control an appropriate gas flow rate to ensure uniform growth of the carbon nanotubes. In addition, during the electric field induced growth of carbon nanotubes, the growth direction of the carbon nanotubes is affected by the gas flow rate, causing the angle between the carbon nanotubes and the electric field to change, and the growth direction of the carbon nanotubes will also change accordingly. However, the above two disclosed methods and similar methods are difficult to adapt to this dynamically changing growth environment during actual operation, and it is impossible to adjust the growth parameters in real time to ensure the quality and consistency of the carbon nanotubes. Summary of the invention

[0006] The purpose of the present invention is to provide an AI-assisted carbon nanotube growth control method and system to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] In the first aspect, an AI-assisted carbon nanotube growth control method is proposed, including:

[0009] The 3D AI virtual platform constructs a carbon nanotube model by collecting carbon nanotube growth data and environmental data per unit time. The growth data includes growth rate, direction and diameter, while the environmental data involves gas flow and electric field strength.

[0010] Mapping the carbon nanotube model 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;

[0011] Record the initial coordinates, i.e. the coordinate positions of the midpoints of both ends of the carbon nanotube before the unit time;

[0012] Record the current coordinates, i.e. the coordinate positions of the midpoints of the two ends of the carbon nanotube at any time node during the unit time;

[0013] Based on the difference between the initial coordinates and the current coordinates, the corresponding environmental features in the environmental data are retrieved and matched;

[0014] Record the time period corresponding to the initial coordinates and the current coordinates, and associate them with the corresponding environmental features to form an association result;

[0015] According to the correlation results and the carbon nanotube growth target, the corresponding environmental characteristic data are adjusted to optimize the growth process of the carbon nanotubes.

[0016] As a further preferred embodiment of the present technical solution, the method for adjusting the corresponding environmental characteristic data according to the correlation result and the carbon nanotube growth target includes:

[0017] Obtaining growth data corresponding to a marked time period, where the marked time period is a time period corresponding to an initial coordinate and a current coordinate;

[0018] determining adjustment parameters of gas flow rate and electric field intensity according to the ratio of the correlation result to the carbon nanotube growth target;

[0019] A linear formula is constructed using adjustment parameters to express the degree of association between growth data and the associated results;

[0020] Calculate new gas flow rate and electric field strength values ​​through linear formula;

[0021] Based on the calculated gas flow and electric field strength, the environmental data in the subsequent unit time are adjusted.

[0022] As a further preferred embodiment of the present technical solution, the linear formula is: , Y represents the growth rate of carbon nanotubes, X 1 Used to indicate gas flow rate, X 2 is used to represent the electric field strength, a and b are used to represent the relative effects of gas flow rate and electric field strength on the growth rate, which are obtained by adjusting the parameters, and d is the basic growth rate of carbon nanotubes.

[0023] As a further preferred embodiment of the present technical solution, the method for constructing the carbon nanotube model includes:

[0024] Collect the carbon nanotube growth data per unit time, including growth rate, direction and diameter;

[0025] Record the environmental data of the carbon nanotube growth stage per unit time, the environmental data including gas flow rate and electric field strength;

[0026] A three-dimensional AI virtual platform is developed using 3D software. The three-dimensional AI virtual platform receives growth data and builds a virtual carbon nanotube model internally.

[0027] As a further preferred embodiment of the present technical solution, in the three-dimensional coordinate system of the three-dimensional AI virtual platform, a magnetic field intensity distribution map is drawn according to the environmental data;

[0028] Calculating a first angle, where the first angle represents the angle between the position of one end of the carbon nanotube before a unit time and the center point of the magnetic field;

[0029] Calculating a second angle, where the second angle represents the angle between the coordinate position of one end of the carbon nanotube after a unit time and the center point of the magnetic field;

[0030] Using the values ​​of the first and second included angles and the corresponding growth data, an angle relationship mapping diagram is constructed;

[0031] According to the angle relationship mapping diagram, the correlation function formula between the magnetic field and the carbon nanotube growth data is derived;

[0032] Substitute the growth target value of the carbon nanotubes into the correlation function formula, and calculate and output the corresponding magnetic field intensity.

[0033] As a further preferred embodiment of the present technical solution, a first gas flow rate is measured, the first gas flow rate corresponding to an instantaneous gas flow rate on the surface of the carbon nanotubes at the moment when the first angle is formed;

[0034] measuring a second gas flow rate, the second gas flow rate corresponding to an instantaneous gas flow rate on the surface of the carbon nanotube when the second angle is formed;

[0035] Constructing an angle gas flow data set based on matching the measured first and second gas flows with the corresponding first angle and second angle;

[0036] Collect the angle gas flow data set and growth data per unit time, and construct a two-dimensional mapping relationship diagram based on it;

[0037] According to the mapping relationship diagram, the correlation function formula between the gas flow rate and the growth direction of carbon nanotubes is derived;

[0038] The carbon nanotube growth target value is input into the correlation function formula to calculate and output the corresponding adjusted gas flow data.

[0039] As a further preferred embodiment of the present technical solution, the proportion of the associated results per unit time is calculated;

[0040] Determine the unit time of all time periods according to the proportion of the associated results;

[0041] Based on the time period corresponding to the correlation result, the growth data of carbon nanotubes in unit time is predicted;

[0042] Comparing the predicted growth data with the target value of carbon nanotube growth to determine whether the corresponding environmental characteristic value needs to be adjusted;

[0043] In the second aspect, in order to improve the above technical solution, the present invention also proposes an AI-assisted carbon nanotube growth control system, wherein an AI-assisted carbon nanotube growth control system uses the above AI-assisted carbon nanotube growth control method and includes:

[0044] A data acquisition module, used to collect growth data and environmental data of carbon nanotubes;

[0045] The data processing module is used to process and analyze the collected data, including data cleaning, data conversion and data normalization, to generate a data set that can be used for model training and prediction;

[0046] A model training module, used for training a prediction model based on the data processed by the data processing module;

[0047] The 3D AI virtual platform module is used to build a 3D model of carbon nanotubes, simulate their growth process under different environmental conditions, and visualize the results;

[0048] The prediction and optimization module predicts the growth process of carbon nanotubes based on the trained prediction model and adjusts the environmental characteristic data according to the prediction results to optimize the growth process;

[0049] The control execution module is used to control the experimental equipment to adjust the environmental characteristics according to the adjustment parameters provided by the prediction and optimization module.

[0050] As a further preferred embodiment of the present technical solution, the data acquisition module is connected to the data processing module via a data interface to realize real-time transmission of data; the data processing module is connected to the model training module and the three-dimensional AI virtual platform module via a data processing pipeline to ensure correct processing and transmission of data; the model training module is connected to the prediction and optimization module via a model interface to realize model loading and prediction; the three-dimensional AI virtual platform module is connected to the display device via a graphic interface to realize visual display of results; the prediction and optimization module is connected to the control execution module via a control interface to realize parameter adjustment and equipment control.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] The AI-assisted carbon nanotube growth control method and system can accurately capture environmental changes during the growth of carbon nanotubes by using a three-dimensional AI virtual platform and real-time data acquisition technology, and dynamically adjust environmental parameters during the growth process in combination with growth data, so that environmental changes can be quickly responded to during actual control, avoiding growth instability or deviation caused by the inability to adjust in time in traditional methods. In addition, by mapping the growth data of carbon nanotubes to a three-dimensional coordinate system and analyzing the difference between the initial coordinates and the current coordinates, the growth parameters that need to be adjusted can be derived according to environmental changes, thereby maintaining precise control of the growth process under complex and dynamic environmental conditions;

[0053] Secondly, the present invention accurately collects and analyzes real-time growth data, and dynamically adjusts environmental data according to growth targets, thereby ensuring that environmental parameters can respond at any time during the growth process, thereby improving the stability and consistency of carbon nanotube growth to a certain extent, and effectively avoiding growth fluctuations caused by manual intervention lag or environmental changes in traditional methods. In addition, by comparing the correlation results with the carbon nanotube growth targets, the growth status in the future can be intelligently predicted, so that adjustments can be made in advance to reduce the negative impact of environmental fluctuations on the growth process. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A flowchart of the method disclosed in the present invention;

[0055] Figure 2 is an auxiliary illustration of step S200 of the present invention;

[0056] Figure 3 This is an auxiliary illustration of the second embodiment of the present invention;

[0057] Figure 4 It is a module composition diagram of the disclosed system of the present invention. DETAILED DESCRIPTION

[0058] 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.

[0059] Before discussing the technical solution of the present invention, it should be made clear that the instantaneous flow rate of the gas flow has a significant effect on the rate of the carbon source in the growth process of carbon nanotubes. Specifically, insufficient gas flow rate will cause the catalyst to stay in the high temperature zone for too long, thereby losing its activity, which will reduce the yield and quality of carbon nanotubes. On the contrary, too high a gas flow rate may inhibit the growth of carbon nanotubes, affect their quality, and reduce growth efficiency. In actual operation, changes in gas flow rate will also change the angle difference between the carbon nanotubes and the electric field. Since the growth direction of carbon nanotubes is affected by the gas flow rate during the electric field induced growth process, when the gas flow rate changes and causes the angle between the carbon nanotubes and the electric field to change, the growth direction of the carbon nanotubes will also change accordingly. Therefore, when controlling the growth of carbon nanotubes, it is necessary to detect the dynamically changing gas flow rate and electric field. In view of this, the present invention proposes an AI-assisted carbon nanotube growth control method.

[0060] Example 1, Reference Figure 1 It can be seen that an AI-assisted carbon nanotube growth control method includes: steps S100 to S700.

[0061] Step S100: The three-dimensional AI virtual platform constructs a carbon nanotube model by collecting carbon nanotube growth data and environmental data within a unit time.

[0062] It should be supplemented that in step S100, the growth data includes growth rate, direction and diameter size, while the environmental data involves gas flow rate and electric field strength.

[0063] In addition, it should be further explained that the method for constructing the carbon nanotube model in step S100 includes: steps S101 to S103.

[0064] Step S101: collecting carbon nanotube growth data per unit time, where the growth data includes growth rate, direction and diameter size.

[0065] Step S102: recording environmental data of the carbon nanotube growth stage within a unit time, the environmental data including gas flow and electric field strength.

[0066] Step S103: Using 3D software to develop a three-dimensional AI virtual platform, the three-dimensional AI virtual platform receives the growth data and constructs a virtual carbon nanotube model internally.

[0067] It should be further explained that, in the present invention, the 3D software used specifically refers to "Materials Studio". Specifically, the construction of the carbon nanotube model follows the process of "build → Build Nano structure → Single-Wall Nanotube" to create a single-wall carbon nanotube. It should be added that "build" is a main menu item in the Materials Studio software, which is specifically used to build nanostructure models, and "Build Nano structure" is located under the "build" menu. It is responsible for creating various nanostructures. In particular, "Single-Wall Nanotube" is a sub-option under the "Build Nanostructure" menu, which is specifically used to build a single-wall carbon nanotube. Based on the operation of "Build Nanostructure", a parameter setting interface will pop up, allowing the user to enter the values ​​of "M" and "N", where "N" is an integer parameter used to control the overall size of the nanotube; and "M" is used to set the angle of the graphite sheet for building the nanotube. By adjusting the values ​​of "N" and "M", the size and chirality of the nanotube can be accurately controlled, thereby generating the desired carbon nanotube model.

[0068] It should be further added that step S100 in the present invention is the basis of the entire AI-assisted control method, providing necessary data support and model basis for subsequent steps. After step S100 is completed, the following steps S200 to S700 will be further controlled and optimized based on this model.

[0069] Step S200: mapping the carbon nanotube model into a three-dimensional coordinate system.

[0070] It should be noted that the reference Figure 2 It can be seen that the X-axis, Y-axis and Z-axis in the three-dimensional coordinate system represent the length, width and height of the carbon nanotube respectively.

[0071] In addition, it should be noted that in the present invention, the purpose of mapping the carbon nanotube model into a three-dimensional coordinate system is to more accurately simulate and control the spatial position and direction of the carbon nanotubes during the actual growth process. In this way, the growth state of the carbon nanotubes can be monitored in real time, and their growth path can be predicted based on the model, thereby achieving precise control of the growth process.

[0072] Step S300: recording the initial coordinates, ie, the coordinate positions of the midpoints of both ends of the carbon nanotube a unit time ago.

[0073] Step S400: recording the current coordinates, that is, the coordinate positions of the nodes at any time period when the midpoints of the two ends of the carbon nanotube are performed in a unit time.

[0074] Step S500: Based on the difference between the initial coordinates and the current coordinates, the corresponding environmental features in the environmental data are retrieved and matched.

[0075] It should be noted that step S300 to step S500 in the present invention are used to analyze environmental changes during the growth of carbon nanotubes. By comparing the initial coordinates and the current coordinates, the growth rate and direction of the carbon nanotubes can be determined.

[0076] Specifically, refer to Figure 2 It can be seen that the initial coordinates obtained in step S200 are (X 1 , Y 1 , Z 1 ), and the current coordinates obtained in step S400 are (X 2 , Y 2 , Z 2 ), through the formula ΔX = X 2 -X 1 , ΔY = Y 2 -Y 1 , ΔZ = Z 2 -Z 1 , the displacement change of the carbon nanotube in the X, Y, and Z directions can be calculated.

[0077] Step S600: Record the time period corresponding to the initial coordinates and the current coordinates, and associate them with corresponding environmental features to form an association result.

[0078] It should be noted that step S600 is used to establish a connection between time and environmental characteristics, thereby providing a basis for dynamic adjustment during the growth of carbon nanotubes. By recording the time periods corresponding to the initial coordinates and the current coordinates, the changes in gas flow and electric field strength during the time period can be analyzed. It should be added that the correlation results help to understand the specific environmental factors that affect the growth rate and direction of carbon nanotubes during the marked time period, providing data support for subsequent growth control.

[0079] Step S700: According to the correlation result and the carbon nanotube growth target, the corresponding environmental characteristic data is adjusted to optimize the growth process of the carbon nanotube.

[0080] It should be noted that step S700 is used in the present invention to achieve real-time optimization of the carbon nanotube growth process. Specifically, by analyzing the correlation results obtained in step S600, the key environmental factors affecting the growth rate and direction of the carbon nanotubes are identified. Then, according to the target parameters of the carbon nanotube growth, such as diameter and length, the environmental characteristic data such as gas flow rate and electric field strength are adjusted. For example, if it is found that the growth rate decreases due to too low gas flow rate, the gas flow rate can be appropriately increased. If the electric field strength is too high and affects the growth direction of the carbon nanotubes, the electric field strength can be appropriately reduced. In this way, it can be ensured that the carbon nanotubes grow according to the predetermined growth targets, thereby improving their yield and quality.

[0081] It should be further supplemented that the method for adjusting the corresponding environmental characteristic data according to the correlation result and the carbon nanotube growth target in step S700 includes: steps S701 to S705.

[0082] Step S701: Acquire growth data corresponding to a marked time period. It should be noted that the marked time period is a time period corresponding to an initial coordinate and a current coordinate.

[0083] Step S702: determining adjustment parameters of gas flow rate and electric field strength according to the ratio of the correlation result to the carbon nanotube growth target.

[0084] It should be noted that, when step S702 is implemented, it is assumed that the specific value of the associated result obtained is that when the gas flow rate increases by 10%, the diameter of the carbon nanotube increases by 5%, the coordinate deviation is 0.05 unit length, and the carbon nanotube growth target is to increase the diameter by 0.1 unit length, then the gas flow rate needs to be increased by 20% to meet the target. Similarly, if the deviation between the electric field strength and the growth direction of the carbon nanotube exceeds the preset threshold, the electric field strength needs to be appropriately adjusted to correct the growth direction.

[0085] Step S703: construct a linear formula using the adjustment parameters to express the degree of association between the growth data and the association result.

[0086] It should be noted that in step S703, the linear formula is , Y represents the growth rate of carbon nanotubes, X 1 Used to indicate gas flow rate, X 2 It is used to represent the electric field strength, a and b are used to represent the relative effects of gas flow rate and electric field strength on the growth rate, which are obtained by adjusting the parameters, and d is the basic growth rate of carbon nanotubes, which is specifically a constant.

[0087] It should be further explained that, by associating step S703 and step S702, it can be seen that the value of a is 0.2 and the value of b is 0.15.

[0088] Step S704: Calculate new gas flow and electric field strength values ​​using a linear formula.

[0089] Step S705: Based on the calculated gas flow and electric field strength, adjust the environmental data in the subsequent unit time.

[0090] Embodiment 2: In order to further reveal the connection between the magnetic field and the growth data, the present invention draws a magnetic field intensity distribution map based on the environmental data in the three-dimensional coordinate system of the three-dimensional AI virtual platform.

[0091] Specifically, if Figure 3 As shown, firstly, the first angle is calculated, which represents the angle between the position of one end of the carbon nanotube before the unit time and the center point of the magnetic field; then the second angle is calculated, which represents the angle between the coordinate position of one end of the carbon nanotube after the unit time and the center point of the magnetic field. Using the values ​​of the first and second angles and the corresponding growth data, an angle relationship mapping diagram is constructed. Based on the mapping diagram, the correlation function formula between the magnetic field and the carbon nanotube growth data is derived. Finally, the growth target value of the carbon nanotube is substituted into the correlation function formula, and the corresponding magnetic field strength is calculated and output.

[0092] It should be noted that the magnetic field strength calculation method of Example 2 of the present invention is different from the linear formula calculation method described in Example 1. It uses a nonlinear model to more accurately describe the relationship between the magnetic field strength and the growth rate of carbon nanotubes. In this way, the growth process of carbon nanotubes can be further controlled to ensure that their growth direction and rate under the action of the magnetic field meet the expected goals.

[0093] Embodiment 3: As a supplement to Embodiment 2, this embodiment discloses the relationship between gas flow rate and the growth direction of carbon nanotubes. Specifically, the first gas flow rate is first measured, and the first gas flow rate corresponds to the instantaneous gas flow rate when the carbon nanotube surface forms a first angle. Then, the second gas flow rate is measured, and the second gas flow rate corresponds to the instantaneous gas flow rate when the carbon nanotube surface forms a second angle. Based on the matching of the measured first and second gas flows with the corresponding first angle and second angle, an angle gas flow data set is constructed, and the angle gas flow data set and growth data within unit time are collected. Based on this, a two-dimensional mapping relationship diagram is constructed. According to the mapping relationship diagram, a correlation function formula between the gas flow rate and the growth direction of the carbon nanotubes is derived. Finally, the carbon nanotube growth target value is input into the correlation function formula to calculate and output the corresponding adjusted gas flow data.

[0094] It should be noted that the gas flow adjustment method of Example 3 of the present invention is different from the methods in Examples 1 and 2. Specifically, Example 3 adopts a gas flow adjustment strategy based on angle change to more accurately control the growth direction of the carbon nanotubes. In this way, the gas flow of the carbon nanotubes at different growth stages is properly adjusted, thereby optimizing its growth process and improving the quality and yield of the carbon nanotubes.

[0095] Example 4. As a further extension of Example 1, the present invention demonstrates a prediction and adjustment strategy for growth data. First, the proportion of correlation results in unit time is calculated, and then the unit length of each time period is set. Based on the time period corresponding to the correlation result, the carbon nanotube growth data in the future unit time is predicted. Then, the predicted data is compared with the target value of carbon nanotube growth to determine whether the value of the environmental characteristics needs to be adjusted.

[0096] For example, it is predicted that the growth rate will slow down due to the reduction in gas flow rate, and the system will automatically increase the gas flow rate to maintain the set growth rate. If it is predicted that the growth direction will deviate, the system will adjust the electric field strength to correct the direction. It should be noted that the prediction and adjustment mechanism proposed in Example 4 increases the predictability and controllability of the carbon nanotube growth process, and provides technical support for the preparation of high-quality carbon nanotubes.

[0097] Example 5, Reference Figure 4 It can be seen that the present invention also proposes an AI-assisted carbon nanotube growth control system, which adopts the aforementioned AI-assisted carbon nanotube growth control method and includes the following components:

[0098] Data acquisition module, responsible for collecting data related to carbon nanotube growth and environment;

[0099] The data processing module performs processing and analysis on the collected data, including data cleaning, conversion, and normalization to produce a data set suitable for model training and prediction;

[0100] The model training module uses the data processed by the data processing module to train the prediction model;

[0101] The 3D AI virtual platform module builds a 3D model of carbon nanotubes, simulates their growth process under different environmental conditions, and displays the results in a visual way;

[0102] The prediction and optimization module uses the trained prediction model to predict the carbon nanotube growth process and adjusts the environmental parameters according to the prediction results to optimize the growth conditions;

[0103] The control execution module controls the experimental equipment to change the environmental characteristics according to the parameter adjustments provided by the prediction and optimization module.

[0104] It should be added that, in this embodiment, the data acquisition module is connected to the data processing module through a data interface to ensure real-time data transmission; the data processing module is connected to the model training module and the three-dimensional AI virtual platform module through a data processing pipeline to ensure correct processing and transmission of data; the model training module and the prediction and optimization module are connected through a model interface to realize model loading and prediction; the three-dimensional AI virtual platform module is connected to the display device through a graphical interface to realize visual display of the results; the prediction and optimization module and the control execution module are connected through a control interface to realize parameter adjustment and equipment control.

[0105] It should be further noted that the system also includes a user interface that allows researchers to input growth parameters, monitor the growth process, and manually intervene in the control execution module.

[0106] 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 AI-assisted carbon nanotube growth control method, characterized in that: include: The 3D AI virtual platform constructs a carbon nanotube model by collecting carbon nanotube growth data and environmental data per unit time. 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; Record the initial coordinates, i.e. the coordinate positions of the midpoints of both ends of the carbon nanotube before the unit time; Record the current coordinates, i.e. the coordinate positions of the midpoints of the two ends of the carbon nanotube at any time node during the unit time; Based on the difference between the initial coordinates and the current coordinates, the corresponding environmental features in the environmental data are retrieved and matched; Record the time period corresponding to the initial coordinates and the current coordinates, and associate them with the corresponding environmental features to form an association result; According to the correlation results and the carbon nanotube growth target, the corresponding environmental characteristic data are adjusted to optimize the growth process of the carbon nanotube; The method of adjusting the corresponding environmental characteristic data according to the correlation result and the carbon nanotube growth target includes: Get and mark the time period corresponding to the growth data; According to the growth target and the ratio of the associated results, the gas flow rate and the electric field strength adjustment parameters are set; Construct a linear formula to reflect the relationship between growth data and correlation results; Use this formula to calculate the new gas flow rate and electric field strength; Adjust subsequent environmental data based on the calculation results; The method for constructing the carbon nanotube model includes: Collect carbon nanotube growth data, including rate, direction, and diameter; Record environmental data during the growth phase, including: gas flow and electric field strength; Develop a three-dimensional AI virtual platform to receive growth data and build a virtual carbon nanotube model; In the three-dimensional coordinate system of the three-dimensional AI virtual platform, a magnetic field intensity distribution map is drawn based on environmental data; Calculating a first angle, where the first angle represents the angle between the position of one end of the carbon nanotube before a unit time and the center point of the magnetic field; Calculating a second angle, where the second angle represents the angle between the coordinate position of one end of the carbon nanotube after a unit time and the center point of the magnetic field; Using the values ​​of the first and second included angles and the corresponding growth data, an angle relationship mapping diagram is constructed; According to the angle relationship mapping diagram, the correlation function formula between the magnetic field and the carbon nanotube growth data is derived; Substitute the growth target value of the carbon nanotube into the correlation function formula, calculate and output the corresponding magnetic field intensity; Determine a first gas flow rate, the first gas flow rate corresponding to an instantaneous gas flow rate on the surface of the carbon nanotube when the first angle is formed; measuring a second gas flow rate, the second gas flow rate corresponding to an instantaneous gas flow rate on the surface of the carbon nanotube when the second angle is formed; Constructing an angle gas flow data set based on matching the measured first and second gas flows with the corresponding first angle and second angle; Collect the angle gas flow data set and growth data per unit time, and construct a two-dimensional mapping relationship diagram based on it; According to the mapping relationship diagram, the correlation function formula between the gas flow rate and the growth direction of carbon nanotubes is derived; The carbon nanotube growth target value is input into the correlation function formula to calculate and output the corresponding adjusted gas flow data.

2. The AI-assisted carbon nanotube growth control method according to claim 1, characterized in that: The linear formula is ,Y represents the growth rate of carbon nanotubes, X1 is used to represent the gas flow rate, X2 is used to represent the electric field strength, a and b are used to represent the relative influence of gas flow rate and electric field strength on the growth rate, which is obtained by adjusting the parameters, and d is the basic growth rate of carbon nanotubes.

3. The AI-assisted carbon nanotube growth control method according to claim 1, characterized in that: Calculate the proportion of associated results per unit time; Determine the unit time of all time periods according to the proportion of the associated results; Based on the time period corresponding to the correlation result, the growth data of carbon nanotubes in unit time is predicted; The predicted growth data is compared with the target value of carbon nanotube growth to determine whether the corresponding environmental characteristic value needs to be adjusted.

4. An AI-assisted carbon nanotube growth control system, using the AI-assisted carbon nanotube growth control method according to any one of claims 1 to 3, characterized in that: include: A data acquisition module, used to collect growth data and environmental data of carbon nanotubes; The data processing module is used to process and analyze the collected data, including data cleaning, data conversion and data normalization, to generate a data set that can be used for model training and prediction; A model training module, used for training a prediction model based on the data processed by the data processing module; The 3D AI virtual platform module is used to build a 3D model of carbon nanotubes, simulate their growth process under different environmental conditions, and visualize the results; The prediction and optimization module predicts the growth process of carbon nanotubes based on the trained prediction model and adjusts the environmental characteristic data according to the prediction results to optimize the growth process; The control execution module is used to control the experimental equipment to adjust the environmental characteristics according to the adjustment parameters provided by the prediction and optimization module.

5. The AI-assisted carbon nanotube growth control system according to claim 4, characterized in that: The data acquisition module is connected to the data processing module via a data interface to achieve real-time data transmission. The data processing module is connected to the model training module and the three-dimensional AI virtual platform module via a data processing pipeline to ensure correct data processing and transmission. The model training module is connected to the prediction and optimization module via a model interface to achieve model loading and prediction. The three-dimensional AI virtual platform module is connected to the display device via a graphic interface to achieve visual display of the results. The prediction and optimization module is connected to the control execution module via a control interface to achieve parameter adjustment and equipment control.

Images