Recognition system for preparing nano material and nano material preparation process

Abstract

The invention discloses an identification system for preparing a nanometer material and a nanometer material preparation process, and relates to the technical field of nanometer material preparation, the identification system comprises a control execution platform building unit used for building a processing platform to receive a control instruction to adjust the operation state of nanometer material preparation equipment; the raw material processing degree analysis unit is used for collecting production data of the nanometer preparation raw materials in the crushing process and identifying the processing degree of the raw materials; the core-spun yarn integrity prediction unit is used for acquiring image data in a core-spun processing process by utilizing a machine vision technology to analyze and predict the integrity of the core-spun yarn; the material mechanical stress analysis unit is used for obtaining the structure of the nano material in the heat treatment furnace and dynamically analyzing the mechanical stress of the nano material; and the control instruction generation and execution unit is used for feeding back the control instruction to the processing platform. According to the invention, the structure change of the nano-material at high temperature can be obtained in real time to analyze the mechanical stress of the nano-material finished product.

Description

Technical Field

[0001] The present invention relates to the technical field of nano material preparation, and in particular to an identification system for preparing nano materials and a nano material preparation process. Background Art

[0002] Nanomaterials refer to materials that are mainly composed of particles, crystals or fibers with a size of nanometers (1 nanometer to 100 nanometers). These materials usually exhibit physical, chemical or biological properties different from those of macroscopic materials due to their unique nanoscale effects. The preparation of nanomaterials usually involves precise control of the chemical composition, crystal structure, shape and size distribution of the materials to ensure that they can perform as expected in specific applications.

[0003] The preparation of nanomaterials involves a variety of technologies and methods, the main purpose of which is to precisely control the size, shape, composition and structure of the material at the atomic or molecular level, thereby giving it special properties and functions. Specifically, it is prepared by chemical vapor deposition, sol-gel method, electrochemical deposition, physical vapor deposition and self-assembly technology.

[0004] Technical identification is a key link in the preparation process of nanomaterials, which is used to ensure that the composition and structure of the nanomaterials meet the design standards, thereby helping to optimize the preparation process and ensure product quality, ensuring that each batch of nanomaterials meets the expected standards and performance.

[0005] However, in the prior art, when identifying the nanomaterial preparation process, the analysis of the degree of crushing and structural dynamics of the raw materials is often ignored. If the degree of crushing is insufficient, it will affect the uniformity of the finished nanomaterial product. At the same time, if the structural dynamics of the nanomaterial are ignored during the preparation process, the degree of fatigue and failure cannot be predicted in advance, thereby reducing the accuracy of the nanomaterial preparation and the quality of the finished product. Summary of the invention

[0006] In order to solve the above problems, the present invention proposes an identification system for preparing nanomaterials and a nanomaterial preparation process, so as to achieve the purpose of improving the accuracy of nanomaterial preparation and the quality of finished products.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] In a first aspect, the present invention provides an identification system for preparing nanomaterials, the identification system comprising a control execution platform building unit, a raw material processing degree analysis unit, a cored wire integrity prediction unit, a material mechanical stress analysis unit, and a control instruction generation and execution unit;

[0009] Among them, the control execution platform building unit, the raw material processing degree analysis unit, the cored wire integrity prediction unit, the material mechanical stress analysis unit and the control instruction generation execution unit are connected in sequence;

[0010] A control execution platform building unit is used to build a processing platform and coordinate control with the nanomaterial preparation equipment, and receive control instructions to adjust the operating state of the nanomaterial preparation equipment;

[0011] The raw material processing degree analysis unit is used to collect production data of nano-preparation raw materials during the crushing process and identify the processing degree of the raw materials based on mining technology;

[0012] The cored wire integrity prediction unit is used to collect image data during the cored wire processing process using machine vision technology, and predict the integrity of the cored wire through recognition technology analysis;

[0013] Material mechanical stress analysis unit, used to obtain the structural dynamics of nanomaterials in the heat treatment furnace using in-situ projection technology, and analyze the mechanical stress of nanomaterials based on the structural dynamics;

[0014] The control instruction generation execution unit is used to generate control instructions for corresponding equipment according to the degree of raw material processing, the integrity of the cored wire and the mechanical stress judgment results, and feed them back to the processing platform.

[0015] Preferably, the raw material processing degree analysis unit includes a production data acquisition module, a particle size determination module and a particle size standard comparison module;

[0016] Among them, the production data acquisition module, the particle size determination module and the particle size standard comparison module are connected in sequence;

[0017] A production data acquisition module is used to capture the video stream of the master alloy ingot during the crushing process within a defined time using a camera at the crusher, and extract production data frames based on the video stream;

[0018] The particle size obtaining module is used to analyze and process the production data frame using detection technology to obtain the edge profile of the master alloy ingot particles and obtain the particle size in combination with the fitting parameters;

[0019] The particle size standard comparison module is used to compare the particle size of the master alloy ingot with the preset standard size to obtain the overlap, and to determine the degree of crushing of the master alloy ingot based on the overlap result.

[0020] Preferably, using detection technology to analyze and process the production data frame to obtain the edge profile of the master alloy ingot particles, and combining the fitting parameters to obtain the particle size includes:

[0021] Use straight-through filtering and statistical filtering to sharpen the production data frame to remove background points and extract the depth information of the particle pixels in the production data frame;

[0022] The three-dimensional coordinates of the particle pixel points are obtained based on the depth information and the internal and external parameters during camera acquisition to obtain the particle point cloud image, and the production data frame is sliced ​​according to the number of particles according to the slicing technology to obtain the slice image;

[0023] The contour points of the particles are extracted quickly by using the horizontal and vertical angle differences between adjacent points in the slice image, and the contour points are filtered.

[0024] Based on the enclosing algorithm, all contour points of the slice image are traversed to obtain the area of ​​the enclosing rectangle, and the area sizes of each rectangle are compared. The enclosing rectangle with the smallest area is selected as the extraction option, and the corresponding contour points are projected onto the plane to extract the particle size.

[0025] Preferably, using the horizontal angle and vertical angle differences between adjacent points in the slice image to quickly extract the contour points of the particles, and performing a filtering operation on the contour points includes:

[0026] All pixel points in the slice image are defined as a point set, and the initial slice density is set based on the height of the preset point in the point set, and the point set is divided into a number of horizontal slices;

[0027] Project each horizontal slice onto the XY plane, and use the average value of the coordinates of the horizontal slice and all pixel points on the XY plane to determine the horizontal angle of the preset point;

[0028] Obtain the horizontal angles of the remaining pixel points in the point set except the preset point, and sort them into a set according to the size rule. According to the sorted horizontal angles, the horizontal angle difference between two adjacent points is calculated in turn;

[0029] The horizontal angle difference between two adjacent points is compared with the horizontal angle threshold, and similar points with a difference greater than the threshold are set as the contour points of the particles in the vertical direction;

[0030] Divide the point set into several vertical slices based on the horizontal angle of the preset point, analyze the vertical angles of the pixels in each group of vertical slices, and sort the vertical angles in order of size;

[0031] The vertical angle difference between two adjacent groups of pixel points is determined based on the vertical angle sorting result, and compared with the preset angle difference, and the two groups of pixel points whose difference is greater than the preset angle difference are set as the contour points of the particle in the horizontal direction;

[0032] The particle contour points in the horizontal and vertical directions are integrated into an operation set, and the points whose distance from the particle contour points is greater than a set value are removed using statistical filtering.

[0033] Preferably, all contour points of the slice image are traversed based on the enclosing algorithm to obtain the area of ​​the enclosing rectangle, and the area sizes of the rectangles are compared, and the enclosing rectangle with the smallest area is selected as the extraction option, and the corresponding contour points are projected onto the plane to extract the particle size, including:

[0034] The average distance is obtained by statistical analysis based on the distance distribution from each contour point to the adjacent points in the operation set, and the contour points are divided by removing outliers using the difference between the distance threshold and the average distance;

[0035] The contour points are classified based on spatial clustering technology, and the sorting technology is used to extract and sort each contour point. According to the sorted contour points, two adjacent groups of contour points are connected to form line segments to construct the contour of the particle;

[0036] Use the enclosing algorithm to traverse the points farthest from the line segment in all contour points and the two groups of contour points farthest from the perpendicular line of the line segment and on both sides of the perpendicular line;

[0037] The area of ​​the enclosing rectangle is calculated based on the distance from the farthest point to the line segment and the sum of the distances from the contour points on both sides of the perpendicular line to the line segment. The areas of the enclosing rectangles are calculated by traversing all the edges that make up the contour, and the areas of each rectangle are compared.

[0038] The enclosing rectangle with the smallest area is selected as the extraction option, and the outline is projected to the XY plane again to extract the length and width of the particle, and then the outline is projected to the XZ plane to extract the height of the particle to obtain the particle size.

[0039] Preferably, comparing the particle size of the master alloy ingot with a preset standard size to obtain a coincidence, and judging the degree of crushing of the master alloy ingot based on the coincidence result includes:

[0040] constructing similar point vector spaces based on contour points corresponding to the master alloy ingot particles and the preset standard sizes, and converting the contour points into vectors in the similar point vector spaces;

[0041] The vectors are combined into a judgment matrix and input into a preset deep selector. The deep selector is used to extract feature vectors. The Manhattan distance is used to calculate the feature vectors extracted by the deep selector to obtain the distance between two groups of contour points, and the overlap degree is calculated based on the distance of the contour points.

[0042] If the degree of overlap between the particle size of the master alloy ingot and the preset standard size is greater than or equal to the preset value, it means that the degree of crushing of the master alloy ingot particles meets the preparation requirements. If the degree of overlap between the particle size of the master alloy ingot and the preset standard size is less than the preset value, it means that the degree of crushing of the master alloy ingot particles does not meet the preparation requirements.

[0043] Preferably, the material mechanical stress analysis unit includes a heat treatment monitoring processing module, a structural state model definition module, a dynamic change process reasoning module and a mechanical stress analysis determination module;

[0044] Among them, the heat treatment monitoring processing module, the structural state model definition module, the dynamic change process reasoning module and the mechanical stress analysis and determination module are connected in sequence;

[0045] A heat treatment monitoring processing module is used to monitor the microscopic morphology of the nanomaterial during the annealing process using an in-situ projection device at the location of the heat treatment furnace;

[0046] The structural state model definition module is used to analyze the changes in the crystal structure of raw materials in the microscopic morphology using the ray diffraction technology, and determine the influence relationship between the crystal structure changes and grain growth and grain defects based on the change results;

[0047] The dynamic change process reasoning module is used to establish a target state reasoning model based on the state reasoning algorithm, and to reason about the dynamic change process of the raw materials in combination with the influence relationship;

[0048] The mechanical stress analysis and determination module is used to combine simulation technology with dynamic change processes to pre-generate prepared nanomaterials, and apply nanoindentation testing technology to analyze the mechanical stress of nanomaterials.

[0049] Preferably, using ray diffraction technology to analyze the change in the crystal structure of the raw material in the microscopic morphology, and determining the influence relationship between the crystal structure change and the grain growth and grain defects based on the change results includes:

[0050] Set the wavelength and scanning angle of the ray diffraction equipment to scan the microscopic morphology to obtain the diffraction spectrum, and use the spectrum analysis software to perform identification and fitting operations on the diffraction spectrum;

[0051] Based on the identification and fitting results, the crystal structure, lattice number, peak width and peak shape of the raw materials during the annealing process are inferred, and the grain size is obtained from the peak width using the size correlation analysis algorithm;

[0052] Analyze the trend of grain growth based on the number of lattices and grain size, and combine quantitative extraction technology with peak shape to identify defects in grains;

[0053] The initial model is defined using the crystal structure, and the influence relationship between the three is reflected based on the grain growth trend and grain defects.

[0054] Preferably, a target state reasoning model is established based on a state reasoning algorithm, and the dynamic change process of the raw material is reasoned in combination with the influence relationship, including:

[0055] Based on the trend of grain growth, the number of lattices and grain size in a specified time period are preset as statistical data to determine the change segmentation nodes of the crystal structure in different time periods;

[0056] The state inference algorithm is used to establish the initial inference network and initialize the probability of changing the segmentation node to define the target state inference model, and the multi-level analysis technology is used to perform weighted processing on the statistical data to obtain the state conditional probability between the crystal structure and the number of lattices, and the number of lattices and the grain size.

[0057] Establish the transition probability between adjacent crystal structures based on the state conditional probability results, and infer the dynamic change process of raw materials in the next period based on the state conditional probability and the transition probability;

[0058] Among them, the calculation formula of state conditional probability is:

[0059]

[0060] In the formula, P represents the state conditional probability value; T represents the weighted result; represents the jth change segmentation node in the mth time period; i represents the number of change segmentation nodes; express The parent node of .

[0061] In a second aspect, the present invention further provides a nanomaterial preparation process for preparing the nanomaterial, the nanomaterial preparation process comprising the following steps:

[0062] S1. Selecting a preset mass fraction of iron, silicon, aluminum, copper, molybdenum, chromium and composite rare earth as spare materials, and fusing the iron, copper, molybdenum and chromium for smelting to obtain a master alloy ingot;

[0063] S2, placing the master alloy ingot into a crusher for crushing to obtain raw materials, and using a raw material processing degree analysis unit to identify the crushing degree of the raw materials;

[0064] S3, using aluminum to core silicon and composite rare earth to obtain a cored wire, and performing analysis on the integrity of the cored wire based on a cored wire integrity prediction unit;

[0065] S4, placing the raw materials and the cored wire into a rotary quenching furnace to melt and obtain a semi-finished nanomaterial product, and using a heat treatment furnace to anneal the semi-finished nanomaterial product to obtain the nanomaterial;

[0066] S5. Performing a structural dynamic analysis on the nanomaterial using a material mechanical stress analysis unit during the annealing process, and determining the mechanical stress of the nanomaterial based on the analysis result;

[0067] S6. Use the control execution platform building unit to build a processing platform and connect it to the preparation equipment. Based on the processing results of steps S2 to S4, a control instruction is generated and fed back to the control instruction generation unit to adjust the control parameters of each device.

[0068] The beneficial effects of the present invention are:

[0069] 1. When crushing the master alloy ingot, the present invention can monitor and analyze the crushing degree of the raw materials in real time, and then when the crushing degree does not meet the preset standard, corresponding adjustments can be made to achieve the ideal processing effect, prevent excessive crushing of the raw materials, save costs and avoid material waste. At the same time, the structural changes of nanomaterials at high temperatures can be obtained in real time, and the mechanical stress of the finished nanomaterials can be analyzed by three-dimensional simulation to predict fatigue and failure degrees, thereby significantly improving the accuracy and efficiency of the preparation of nanomaterials.

[0070] 2. The present invention uses a camera to capture the crushing process in real time to obtain a dynamic view of the raw material crushing process, and analyzes the dynamic view to accurately obtain the edge contour of the master alloy ingot particles, thereby facilitating the calculation of the particle size, and compares the particle size with the preset standard size to standardize the degree of crushing and ensure product consistency. The result of the particle size overlap is used to generate control quality to adjust the working parameters of the crusher, optimize the crushing process, avoid excessive or insufficient crushing, save energy and materials, and reduce the scrap rate.

[0071] 3. The present invention monitors the microscopic morphology of the material in real time to discover slight changes in the morphology of the material during the annealing process, and uses diffraction pattern analysis to accurately determine the changes in the crystal structure and the relationship between the crystal structure changes and grain growth and grain defects. At the same time, the inference algorithm is used to help predict the behavior of the material under different states and the performance of the nanomaterial, thereby reducing the uncertainty in production and optimizing the product preparation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0073] Figure 1 is a principle block diagram of an identification system for preparing nanomaterials according to an embodiment of the present invention;

[0074] Figure 2 The present invention is a flow chart of a process for preparing nanomaterials according to an embodiment of the present invention.

[0075] In the figure:

[0076] 1. Control execution platform building unit; 2. Raw material processing degree analysis unit; 3. Core wire integrity prediction unit; 4. Material mechanical stress analysis unit; 5. Control instruction generation and execution unit. DETAILED DESCRIPTION

[0077] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0078] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0079] It should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "include" and "have" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0080] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0081] See also Figure 1 The present invention provides an identification system for preparing nanomaterials, which includes a control execution platform building unit 1, a raw material processing degree analysis unit 2, a core wire integrity prediction unit 3, a material mechanical stress analysis unit 4 and a control instruction generation execution unit 5.

[0082] Among them, the control execution platform building unit 1, the raw material processing degree analysis unit 2, the cored wire integrity prediction unit 3, the material mechanical stress analysis unit 4 and the control instruction generation execution unit 5 are connected in sequence.

[0083] The control execution platform building unit 1 is used to build a processing platform and coordinate control with the nano material preparation equipment, and receive control instructions to adjust the operating state of the nano material preparation equipment.

[0084] In this embodiment, establishing a processing platform to coordinate and control the nanomaterial preparation equipment, and receiving control instructions to adjust the operating state of the nanomaterial preparation equipment includes:

[0085] Based on the specific requirements of the nanomaterial preparation process, including operating accuracy, control speed, and environmental stability, the overall architecture is designed, including hardware selection (including sensors, actuators, controllers, etc.) and software development including interface design, data processing algorithms, etc.

[0086] Select appropriate sensors and actuators according to system requirements, ensure that they can accurately measure and control the preparation conditions of nanomaterials, and install the required hardware on the nanomaterial preparation equipment.

[0087] Write software to control nanomaterial preparation equipment to receive data and adjust equipment status according to preset control logic. Develop a user interface so that operators can easily set parameters, monitor equipment status and perform fault diagnosis.

[0088] The raw material processing degree analysis unit 2 is used to collect production data of nano-preparation raw materials during the crushing process and identify the processing degree of the raw materials based on mining technology.

[0089] In this embodiment, the raw material processing degree analysis unit 2 includes a production data acquisition module, a particle size determination module and a particle size standard comparison module.

[0090] Among them, the production data acquisition module, the particle size determination module and the particle size standard comparison module are connected in sequence.

[0091] The production data acquisition module is used to use the camera at the crusher to capture the video stream of the master alloy ingot during the crushing process within a defined time, and extract the production data frame based on the video stream.

[0092] Specifically, the camera at the crusher is used to capture the video stream of the master alloy ingot during the crushing process within a defined time, and the production data frame is extracted based on the video stream, including:

[0093] Install a high-definition camera at a suitable position of the crusher to ensure that the crushing process of the master alloy ingot can be clearly captured, ensure that the camera is connected to the data processing system, transmit the real-time video stream to the data storage and processing equipment, and denoise the video stream.

[0094] Through image enhancement techniques, such as contrast adjustment and sharpening, and according to the specific situation to be analyzed, the time interval for extracting data frames in the video stream is defined, and key frames are extracted from the video stream according to the defined time interval.

[0095] The particle size obtaining module is used to analyze and process the production data frame using detection technology, obtain the edge contour of the master alloy ingot particles, and obtain the particle size in combination with the fitting parameters.

[0096] Specifically, the production data frame is analyzed and processed using detection technology to obtain the edge profile of the master alloy ingot particles, and the particle size is calculated in combination with the fitting parameters, including:

[0097] Use straight-through filtering and statistical filtering to sharpen the production data frame to remove background points and extract the depth information of the particle pixels in the production data frame;

[0098] The three-dimensional coordinates of the particle pixel points are obtained based on the depth information and the internal and external parameters during camera acquisition to obtain the particle point cloud image, and the production data frame is sliced ​​according to the number of particles according to the slicing technology to obtain the slice image;

[0099] The horizontal and vertical angle differences between adjacent points in the slice image are used to quickly extract the contour points of the particles, and the contour points are filtered.

[0100] Among them, using the horizontal angle and vertical angle differences between adjacent points in the slice image to quickly extract the contour points of the particles, and performing filtering operations on the contour points includes:

[0101] All pixel points in the slice image are defined as a point set, and the initial slice density is set based on the height of the preset point in the point set, and the point set is divided into a number of horizontal slices;

[0102] Project each horizontal slice onto the XY plane, and use the average value of the coordinates of the horizontal slice and all pixel points on the XY plane to determine the horizontal angle of the preset point;

[0103] Obtain the horizontal angles of the remaining pixel points in the point set except the preset point, and sort them into a set according to the size rule. According to the sorted horizontal angles, the horizontal angle difference between two adjacent points is calculated in turn;

[0104] The horizontal angle difference between two adjacent points is compared with the horizontal angle threshold, and similar points with a difference greater than the threshold are set as the contour points of the particles in the vertical direction;

[0105] Divide the point set into several vertical slices based on the horizontal angle of the preset point, analyze the vertical angles of the pixels in each group of vertical slices, and sort the vertical angles in order of size;

[0106] The vertical angle difference between two adjacent groups of pixel points is determined based on the vertical angle sorting result, and compared with the preset angle difference, and the two groups of pixel points whose difference is greater than the preset angle difference are set as the contour points of the particle in the horizontal direction;

[0107] The particle contour points in the horizontal and vertical directions are integrated into an operation set, and the points whose distance from the particle contour points is greater than a set value are removed using statistical filtering.

[0108] It should be noted that the calculation formula for the horizontal angle is:

[0109]

[0110] Where E represents the horizontal angle, u i and u0 represents the coordinates of the pixel point in the XY plane, v i and v0 represents the origin coordinates of the mean pixel value.

[0111] The formula for calculating the vertical angle is:

[0112]

[0113] Where D is the vertical angle, z i Represents the coordinates of the pixel point in the XY plane, and z0 represents the origin coordinates of the pixel mean.

[0114] Based on the enclosing algorithm, all contour points of the slice image are traversed to obtain the area of ​​the enclosing rectangle, and the area sizes of each rectangle are compared. The enclosing rectangle with the smallest area is selected as the extraction option, and the corresponding contour points are projected onto the plane to extract the particle size.

[0115] Among them, based on the enclosing algorithm, all the contour points of the slice image are traversed to obtain the area of ​​the enclosing rectangle, and the area size of each rectangle is compared. The enclosing rectangle with the smallest area is selected as the extraction option, and the corresponding contour points are projected onto the plane to extract the particle size, including:

[0116] The average distance is obtained by statistical analysis based on the distance distribution from each contour point to the adjacent points in the operation set, and the contour points are divided by removing outliers using the difference between the distance threshold and the average distance;

[0117] The contour points are classified based on spatial clustering technology, and the sorting technology is used to extract and sort each contour point. According to the sorted contour points, two adjacent groups of contour points are connected to form line segments to construct the contour of the particle;

[0118] Use the enclosing algorithm to traverse the points farthest from the line segment in all contour points and the two groups of contour points farthest from the perpendicular line of the line segment and on both sides of the perpendicular line;

[0119] The area of ​​the enclosing rectangle is calculated based on the distance from the farthest point to the line segment and the sum of the distances from the contour points on both sides of the perpendicular line to the line segment. The areas of the enclosing rectangles are calculated by traversing all the edges that make up the contour, and the areas of each rectangle are compared.

[0120] The enclosing rectangle with the smallest area is selected as the extraction option, and the outline is projected to the XY plane again to extract the length and width of the particle, and then the outline is projected to the XZ plane to extract the height of the particle to obtain the particle size.

[0121] The particle size standard comparison module is used to compare the particle size of the master alloy ingot with the preset standard size to obtain the overlap, and to determine the degree of crushing of the master alloy ingot based on the overlap result.

[0122] Specifically, comparing the particle size of the master alloy ingot with the preset standard size to obtain the overlap, and judging the degree of crushing of the master alloy ingot based on the overlap result includes:

[0123] constructing similar point vector spaces based on contour points corresponding to the master alloy ingot particles and the preset standard sizes, and converting the contour points into vectors in the similar point vector spaces;

[0124] The vectors are combined into a judgment matrix and input into a preset deep selector. The deep selector is used to extract feature vectors. The Manhattan distance is used to calculate the feature vectors extracted by the deep selector to obtain the distance between two groups of contour points, and the overlap degree is calculated based on the distance of the contour points.

[0125] If the degree of overlap between the particle size of the master alloy ingot and the preset standard size is greater than or equal to the preset value, it means that the degree of crushing of the master alloy ingot particles meets the preparation requirements. If the degree of overlap between the particle size of the master alloy ingot and the preset standard size is less than the preset value, it means that the degree of crushing of the master alloy ingot particles does not meet the preparation requirements.

[0126] It should be explained that the deep selector uses an autoencoder, which is a multi-layer forward neural network that can be used to reduce the dimensionality of high-dimensional data to obtain a low-dimensional feature vector.

[0127] In order to facilitate understanding of the technical solution of the present invention, clear parameters and dimensions are set in this embodiment to analyze and judge the degree of crushing.

[0128] Step 1, production data frame extraction;

[0129] (1) Camera installation: Install a high-resolution camera with a resolution of at least 1080p at a suitable location on the crusher, ensure that the camera can cover the entire crushing area and has adequate lighting, and connect the camera to the data processing system in real time to ensure there is no delay and use a network speed of at least 100Mbps for data transmission.

[0130] (2) Video stream acquisition and transmission: The real-time video stream is transmitted to a data storage device with high-speed writing capability, such as an SSD hard disk. The video stream extraction time interval is defined as at least 30 frames per second to capture sufficient details of the crushing process.

[0131] (3) Video processing and frame extraction: De-noise the video stream, use digital filtering technology to remove environmental interference, and apply image enhancement technology to adjust contrast and sharpness.

[0132] Step 2, extracting the particle size of the master alloy ingot;

[0133] (1) Edge detection: The Canny edge detection algorithm is used with the thresholds set to 100 and 200. Stereo vision technology is applied to slice the particle point cloud every 0.5 mm in height according to the camera’s intrinsic focal length and extrinsic position and angle calculations to generate slice images.

[0134] (2) Contour extraction: The Sobel operator is used to calculate the horizontal and vertical angle differences between adjacent points in the slice image. The horizontal and vertical angle thresholds are set to 10°. The median filter is applied to the extracted contour points with a window size of 3x3.

[0135] (3) Enclosing rectangle and particle size extraction: Use the minimum area rectangle RotatedRect algorithm to find the minimum rectangle enclosing each particle, and calculate the length and width of each minimum enclosing rectangle and the particle height obtained from the slice height.

[0136] (4) Calculation and evaluation of overlap: The overlap threshold is set to 85%, and the overlap between the master alloy ingot particles and the preset standard size is compared using a vector space model. The input feature vector is used to calculate the actual overlap.

[0137] (5) Control and feedback: If the overlap is greater than or equal to 85%, the system marks the crushing degree as satisfied; if it is less than 85%, it is unsatisfactory. Based on the overlap result, the operating parameters of the crusher such as speed and pressure are adjusted to optimize the crushing effect.

[0138] Therefore, the crushing process is captured in real time by a camera to obtain a dynamic view of the raw material crushing process, and the dynamic view is analyzed to accurately obtain the edge contour of the master alloy ingot particles, which is convenient for calculating the particle size. The particle size is compared with the preset standard size to standardize the degree of crushing and ensure product consistency. The particle size overlap result is used to generate control quality to adjust the crusher's working parameters, optimize the crushing process, avoid excessive or insufficient crushing, save energy and materials, and reduce the scrap rate.

[0139] The cored wire integrity prediction unit 3 is used to collect image data during the cored wire processing process using machine vision technology, and to analyze and predict the integrity of the cored wire through recognition technology.

[0140] In this embodiment, the image data of the core-wrapping process is collected by machine vision technology, and the integrity of the core-wrapped wire is predicted by recognition technology analysis, including:

[0141] Suitable cameras or image acquisition devices are installed around the core wrapping processing equipment to capture image data during the processing, and the collected image data are denoised to eliminate environmental noise and image interference.

[0142] The image is enhanced, and the features of the cored wire are extracted from the image using edge detection and morphological operations. The key features of the cored wire, including shape, length, curvature, etc., are identified and extracted.

[0143] Analyze the extracted cored wire features, including the change in curvature, continuity of the lines, etc. According to the analysis results, classify the cored wires and set standard values ​​for integrity, breakage, and bending;

[0144] A prediction model is established using machine learning or deep learning methods to associate the characteristics of the cored wire with its integrity. The prediction model is trained using labeled image data so that it can accurately predict the integrity of the cored wire.

[0145] Furthermore, machine vision technology can be used to achieve real-time monitoring and predictive analysis of the integrity of the core wire during the core processing process, which helps to improve production efficiency and product quality and reduce errors in manual operations.

[0146] The material mechanical stress analysis unit 4 is used to obtain the structural dynamics of the nanomaterial in the heat treatment furnace using the in-situ projection technology, and analyze the mechanical stress of the nanomaterial based on the structural dynamics.

[0147] In this embodiment, the material mechanical stress analysis unit 4 includes a heat treatment monitoring processing module, a structural state model definition module, a dynamic change process reasoning module and a mechanical stress analysis determination module.

[0148] Among them, the heat treatment monitoring processing module, the structural state model definition module, the dynamic change process reasoning module and the mechanical stress analysis and determination module are connected in sequence.

[0149] The heat treatment monitoring processing module is used to monitor the microscopic morphology of the nanomaterial during the annealing process by using an in-situ projection device at the location of the heat treatment furnace.

[0150] Specifically, the in-situ projection equipment at the heat treatment furnace is used to monitor the microscopic morphology of the nanomaterial during the annealing process, including:

[0151] Select in-situ projection equipment that can withstand high temperature environments and provide high-resolution imaging capabilities, and install the in-situ projection equipment at appropriate locations in the heat treatment furnace to ensure that the equipment can capture the microscopic morphology of nanomaterials in all directions.

[0152] Place the nanomaterial semi-finished product in a specific area in the heat treatment furnace, ensure that the sample is flat and within the optimal focal range of the equipment, calibrate the in-situ projection equipment, and set the appropriate focus, exposure time and lighting conditions to obtain a clear image.

[0153] According to the annealing requirements of nanomaterials, the temperature of the heat treatment furnace is set and precisely controlled. The temperature in the furnace is monitored using a temperature sensor to ensure the uniformity and stability of the temperature throughout the annealing process.

[0154] During the entire annealing process, the in-situ projection equipment is used to collect the microscopic morphology images of the nanomaterials in real time, and the collected images are preprocessed in real time, such as denoising and contrast enhancement, to improve the image quality.

[0155] The structural state model definition module is used to analyze the changes in the crystal structure of raw materials in the microscopic morphology using ray diffraction technology, and determine the influence relationship between the crystal structure changes and grain growth and grain defects based on the change results.

[0156] Specifically, the X-ray diffraction technology is used to analyze the changes in the crystal structure of the raw materials in the microscopic morphology, and the influence relationship between the crystal structure changes and grain growth and grain defects is determined based on the change results, including:

[0157] Set the wavelength and scanning angle of the ray diffraction equipment to scan the microscopic morphology to obtain the diffraction spectrum, and use the spectrum analysis software to perform identification and fitting operations on the diffraction spectrum;

[0158] Based on the identification and fitting results, the crystal structure, lattice number, peak width and peak shape of the raw materials during the annealing process are inferred, and the grain size is obtained from the peak width using the size correlation analysis algorithm;

[0159] Analyze the trend of grain growth based on the number of lattices and grain size, and combine quantitative extraction technology with peak shape to identify defects in grains;

[0160] The initial model is defined using the crystal structure, and the influence relationship between the three is reflected based on the grain growth trend and grain defects.

[0161] The dynamic change process reasoning module is used to establish a target state reasoning model based on the state reasoning algorithm, and to reason about the dynamic change process of the raw materials in combination with the influence relationship.

[0162] Specifically, the target state reasoning model is established based on the state reasoning algorithm, and the dynamic change process of the raw materials is inferred by combining the influence relationship, including:

[0163] Based on the trend of grain growth, the number of lattices and grain size in a specified time period are preset as statistical data to determine the change segmentation nodes of the crystal structure in different time periods;

[0164] The state inference algorithm is used to establish the initial inference network and initialize the probability of changing the segmentation node to define the target state inference model, and the multi-level analysis technology is used to perform weighted processing on the statistical data to obtain the state conditional probability between the crystal structure and the number of lattices, and the number of lattices and the grain size.

[0165] Establish the transition probability between adjacent crystal structures based on the state conditional probability results, and infer the dynamic change process of raw materials in the next period based on the state conditional probability and the transition probability;

[0166] Among them, the calculation formula of state conditional probability is:

[0167]

[0168] In the formula, P represents the state conditional probability value; T represents the weighted result; represents the jth change segmentation node in the mth time period; i represents the number of change segmentation nodes; express The parent node can be in the m+1th or m-1th time period.

[0169] It should be explained that the state inference algorithm can use Bayesian network technology. The Bayesian network is called a belief network or a probabilistic graphical model, which is a model used to represent the probabilistic dependency relationship between variables.

[0170] The mechanical stress analysis and determination module is used to combine simulation technology with dynamic change processes to pre-generate prepared nanomaterials, and apply nanoindentation testing technology to analyze the mechanical stress of nanomaterials.

[0171] Specifically, the simulation technology is combined with the dynamic change process to pre-generate the prepared nanomaterials, and the nanoindentation test technology is used to analyze the mechanical stress of the nanomaterials, including:

[0172] Select specific material science simulation software, such as MD (molecular dynamics) simulation or finite element analysis software, set the initial simulation parameters according to the physical and chemical properties of the nanomaterials, perform simulations to dynamically observe the structural changes of the nanomaterials during the preparation process, such as phase changes, lattice rearrangements, etc., and use corresponding monitoring technology to ensure that the microstructure of the material is consistent with the simulation predictions.

[0173] Set up the nanoindentation instrument, ensure that the test needle tip is suitable for the hardness and elastic modulus range of the material, prepare the nanomaterial sample, set the parameters such as indentation depth, loading rate and holding time according to the material characteristics, and conduct the indentation experiment, and record the loading and unloading curves in real time, including the relationship between load and displacement.

[0174] Analyze load-displacement curves to determine the hardness and modulus of materials and analyze mechanical stress in nanomaterials.

[0175] In order to facilitate understanding of the technical solution of the present invention, clear parameters are set in this embodiment to analyze the mechanical stress.

[0176] Step 1, in-situ projection equipment setting and annealing treatment;

[0177] (1) Equipment selection and installation: Select an in-situ X-ray diffraction device that is resistant to high temperatures (operable up to 1200°C), install it above the heat treatment furnace, align the center with the sample position, and place the nanomaterial sample in the furnace. Set the sample size to approximately 10 mm*10 mm*1 mm, and adjust the position to ensure that the sample is within the optimal focal length of the device (approximately 50 cm);

[0178] (2) Parameter setting: Set the furnace temperature to 950°C, the heating rate to 5°C / min, the holding time to 2 hours, the cooling rate to room temperature to 10°C / min, and the wavelength of the radiation to (Copper target Kα ray), scanning angle from 20° to 80°, step of 0.02°;

[0179] (3) Real-time monitoring and analysis of microstructure: During the annealing process, X-ray diffraction patterns are automatically collected every 10 minutes, and analysis software is used to perform real-time denoising and peak fitting on the diffraction patterns to identify changes in the crystal structure;

[0180] (4) Grain size calculation: The grain size is calculated based on the peak width using the Scherrer formula. The specific formula is: Where K is the shape factor (about 0.9), α is the wavelength of the ray, β is the peak width, and θ is the Bragg angle.

[0181] Step 2: Nanoindentation test;

[0182] (1) Equipment settings: Berkovich tip was used, hardness was set to 4500 HV, loading depth was set to 200 nm, loading rate was 10 nm / s, holding time was 10 s, and loading and unloading force-displacement curves were recorded every 5 s.

[0183] (2) Data analysis and material performance evaluation: The hardness is calculated using the Oliver-Pharr method, where the hardness calculation formula is: Q max represents the maximum load, A represents the contact area; the elastic modulus of the material is estimated using the initial slope of the unloading curve and the surface area of ​​the sample, and the mechanical stress of the nanomaterial is analyzed based on the hardness and modulus of the material.

[0184] Therefore, by real-time monitoring of the microscopic morphology of the material, slight changes in the material morphology during the annealing process can be discovered, and the application of diffraction pattern analysis can accurately determine the changes in the crystal structure and determine the relationship between the crystal structure changes and grain growth and grain defects. At the same time, the inference algorithm is used to help predict the behavior of the material under different states and predict the performance of nanomaterials, thereby reducing uncertainty in production and optimizing the product preparation process.

[0185] The control instruction generation and execution unit 5 is used to generate control instructions for corresponding equipment according to the raw material processing degree, the core wire integrity and the mechanical stress judgment result, and feed back to the processing platform.

[0186] In this embodiment, the control instructions of the corresponding equipment are generated according to the raw material processing degree, the integrity of the cored wire and the mechanical stress judgment results, and the control instructions are fed back to the processing platform, including:

[0187] Collect data on raw material processing degree, core wire integrity and mechanical stress from testing equipment and simulation software, and extract key features from the collected data, such as processing degree index, integrity score, stress level, etc.

[0188] Apply the preset rule set to determine the current state of the device, apply decision logic based on the model judgment result to generate specific control instructions, and format the control instructions into a format that can be recognized by the processing platform.

[0189] The control instructions are sent to the processing platform through the set communication protocol. The processing platform adjusts the equipment parameters or operating procedures according to the received control instructions, and collects feedback data after the equipment adjustment for closed-loop control.

[0190] Specifically, the degree of raw material processing is expressed as a score of 0-100, the integrity of the cored wire is expressed as a probability of 0-1, and the mechanical stress is given by the nanoindentation test in MPa. In practical applications, the parameters and models may need to be adjusted according to the specific situation.

[0191] If the processing degree is lower than 85 points, increase the processing intensity; if the completeness is lower than 0.9, adjust the core wrapping machine speed; if the stress exceeds 200MPa, reduce the processing depth.

[0192] The above decisions are converted into machine-readable instruction codes, and the instructions are sent to the processing platform through the TCP / IP protocol. The processing platform then adjusts the relevant equipment parameters according to the instructions.

[0193] See also Figure 2 The present invention also provides a nanomaterial preparation process for preparing the nanomaterial, the nanomaterial preparation process comprising the following steps:

[0194] S1. Selecting a preset mass fraction of iron, silicon, aluminum, copper, molybdenum, chromium and composite rare earth as spare materials, and fusing the iron, copper, molybdenum and chromium for smelting to obtain a master alloy ingot;

[0195] S2, placing the master alloy ingot into a crusher for crushing to obtain raw materials, and using the raw material processing degree analysis unit 2 to identify the crushing degree of the raw materials;

[0196] S3, using aluminum to core silicon and composite rare earth to obtain a cored wire, and performing analysis on the integrity of the cored wire based on the cored wire integrity prediction unit 3;

[0197] S4, placing the raw materials and the cored wire into a rotary quenching furnace to melt and obtain a semi-finished nanomaterial product, and using a heat treatment furnace to anneal the semi-finished nanomaterial product to obtain the nanomaterial;

[0198] S5, performing structural dynamic analysis on the nanomaterial using the material mechanical stress analysis unit 4 during the annealing process, and determining the mechanical stress of the nanomaterial based on the analysis result;

[0199] S6. Use the control execution platform building unit 1 to build a processing platform to connect with the preparation equipment, generate control instructions based on the processing results of steps S2 to S4 and feed them back to the control instruction generation unit 5 to adjust the control parameters of each device.

[0200] In summary, with the help of the above technical scheme of the present invention, when the mother alloy ingot is crushed, the present invention can monitor and analyze the crushing degree of the raw materials in real time, and then when the crushing degree does not meet the preset standard, corresponding adjustments can be made to achieve the ideal processing effect, prevent excessive crushing of the raw materials, save costs and avoid material waste, and at the same time, it can also obtain the structural changes of nanomaterials at high temperatures in real time, and use three-dimensional simulation to analyze the mechanical stress of the finished nanomaterials to predict fatigue and failure, thereby significantly improving the accuracy and efficiency of nanomaterials in preparation. The present invention uses a camera to capture the crushing process in real time to obtain a dynamic view of the raw material crushing process, and analyzes the dynamic view to accurately obtain the edge contour of the mother alloy ingot particles, thereby facilitating the calculation of the particle size, and compares the particle size with the preset standard size, which can standardize the crushing degree, ensure product consistency, and use the particle size overlap result to generate control quality to adjust the working parameters of the crusher, optimize the crushing process, avoid excessive crushing or insufficient crushing, save energy and materials, and reduce the scrap rate. The present invention monitors the microscopic morphology of the material in real time to discover slight changes in the material morphology during the annealing process, and uses diffraction pattern analysis to accurately determine changes in the crystal structure and determine the relationship between the crystal structure changes and grain growth and grain defects. At the same time, the inference algorithm is used to help predict the behavior of the material in different states and predict the performance of the nanomaterial, thereby reducing uncertainty in production and optimizing the product preparation process.

[0201] Those skilled in the art will appreciate that the units, i.e., algorithm steps, of the various examples described in conjunction with this embodiment can be implemented in electronic hardware or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0202] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. An identification system for preparing nanomaterials, characterized in that: The identification system comprises a control execution platform building unit (1), a raw material processing degree analysis unit (2), a cored wire integrity prediction unit (3), a material mechanical stress analysis unit (4) and a control instruction generation execution unit (5); The control execution platform building unit (1), the raw material processing degree analysis unit (2), the cored wire integrity prediction unit (3), the material mechanical stress analysis unit (4) and the control instruction generation execution unit (5) are connected in sequence; The control execution platform building unit (1) is used to build a processing platform and coordinate control with the nano material preparation equipment, and receive control instructions to adjust the operating state of the nano material preparation equipment; The raw material processing degree analysis unit (2) is used to collect production data of the nano-preparation raw materials during the crushing process and identify the processing degree of the raw materials based on mining technology; The cored wire integrity prediction unit (3) is used to collect image data during the cored wire processing process using machine vision technology, and to analyze and predict the integrity of the cored wire through recognition technology; The material mechanical stress analysis unit (4) is used to obtain the structural dynamics of the nanomaterial in the heat treatment furnace using the in-situ projection technology, and analyze the mechanical stress of the nanomaterial based on the structural dynamics; The control instruction generation and execution unit (5) is used to generate control instructions for corresponding equipment according to the raw material processing degree, the cored wire integrity and the mechanical stress judgment result, and feed back the control instructions to the processing platform.

2. The identification system for preparing nanomaterials according to claim 1, characterized in that: The raw material processing degree analysis unit (2) comprises a production data acquisition module, a particle size determination module and a particle size standard comparison module; Wherein, the production data acquisition module, the particle size determination module and the particle size standard comparison module are connected in sequence; The production data acquisition module is used to capture the video stream of the master alloy ingot during the crushing process within a defined time using a camera at the crusher, and extract the production data frame based on the video stream; The particle size obtaining module is used to analyze and process the production data frame using detection technology to obtain the edge profile of the master alloy ingot particles and obtain the particle size in combination with the fitting parameters; The particle size standard comparison module is used to compare the particle size of the master alloy ingot with the preset standard size to obtain the overlap, and to determine the degree of crushing of the master alloy ingot based on the overlap result.

3. The identification system for preparing nanomaterials according to claim 2, characterized in that: The method of analyzing and processing the production data frame by using the detection technology to obtain the edge profile of the master alloy ingot particles and calculating the particle size by combining the fitting parameters includes: Use straight-through filtering and statistical filtering to sharpen the production data frame to remove background points and extract the depth information of the particle pixels in the production data frame; The three-dimensional coordinates of the particle pixel points are obtained based on the depth information and the internal and external parameters during camera acquisition to obtain the particle point cloud image, and the production data frame is sliced ​​according to the number of particles according to the slicing technology to obtain the slice image; The contour points of the particles are extracted quickly by using the horizontal and vertical angle differences between adjacent points in the slice image, and the contour points are filtered. Based on the enclosing algorithm, all contour points of the slice image are traversed to obtain the area of ​​the enclosing rectangle, and the area sizes of each rectangle are compared. The enclosing rectangle with the smallest area is selected as the extraction option, and the corresponding contour points are projected onto the plane to extract the particle size.

4. The identification system for preparing nanomaterials according to claim 3, characterized in that: The method of extracting the contour points of the particles by using the horizontal angle and vertical angle differences between adjacent points in the slice image and performing filtering operations on the contour points comprises: All pixel points in the slice image are defined as a point set, and the initial slice density is set based on the height of the preset point in the point set, and the point set is divided into a number of horizontal slices; Project each horizontal slice onto the XY plane, and use the average value of the coordinates of the horizontal slice and all pixel points on the XY plane to determine the horizontal angle of the preset point; Obtain the horizontal angles of the remaining pixel points in the point set except the preset point, and sort them into a set according to the size rule. According to the sorted horizontal angles, the horizontal angle difference between two adjacent points is calculated in turn; The horizontal angle difference between two adjacent points is compared with the horizontal angle threshold, and similar points with a difference greater than the threshold are set as the contour points of the particles in the vertical direction; Divide the point set into several vertical slices based on the horizontal angle of the preset point, analyze the vertical angles of the pixels in each group of vertical slices, and sort the vertical angles in order of size; The difference in vertical angles between two adjacent groups of pixel points is determined based on the vertical angle sorting result, and compared with a preset angle difference, and two groups of pixel points whose difference is greater than the preset angle difference are set as contour points of the particle in the horizontal direction; The particle contour points in the horizontal and vertical directions are integrated into an operation set, and the points whose distance from the particle contour points is greater than a set value are removed using statistical filtering.

5. The identification system for preparing nanomaterials according to claim 4, characterized in that: The method of traversing all contour points of the slice image based on the enclosing algorithm to obtain the area of ​​the enclosing rectangle, comparing the area sizes of the rectangles, selecting the enclosing rectangle with the smallest area as the extraction option, and projecting the corresponding contour points onto the plane to extract the particle size includes: The average distance is obtained by statistical analysis based on the distance distribution from each contour point to the adjacent points in the operation set, and the contour points are divided by removing outliers using the difference between the distance threshold and the average distance; The contour points are classified based on spatial clustering technology, and the sorting technology is used to extract and sort each contour point. According to the sorted contour points, two adjacent groups of contour points are connected to form line segments to construct the contour of the particle; Use the enclosing algorithm to traverse the points farthest from the line segment in all contour points and the two groups of contour points farthest from the perpendicular line of the line segment and on both sides of the perpendicular line; The area of ​​the enclosing rectangle is calculated based on the sum of the distance from the farthest point to the line segment and the distance from the contour points on both sides of the perpendicular line to the line segment. The areas of the enclosing rectangles are calculated by traversing all the edges that make up the contour, and the areas of each rectangle are compared. The enclosing rectangle with the smallest area is selected as the extraction option, and the outline is projected to the XY plane again to extract the length and width of the particle, and then the outline is projected to the XZ plane to extract the height of the particle to obtain the particle size.

6. The identification system for preparing nanomaterials according to claim 5, characterized in that: The step of comparing the particle size of the master alloy ingot with the preset standard size to obtain the overlap, and judging the degree of crushing of the master alloy ingot based on the overlap result includes: constructing similar point vector spaces based on contour points corresponding to the master alloy ingot particles and the preset standard sizes, and converting the contour points into vectors in the similar point vector spaces; The vectors are combined into a judgment matrix and input into a preset deep selector. The deep selector is used to extract feature vectors. The Manhattan distance is used to calculate the feature vectors extracted by the deep selector to obtain the distance between two groups of contour points, and the overlap degree is calculated based on the distance of the contour points. If the degree of overlap between the particle size of the master alloy ingot and the preset standard size is greater than or equal to the preset value, it means that the degree of crushing of the master alloy ingot particles meets the preparation requirements. If the degree of overlap between the particle size of the master alloy ingot and the preset standard size is less than the preset value, it means that the degree of crushing of the master alloy ingot particles does not meet the preparation requirements.

7. The identification system for preparing nanomaterials according to claim 1, characterized in that: The material mechanical stress analysis unit (4) comprises a heat treatment monitoring processing module, a structural state model definition module, a dynamic change process reasoning module and a mechanical stress analysis and determination module; The heat treatment monitoring processing module, the structural state model definition module, the dynamic change process reasoning module and the mechanical stress analysis and determination module are connected in sequence; The heat treatment monitoring module is used to monitor the microscopic morphology of the nanomaterial during the annealing process by using an in-situ projection device at the location of the heat treatment furnace; The structural state model definition module is used to analyze the crystal structure changes of raw materials in the microscopic morphology by using ray diffraction technology, and determine the influence relationship between the crystal structure changes and grain growth and grain defects based on the change results; The dynamic change process reasoning module is used to establish a target state reasoning model based on the state reasoning algorithm, and to reason about the dynamic change process of the raw material in combination with the influence relationship; The mechanical stress analysis and determination module is used to combine simulation technology with a dynamic change process to pre-generate a prepared nanomaterial, and to apply nanoindentation testing technology to analyze the mechanical stress of the nanomaterial.

8. The identification system for preparing nanomaterials according to claim 7, characterized in that: The method of analyzing the crystal structure change of raw materials in the microscopic morphology by using the ray diffraction technology and determining the influence relationship between the crystal structure change and the grain growth and grain defects based on the change results includes: Set the wavelength and scanning angle of the ray diffraction equipment to scan the microscopic morphology to obtain the diffraction spectrum, and use the spectrum analysis software to perform identification and fitting operations on the diffraction spectrum; Based on the identification and fitting results, the crystal structure, lattice number, peak width and peak shape of the raw materials during the annealing process are inferred, and the grain size is obtained from the peak width using the size correlation analysis algorithm; Analyze the trend of grain growth based on the number of lattices and grain size, and combine quantitative extraction technology with peak shape to identify defects in grains; The initial model is defined using the crystal structure, and the influence relationship between the three is reflected based on the grain growth trend and grain defects.

9. The identification system for preparing nanomaterials according to claim 8, characterized in that: The process of establishing a target state reasoning model based on the state reasoning algorithm and reasoning about the dynamic changes of the raw materials in combination with the influence relationship includes: Based on the trend of grain growth, the number of lattices and grain size in a specified time period are preset as statistical data to determine the change segmentation nodes of the crystal structure in different time periods; The state inference algorithm is used to establish the initial inference network and initialize the probability of changing the segmentation node to define the target state inference model, and the multi-level analysis technology is used to perform weighted processing on the statistical data to obtain the state conditional probability between the crystal structure and the number of lattices, and the number of lattices and the grain size. Establish the transition probability between adjacent crystal structures based on the state conditional probability results, and infer the dynamic change process of raw materials in the next period based on the state conditional probability and the transition probability; The calculation formula of the state conditional probability is: In the formula, P represents the state conditional probability value; T represents the weighted result; represents the jth change segmentation node in the mth time period; i represents the number of change segmentation nodes; express The parent node of .

10. A nanomaterial preparation process for preparing a nanomaterial, used to prepare the nanomaterial according to any one of claims 1 to 9, characterized in that: The nano material preparation process comprises the following steps: S1. Selecting a preset mass fraction of iron, silicon, aluminum, copper, molybdenum, chromium and composite rare earth as spare materials, and fusing the iron, copper, molybdenum and chromium for smelting to obtain a master alloy ingot; S2, placing the master alloy ingot into a crusher for crushing to obtain raw materials, and using the raw material processing degree analysis unit (2) to identify the crushing degree of the raw materials; S3, using aluminum to core silicon and composite rare earth to obtain a cored wire, and performing analysis on the integrity of the cored wire based on the cored wire integrity prediction unit (3); S4, placing the raw materials and the cored wire into a rotary quenching furnace to melt and obtain a semi-finished nanomaterial product, and using a heat treatment furnace to anneal the semi-finished nanomaterial product to obtain the nanomaterial; S5, performing structural dynamic analysis on the nanomaterial using the material mechanical stress analysis unit (4) during the annealing process, and determining the mechanical stress of the nanomaterial based on the analysis result; S6. Use the control execution platform building unit (1) to build a processing platform to connect with the preparation equipment, generate control instructions based on the processing results of steps S2 to S4 and feed them back to the control instruction generation unit (5) to adjust the control parameters of each device.

Images