Intelligent adaptive system and method in blade processing

Abstract

The present invention belongs to the technical field of tool processing, and discloses an intelligent adaptive system and method in a blade processing process; the method comprises: collecting physical parameters of a blade processing material; obtaining the processing parameters of the blade in real time; collecting in real time a surface image of the processing material within a unit time; processing the surface image of the processing material within a unit time to obtain a crystal orientation matrix set; inputting the physical parameters and the crystal orientation matrix set into a crystal orientation prediction model to obtain a crystal orientation matrix for a future unit time; based on the physical parameters, processing parameters, the crystal orientation matrix set and the crystal orientation matrix for a future unit time, performing intelligent adaptive adjustment on the processing parameters of the blade; the scheme of the present invention combines physical parameters, processing parameters and crystal orientation prediction, so that tool processing can be adaptively adjusted according to the actual state of the processing material, dynamically optimizes the processing parameters, and improves the stability of processing quality and the durability of the tool.

Description

Technical Field

[0001] The present invention relates to the technical field of tool processing, and more particularly to an intelligent self-adaptive system and method in a blade processing process. Background Art

[0002] In the processing of superhard materials, existing technologies generally focus on the macroscopic properties of the material, while ignoring the microscopic orientation differences within the crystal. The complex crystal structure characteristics lead to significant anisotropy during the processing, making it difficult to achieve optimal processing accuracy and efficiency for superhard materials. Although existing technologies attempt to adapt to the properties of different materials by adjusting cutting parameters, these methods are generally based on the material type and hardness, and do not fully consider the orientation changes within the crystal.

[0003] When machining superhard materials with blades, even when the material type and hardness are known before machining, existing technologies fail to account for the significant differences in cutting forces, blade wear mechanisms, and friction characteristics associated with different crystal orientations. Furthermore, they fail to adaptively adjust machining parameters for different crystal orientations, resulting in uneven loading on the blades, exacerbating localized wear and micro-chipping, and impacting machining accuracy for high-hardness materials. Furthermore, the high cost of blades dictates that their service life and stability are crucial to overall machining efficiency. Failure to consider crystal orientation optimization can shorten blade life and increase replacement frequency, reducing production cycle time and machining stability, making it difficult to achieve optimal machining quality and efficiency.

[0004] Therefore, there is an urgent need for an effective intelligent system that can dynamically identify crystal orientation and dynamically optimize cutting strategies during the processing process, thereby optimizing blade wear, improving blade processing accuracy and overall processing efficiency. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: an intelligent adaptive method in the blade processing process, comprising:

[0006] Collect physical parameters of the blade processing material;

[0007] Get the real-time blade processing parameters;

[0008] Real-time acquisition of surface images of processed materials within a unit of time;

[0009] Processing the surface image of the processed material within a unit time to obtain a set of crystal orientation matrices;

[0010] Input the physical parameters and crystal orientation matrix set into the crystal orientation prediction model to obtain the crystal orientation matrix per unit time in the future;

[0011] Based on physical parameters, processing parameters, crystal orientation matrix set and crystal orientation matrix of future unit time, the processing parameters of the blade are intelligently and adaptively adjusted.

[0012] Furthermore, the method for intelligently and adaptively adjusting the processing parameters of the blade includes:

[0013] Count the occurrence frequency of each crystal orientation matrix in the crystal orientation matrix set, select the crystal orientation matrix with the highest occurrence frequency, and record it as the crystal main orientation matrix;

[0014] The crystal orientation angle difference is calculated based on the crystal main orientation matrix and the crystal orientation matrix of the future unit time;

[0015] If the crystal orientation angle difference is greater than or equal to the preset crystal orientation angle difference threshold, it is considered that the crystal orientation has changed and intelligent adaptive adjustment is required;

[0016] Obtaining crystal type from physical parameters;

[0017] If the crystal type is single crystal material, the processing parameters are intelligently and adaptively adjusted for the single crystal material;

[0018] If the crystal type is polycrystalline material, the processing parameters are intelligently and adaptively adjusted for the polycrystalline material.

[0019] Furthermore, the method for intelligently and adaptively adjusting processing parameters for single crystal materials includes:

[0020] Step 1: setting a single crystal orientation angle difference threshold value 1 and a single crystal orientation angle difference threshold value 2 for the single crystal material; the single crystal orientation angle difference threshold value 1 is smaller than the single crystal orientation angle difference threshold value 2;

[0021] Step 2: If the crystal orientation angle difference is less than the single crystal orientation angle difference threshold 1, there is no need to adjust the processing parameters of the single crystal material;

[0022] If the crystal orientation angle difference is greater than or equal to a single crystal orientation angle difference threshold value 1 and less than a single crystal orientation angle difference threshold value 2, inputting the crystal type, the crystal orientation angle difference, and the processing parameters into a blade processing parameter setting model to obtain target processing parameters, wherein the target processing parameters include a target cutting force, a target cutting speed, a target cutting depth, a target tool temperature, and a target vibration amplitude; and adjusting the blade processing parameters to the target processing parameters;

[0023] If the crystal orientation angle difference is greater than or equal to the single crystal orientation angle difference threshold value 2, the crystal plane of the currently processed single crystal material is not suitable for processing, and a crystal plane switching operation is performed to adjust to the crystal plane of the single crystal material adjacent to the crystal plane of the currently processed single crystal material;

[0024] Step 3: Repeat step 2 until the processing of the single crystal material is completed.

[0025] Furthermore, the method for intelligently and adaptively adjusting processing parameters for polycrystalline materials includes:

[0026] Step 1: Set the polycrystalline orientation angle difference threshold for polycrystalline materials;

[0027] Step 2: If the crystal orientation angle difference is less than the polycrystalline orientation angle difference threshold, there is no need to adjust the processing parameters of the polycrystalline material;

[0028] If the crystal orientation angle difference is greater than or equal to the polycrystalline orientation angle difference threshold, the crystal type, the crystal orientation angle difference and the processing parameters are input into the blade processing parameter setting model to obtain the target processing parameters;

[0029] Step 3: Adjust the processing parameters of the blade to the target processing parameters;

[0030] Step 4: Repeat steps 2 to 3 until the processing of the polycrystalline material is completed.

[0031] Furthermore, the method for obtaining the crystal orientation matrix set includes:

[0032] S100: Divide the unit time into N time points, set the initial value of n to 1, and set the value range of n to 1 to N;

[0033] S101: Acquire a surface image of a processed material at the nth time point; divide the surface image of the processed material into M sub-regions, which are recorded as surface sub-images of the processed material;

[0034] S102: performing diffraction band detection processing on M sub-images of the processed material surface to obtain Kikuchi diffraction bands corresponding to the M sub-images of the processed material surface;

[0035] S103: obtaining crystal orientation matrices corresponding to M surface sub-images of the processed material based on the M Kikuchi diffraction bands;

[0036] S104: performing matrix numerical comparison on the M crystal orientation matrices to obtain the crystal orientation matrix of the surface image of the processed material at the nth time point;

[0037] S105: Let n=n+1. If n is less than or equal to N, continue to execute S101 to S104. If n is greater than N, obtain the crystal orientation matrix of the surface image of the processed material corresponding to N time points, and execute S106.

[0038] S106: Constructing the crystal orientation matrices of the processed material surface images corresponding to N time points into a crystal orientation matrix set.

[0039] Furthermore, a method for obtaining Kikuchi diffraction bands corresponding to the M sub-images of the processed material surface includes:

[0040] S200: Let the initial value of m be 1, and the value range of m be 1 to M;

[0041] S201: Acquire the mth sub-image of the surface of the processed material; update the mth sub-image of the surface of the processed material into a sub-image of the surface of the processed material with two-dimensional coordinates through an image processing library;

[0042] S202: Record the number of pixels in the mth processed material surface sub-image as R; calculate the corresponding diffraction band gradient matrix for each of the R pixels;

[0043] S203: Inputting the physical parameters of the blade processing material and R diffraction band gradient matrices into a diffraction band gradient threshold setting model to obtain a diffraction band gradient threshold;

[0044] S204: constructing a Kikuchi diffraction band of the mth processed material surface sub-image based on R diffraction band gradient matrices and diffraction band gradient thresholds;

[0045] S205: Let m=m+1. If m is less than or equal to M, continue executing S201 to S204. If m is greater than M, obtain M Kikuchi diffraction bands corresponding to the surface sub-images of the processed material, and end the current process.

[0046] Furthermore, a method for constructing a Kikuchi diffraction band of the mth processed material surface sub-image based on R diffraction band gradient matrices and a diffraction band gradient threshold includes:

[0047] S300: Let the initial value of r be 1, and the value range of r be 1 to R;

[0048] S301: Obtain the rth diffraction zone gradient matrix, and perform diffraction zone gradient threshold determination on each element value in the matrix, record the elements whose element values ​​are greater than or equal to the diffraction zone gradient threshold as diffraction zone elements, and count the number of diffraction zone elements, which is recorded as the number of diffraction zone elements; record the elements whose element values ​​are less than the diffraction zone gradient threshold as non-diffraction zone elements, and count the number of non-diffraction zone elements, which is recorded as the number of non-diffraction zone elements;

[0049] S302: summing the number of diffraction zone elements and the number of non-diffraction zone elements to obtain the total number of elements; dividing the number of diffraction zone elements by the total number of elements to obtain the diffraction zone element ratio;

[0050] S303: If the diffraction zone element ratio is greater than or equal to a preset diffraction zone element ratio threshold, then mark the pixel corresponding to the rth diffraction zone gradient matrix as a diffraction zone pixel; if the diffraction zone element ratio is less than the preset diffraction zone element ratio threshold, then mark the pixel corresponding to the rth diffraction zone gradient matrix as a non-diffraction zone pixel;

[0051] S304: Let r = r + 1. If r is less than or equal to R, continue executing S301 to S303. If r is greater than R, execute S305.

[0052] S305: Based on all diffraction band pixels, a pixel connection algorithm is used to connect the discrete diffraction band pixels into complete diffraction band lines to obtain the Kikuchi diffraction band of the mth processed material surface sub-image.

[0053] Furthermore, a method for obtaining the crystal orientation matrix corresponding to the M processed material surface sub-images includes:

[0054] S400: Let the initial value of m be 1, and the value range of m be 1 to M;

[0055] S401: Obtaining the Kikuchi diffraction band of the mth processed material surface sub-image; selecting three independent diffraction band normal vectors from the Kikuchi diffraction band, and recording them as diffraction band normal vector 1, diffraction band normal vector 2, and diffraction band normal vector 3, respectively;

[0056] S402: constructing a diffraction zone normal vector matrix from the first diffraction zone normal vector, the second diffraction zone normal vector, and the third diffraction zone normal vector;

[0057] S403: Calculating a first diffraction direction angle, a second diffraction direction angle, and a third diffraction direction angle based on the diffraction zone normal vector matrix;

[0058] S404: constructing a diffraction direction cosine matrix 1 based on the diffraction direction angle 1, constructing a diffraction direction cosine matrix 2 based on the diffraction direction angle 2, and constructing a diffraction direction cosine matrix 3 based on the diffraction direction angle 3;

[0059] S405: performing matrix multiplication on the diffraction direction cosine matrix 1, the diffraction direction cosine matrix 2, and the diffraction direction cosine matrix 3 to obtain a crystal orientation matrix corresponding to the mth processed material surface sub-image;

[0060] S406: Let m=m+1. If m is less than or equal to M, continue executing S401 to S405. If m is greater than M, obtain the crystal orientation matrices corresponding to the M sub-images of the processed material surface, and end the current process.

[0061] Furthermore, a method for obtaining a crystal orientation matrix of a surface image of a processed material at an n-th time point includes:

[0062] S500: Let the initial value of m be 1, and the value range of m be 1 to M; pre-construct a crystal orientation matrix key-value pair set; the crystal orientation matrix key-value pair set includes a crystal orientation matrix key-value pair; the crystal orientation matrix key-value pair includes a key and a value, the key is the crystal orientation matrix, the key is initially empty, the value is the number corresponding to the crystal orientation matrix, and the initial value of the value is 0;

[0063] S501: Obtain the mth crystal orientation matrix; if the mth crystal orientation matrix has the same key as the crystal orientation matrix key-value pair in the crystal orientation matrix key-value pair set, then increase the value corresponding to the crystal orientation matrix key-value pair by one; if the mth crystal orientation matrix has different keys from the crystal orientation matrix key-value pair in the crystal orientation matrix key-value pair set, then create a new crystal orientation matrix key-value pair, use the mth crystal orientation matrix as the key of the new crystal orientation matrix key-value pair, increase the value of the new crystal orientation matrix key-value pair by one; and add the new crystal orientation matrix key-value pair to the crystal orientation matrix key-value pair set;

[0064] S502: Let m=m+1. If m is less than or equal to M, continue to execute S501; if m is greater than M, execute S503;

[0065] S503: Retrieve the crystal orientation matrix key-value pair with the maximum value from the crystal orientation matrix key-value pair set, use the key of the crystal orientation matrix key-value pair with the maximum value as the crystal orientation matrix of the surface image of the processed material at the nth time point, and end the current process.

[0066] An intelligent self-adaptive system in a blade processing process implements the intelligent self-adaptive method in the blade processing process, including:

[0067] The first acquisition module collects physical parameters of the blade processing material;

[0068] The second acquisition module is used to obtain the real-time processing parameters of the blade;

[0069] The third acquisition module is used to collect the surface image of the processed material in unit time in real time;

[0070] The first processing module processes the surface image of the processed material within a unit time to obtain a crystal orientation matrix set;

[0071] An orientation prediction module is used to input the physical parameters and the crystal orientation matrix set into the crystal orientation prediction model to obtain the crystal orientation matrix per unit time in the future;

[0072] The intelligent optimization module performs intelligent adaptive adjustment of the blade's processing parameters based on physical parameters, processing parameters, crystal orientation matrix set and crystal orientation matrix of future unit time.

[0073] Compared with the prior art, the technical effects and advantages of the intelligent adaptive system and method in the blade processing process of the present invention are as follows:

[0074] The present invention provides an intelligent adaptive system and method for blade processing, which can monitor the crystal orientation changes of the processed material in real time and dynamically optimize the processing parameters in combination with the predicted future unit time crystal orientation matrix.

[0075] For single crystal materials, this solution sets a single crystal orientation angle difference threshold. By monitoring the changes in the crystal orientation angle difference, it intelligently determines whether it is necessary to adjust the processing parameters or perform a face-changing operation. For cases where the crystal orientation angle difference is small, the original processing parameters are maintained to avoid unnecessary adjustments, thereby improving processing continuity and efficiency. When the crystal orientation angle difference enters the set range, the target processing parameters are obtained based on the blade processing parameter setting model, and adaptive adjustments are made to ensure that the processing process is always in the optimal crystal plane, thereby improving tool life and processing accuracy. If the crystal orientation angle difference exceeds the set threshold, it indicates that the current crystal plane is no longer suitable for continued processing. The system automatically performs a face-changing operation, switching to the adjacent crystal plane to ensure processing stability and consistency.

[0076] For polycrystalline materials, due to the randomness of their internal grain orientation, it is difficult to accurately determine the need for face replacement by relying solely on the orientation angle difference. Therefore, this solution adopts a dynamic adjustment method for processing parameters. For areas with small orientation variation, the original processing parameters are maintained, unnecessary adjustments are reduced, and processing efficiency is improved. When the orientation variation enters the set range, the system optimizes the target processing parameters based on the blade processing parameter setting model to adapt to complex orientation changes, reduce tool wear, improve processing quality, and ensure processing stability.

[0077] The solution of the present invention combines physical parameters, processing parameters and crystal orientation prediction, and realizes intelligent optimization through machine learning models and real-time monitoring data, so that tool processing can be adaptively adjusted according to the actual state of the processed material. Compared with the existing technology, it significantly improves the processing efficiency, quality stability and tool durability, and has important application value in the field of superhard blade processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 Schematic diagram of the intelligent adaptive system during blade processing according to Example 1 of the present invention;

[0079] Figure 2 This is a flow chart of the intelligent adaptive method in the blade processing process according to Example 2 of the present invention;

[0080] Figure 3 A flow chart of a method for intelligently and adaptively adjusting the machining parameters of a blade;

[0081] Figure 4Schematic diagram of Kikuchi diffraction bands of single crystal materials;

[0082] Figure 5 Schematic diagram of Kikuchi diffraction bands of polycrystalline materials;

[0083] Figure 6 Schematic diagram of the curve showing the change of crystal orientation angle difference over time. DETAILED DESCRIPTION

[0084] The technical solutions in the embodiments of the present invention will be described in detail, clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. It should be noted that the specific embodiments described below are only used to better illustrate and describe the technical solutions of the present invention, and are intended to enable those skilled in the art to better understand and implement the present invention, and should not be construed as limiting the scope of protection of the present invention. Without departing from the spirit and essence of the present invention, those skilled in the art may modify, adjust or make equivalent replacements based on the contents disclosed in the present invention, and these should all be regarded as the scope of protection of the present invention.

[0085] Example 1

[0086] See also Figure 1 As shown, the intelligent adaptive system in the blade processing process described in this embodiment includes a first acquisition module, a second acquisition module, a third acquisition module, a first processing module, an orientation prediction module and an intelligent optimization module. Each module realizes data transmission through wired and / or wireless connections.

[0087] The first acquisition module collects physical parameters of the blade processing material; the physical parameters include crystal type, material hardness, elastic modulus, fracture toughness, thermal conductivity and specific heat capacity, and the crystal type includes single crystal material and polycrystalline material.

[0088] It should be noted that physical parameters such as crystal type, material hardness, elastic modulus, fracture toughness, thermal conductivity and specific heat capacity can be obtained from the technical manual of the manufacturer or supplier, or from the material database.

[0089] During tool processing, physical parameters such as the crystal type, material hardness, elastic modulus, fracture toughness, thermal conductivity and specific heat capacity of the processing material have a direct impact on the processing performance. The rational collection and utilization of these physical parameters are crucial for optimizing the processing technology and improving processing quality and efficiency. The crystal type determines the anisotropic characteristics of the material, affecting the directionality of the cutting force and the wear pattern of the tool during the cutting process; the hardness of the material is directly related to the difficulty of cutting, affecting the wear rate of the tool and the quality of the processed surface; the elastic modulus affects the degree of deformation of the material under the action of the cutting force, and determines the load response of the tool and the processing accuracy; the fracture toughness determines the material's resistance to cracking, affecting the material's chip breaking method and the risk of tool chipping during the cutting process; the thermal conductivity and specific heat capacity determine the conduction and accumulation of heat during the cutting process, directly affecting the tool temperature, thermal expansion effect and processing stability.

[0090] Therefore, collecting the above physical parameters and performing intelligent adaptive adjustments in combination with real-time processing status can effectively optimize cutting parameters, improve tool life, reduce processing defects, and ensure the optimal level of processing efficiency and accuracy.

[0091] The material processed by the blade refers to the entire processing object, while the crystal is the microstructural characteristic of the processing material. For example, metal materials are composed of metal crystals, which include single crystal metals (such as single crystal copper, single crystal copper, etc.) and polycrystalline metals (such as steel, aluminum alloy, etc.). "Crystal orientation" refers to the arrangement direction of the crystal structure inside the material. Crystals are formed by atoms, ions or molecules arranged in a specific periodic pattern. The density and bonding mode of atoms in different directions are different, resulting in significant differences in the physical and mechanical properties of the material (such as hardness, elastic modulus, thermal conductivity, etc.) in different directions. This phenomenon is called anisotropy.

[0092] The second acquisition module is used to obtain the real-time processing parameters of the blade, which include cutting force, cutting speed, cutting depth, tool temperature and vibration amplitude.

[0093] It should be noted that during the tool processing process, processing parameters such as cutting force, cutting speed, cutting depth, tool temperature and vibration amplitude have an important influence on processing quality and tool life. Reasonable collection and utilization of these parameters are crucial to optimizing the processing technology and improving processing accuracy.

[0094] Cutting force can be collected in real time through dynamic cutting force sensors, reflecting the mechanical interaction between the tool and the workpiece, directly affecting the tool wear and the surface quality of the workpiece; the cutting speed is calculated from the machine tool spindle speed and feed rate, which determines the material removal rate and tool thermal load during the cutting process; the cutting depth can be measured by a displacement sensor, affecting the size of the cutting force and the processing accuracy of the workpiece; the tool temperature can be collected by thermocouples or infrared thermometers, reflecting the heat accumulation during the cutting process, affecting the thermal expansion and wear rate of the tool; the vibration amplitude can be monitored by an acceleration sensor, reflecting the stability of the system during the cutting process. Excessive vibration may lead to tool chipping, increased surface roughness of the processed surface and increased equipment loss.

[0095] Therefore, collecting the above-mentioned processing parameters and performing intelligent adaptive adjustments based on the real-time processing status can effectively optimize the cutting path and tool load, improve tool life, reduce processing defects, and ensure the stability and efficiency of the processing process.

[0096] The third acquisition module is used to acquire the surface image of the processed material in real time within a unit time. The surface image of the processed material is acquired through a high-resolution scanning electron microscope.

[0097] The first processing module processes the surface image of the processed material within a unit time to obtain a crystal orientation matrix set.

[0098] The method for obtaining the crystal orientation matrix set includes:

[0099] S100: Divide the unit time into N time points, set the initial value of n to 1, and set the value range of n to 1 to N;

[0100] S101: Acquire a surface image of a processed material at the nth time point; divide the surface image of the processed material into M sub-regions, which are recorded as surface sub-images of the processed material;

[0101] S102: performing diffraction band detection processing on M sub-images of the processed material surface to obtain Kikuchi diffraction bands corresponding to the M sub-images of the processed material surface;

[0102] S103: obtaining crystal orientation matrices corresponding to M surface sub-images of the processed material based on the M Kikuchi diffraction bands;

[0103] S104: performing matrix numerical comparison on the M crystal orientation matrices to obtain the crystal orientation matrix of the surface image of the processed material at the nth time point;

[0104] S105: Let n=n+1. If n is less than or equal to N, continue to execute S101 to S104. If n is greater than N, obtain the crystal orientation matrix of the surface image of the processed material corresponding to N time points, and execute S106.

[0105] S106: Constructing the crystal orientation matrices of the processed material surface images corresponding to N time points into a crystal orientation matrix set.

[0106] The method for obtaining Kikuchi diffraction bands corresponding to M surface sub-images of a processed material includes:

[0107] S200: Let the initial value of m be 1, and the value range of m be 1 to M;

[0108] S201: Acquire the mth sub-image of the surface of the processed material; update the mth sub-image of the surface of the processed material into a sub-image of the surface of the processed material with two-dimensional coordinates through an image processing library;

[0109] S202: Record the number of pixels in the mth processed material surface sub-image as R; calculate the corresponding diffraction band gradient matrix for each of the R pixels;

[0110] S203: Inputting the physical parameters of the blade processing material and R diffraction band gradient matrices into a diffraction band gradient threshold setting model to obtain a diffraction band gradient threshold;

[0111] S204: constructing a Kikuchi diffraction band of the mth processed material surface sub-image based on R diffraction band gradient matrices and diffraction band gradient thresholds;

[0112] S205: Let m=m+1. If m is less than or equal to M, continue executing S201 to S204. If m is greater than M, obtain M Kikuchi diffraction bands corresponding to the surface sub-images of the processed material, and end the current process.

[0113] The calculation method of the diffraction zone gradient matrix includes:

[0114]

[0115] Among them, TDJZ r is the diffraction band gradient matrix corresponding to the r-th pixel point, TD r，x is the gradient matrix of the r-th pixel in the horizontal direction, TD r，y is the gradient matrix of the r-th pixel in the vertical direction, XSZ r is the pixel value of the r-th pixel, XSZ min is the minimum pixel value of the sub-image of the processed material surface where the r-th pixel point is located, XSZ max is the maximum pixel value of the sub-image of the processed material surface where the r-th pixel point is located, r≤R.

[0116] The training method of the diffraction zone gradient threshold setting model includes:

[0117] Preliminarily collecting a diffraction zone gradient threshold setting data set, the diffraction zone gradient threshold setting data set comprising K groups of diffraction zone gradient threshold setting data and diffraction zone gradient thresholds corresponding to the K groups of diffraction zone gradient threshold setting data, where K is a positive integer greater than 0, and the diffraction zone gradient threshold setting data comprising crystal type, material hardness, elastic modulus, fracture toughness, thermal conductivity, specific heat capacity, and R diffraction zone gradient matrices; dividing the diffraction zone gradient threshold setting data set into a training set and a validation set, wherein the training set is used to train a diffraction zone gradient threshold setting model, and the validation set is used to evaluate the generalization performance of the diffraction zone gradient threshold setting model;

[0118] During the training process of the diffraction zone gradient threshold setting model, minimizing the cross-entropy loss function is used as the optimization goal. The performance of the validation set is monitored using an early stopping strategy, and the model performance is optimized by continuously adjusting the network parameters. When the prediction accuracy on the validation set reaches the expected accuracy, the diffraction zone gradient threshold setting model is considered to have converged and training is stopped. The diffraction zone gradient threshold setting model is trained using a deep neural network based on a multilayer perceptron.

[0119] The diffraction band gradient threshold setting data is converted into a feature vector; the input layer of the diffraction band gradient threshold setting model receives the feature vector, and the nonlinear relationship in the data is extracted through the hidden layer. Finally, the output layer of the diffraction band gradient threshold setting model calculates the probability distribution of the diffraction band gradient threshold through the softmax activation function, and outputs the diffraction band gradient threshold corresponding to the maximum probability as the final prediction result.

[0120] The softmax activation function is:

[0121]

[0122] Among them, Softmax(XL num ) is the output probability corresponding to the num-th eigenvector, XL num is the num-th eigenvector, NUM is the total number of eigenvectors, and e is a constant.

[0123] It should be noted that the Kikuchi diffraction bands of single crystal materials are Figure 4 As shown, the Kikuchi diffraction bands of polycrystalline materials are as follows Figure 5As shown in the figure. The crystal type determines the internal structural characteristics of the material and affects the distribution pattern of the Kikuchi diffraction bands. The hardness and elastic modulus of the material jointly determine the degree of deformation of the material during processing, thereby affecting the changes in the surface microstructure. The fracture toughness determines whether the material is prone to microcracks under local stress conditions, thereby affecting the clarity of the diffraction bands. The thermal conductivity and specific heat capacity determine the changes in the temperature gradient during processing, which in turn affects the surface stress distribution and the range of the heat-affected zone of the material after processing, causing the contrast of the diffraction bands to change accordingly. Combined with the diffraction band gradient matrix, the changing characteristics of the Kikuchi diffraction bands in the surface image of the processed material can be reflected.

[0124] Therefore, the present invention constructs a data-driven machine learning model based on crystal type, material hardness, elastic modulus, fracture toughness, thermal conductivity, specific heat capacity and diffraction band gradient matrix to realize the dynamic setting of the diffraction band gradient threshold during the Kikuchi diffraction band detection process, thereby obtaining the optimal diffraction band gradient threshold of the Kikuchi diffraction band under different materials, realizing adaptive adjustment of the diffraction band gradient threshold, improving the accuracy and robustness of Kikuchi diffraction band detection, and thus optimizing subsequent crystal orientation analysis and material processing quality evaluation.

[0125] The method for constructing the Kikuchi diffraction band of the mth processed material surface sub-image based on R diffraction band gradient matrices and diffraction band gradient thresholds includes:

[0126] S300: Let the initial value of r be 1, and the value range of r be 1 to R;

[0127] S301: Obtain the rth diffraction zone gradient matrix, and perform diffraction zone gradient threshold determination on each element value in the matrix, record the elements whose element values ​​are greater than or equal to the diffraction zone gradient threshold as diffraction zone elements, and count the number of diffraction zone elements, which is recorded as the number of diffraction zone elements; record the elements whose element values ​​are less than the diffraction zone gradient threshold as non-diffraction zone elements, and count the number of non-diffraction zone elements, which is recorded as the number of non-diffraction zone elements;

[0128] S302: summing the number of diffraction zone elements and the number of non-diffraction zone elements to obtain the total number of elements; dividing the number of diffraction zone elements by the total number of elements to obtain the diffraction zone element ratio;

[0129] S303: If the diffraction zone element ratio is greater than or equal to a preset diffraction zone element ratio threshold, then mark the pixel corresponding to the rth diffraction zone gradient matrix as a diffraction zone pixel; if the diffraction zone element ratio is less than the preset diffraction zone element ratio threshold, then mark the pixel corresponding to the rth diffraction zone gradient matrix as a non-diffraction zone pixel;

[0130] For example, the diffraction zone element ratio threshold can be set to or

[0131] S304: Let r = r + 1. If r is less than or equal to R, continue executing S301 to S303. If r is greater than R, execute S305.

[0132] S305: Based on all diffraction band pixels, a pixel connection algorithm is used to connect the discrete diffraction band pixels into complete diffraction band lines to obtain the Kikuchi diffraction band of the mth processed material surface sub-image.

[0133] It should be noted that the identification of Kikuchi diffraction bands is a crucial step in intelligent tool processing. Kikuchi diffraction bands refer to high-intensity diffraction regions formed by Bragg scattering within a crystal during electron backscatter diffraction or transmission electron microscopy analysis. The distribution of Kikuchi diffraction bands is closely related to the crystal's orientation and is a direct reflection of the material's crystal orientation. The distribution of Kikuchi diffraction bands strictly corresponds to the crystal's orientation, so the material's crystal orientation can be determined by analyzing the Kikuchi diffraction bands.

[0134] The method for obtaining the crystal orientation matrix corresponding to the M surface sub-images of the processed material includes:

[0135] S400: Let the initial value of m be 1, and the value range of m be 1 to M;

[0136] S401: Obtaining the Kikuchi diffraction band of the mth processed material surface sub-image; selecting three independent diffraction band normal vectors from the Kikuchi diffraction band, and recording them as diffraction band normal vector 1, diffraction band normal vector 2, and diffraction band normal vector 3, respectively;

[0137] S402: constructing a diffraction zone normal vector matrix from the first diffraction zone normal vector, the second diffraction zone normal vector, and the third diffraction zone normal vector;

[0138] The diffraction band normal vector matrix is:

[0139]

[0140] Among them, FXLJZ is the diffraction zone normal vector matrix, (fxl 11 ,fxl 21 ,fxl 31 ) is the diffraction band normal vector, (fxl 12 ,fxl 22 ,fxl 32 ) is the diffraction band normal vector 2, (fxl 13 ,fxl 23 ,fxl 33 ) is the diffraction band normal vector three.

[0141] S403: Calculating a first diffraction direction angle, a second diffraction direction angle, and a third diffraction direction angle based on the diffraction zone normal vector matrix;

[0142] The calculation method of the diffraction direction angle 1, the diffraction direction angle 2 and the diffraction direction angle 3 includes:

[0143] θ1=cos -1 (fxl 33 );

[0144]

[0145] Among them, θ1 is the diffraction direction angle 1, θ2 is the diffraction direction angle 2, θ3 is the diffraction direction angle 3, cos -1 () is the arccosine function, tan -1 () is the inverse tangent function.

[0146] S404: constructing a diffraction direction cosine matrix 1 based on the diffraction direction angle 1, constructing a diffraction direction cosine matrix 2 based on the diffraction direction angle 2, and constructing a diffraction direction cosine matrix 3 based on the diffraction direction angle 3;

[0147] The method for obtaining the diffraction direction cosine matrix 1, the diffraction direction cosine matrix 2, and the diffraction direction cosine matrix 3 includes:

[0148]

[0149]

[0150] Among them, RJZ z (θ1) is the diffraction direction cosine matrix, RJZ x (θ2) is the diffraction direction cosine matrix 2, RJZ y (θ3) is the diffraction direction cosine matrix three.

[0151] S405: performing matrix multiplication on the diffraction direction cosine matrix 1, the diffraction direction cosine matrix 2, and the diffraction direction cosine matrix 3 to obtain a crystal orientation matrix corresponding to the mth processed material surface sub-image;

[0152] The method for obtaining the crystal orientation matrix corresponding to the mth processed material surface sub-image includes:

[0153] JTQ m =RJZ z (θ1)×RJZ x (θ2)×RJZ y (θ3);

[0154] Among them, JTQX mis the crystal orientation matrix corresponding to the mth processed material surface sub-image.

[0155] S406: Let m=m+1. If m is less than or equal to M, continue executing S401 to S405. If m is greater than M, obtain the crystal orientation matrices corresponding to the M sub-images of the processed material surface, and end the current process.

[0156] The method for obtaining the crystal orientation matrix of the surface image of the processed material at the nth time point includes:

[0157] S500: Let the initial value of m be 1, and the value range of m be 1 to M; pre-construct a crystal orientation matrix key-value pair set; the crystal orientation matrix key-value pair set includes a crystal orientation matrix key-value pair; the crystal orientation matrix key-value pair includes a key and a value, the key is the crystal orientation matrix, the key is initially empty, the value is the number corresponding to the crystal orientation matrix, and the initial value of the value is 0;

[0158] S501: Obtain the mth crystal orientation matrix; if the mth crystal orientation matrix has the same key as the crystal orientation matrix key-value pair in the crystal orientation matrix key-value pair set, then increase the value corresponding to the crystal orientation matrix key-value pair by one; if the mth crystal orientation matrix has different keys from the crystal orientation matrix key-value pair in the crystal orientation matrix key-value pair set, then create a new crystal orientation matrix key-value pair, use the mth crystal orientation matrix as the key of the new crystal orientation matrix key-value pair, increase the value of the new crystal orientation matrix key-value pair by one; and add the new crystal orientation matrix key-value pair to the crystal orientation matrix key-value pair set;

[0159] S502: Let m=m+1. If m is less than or equal to M, continue to execute S501; if m is greater than M, execute S503;

[0160] S503: Retrieve the crystal orientation matrix key-value pair with the maximum value from the crystal orientation matrix key-value pair set, use the key of the crystal orientation matrix key-value pair with the maximum value as the crystal orientation matrix of the surface image of the processed material at the nth time point, and end the current process.

[0161] The orientation prediction module is used to input the physical parameters and the crystal orientation matrix set into the crystal orientation prediction model to obtain the crystal orientation matrix per unit time in the future.

[0162] The training method of the crystal orientation prediction model includes:

[0163] Preliminarily collecting a crystal orientation prediction data set, the crystal orientation prediction data set comprising F groups of crystal orientation prediction data and crystal orientation matrices corresponding to the F groups of crystal orientation prediction data, where F is a positive integer greater than 0, and the crystal orientation prediction data comprises a set of physical parameters and a crystal orientation matrix; dividing the crystal orientation prediction data set into a training set and a validation set, wherein the training set is used to train a crystal orientation prediction model, and the validation set is used to evaluate the generalization performance of the crystal orientation prediction model;

[0164] During the crystal orientation prediction model training process, minimizing the cross-entropy loss function is used as the optimization goal. An early stopping strategy is used to monitor the performance of the validation set, and the network parameters are continuously adjusted to optimize the model performance. When the prediction accuracy on the validation set reaches the expected accuracy, the crystal orientation prediction model is considered to have converged and training is stopped. The crystal orientation prediction model is trained using a deep neural network based on a multilayer perceptron.

[0165] The crystal orientation prediction data is converted into feature vectors; the input layer of the crystal orientation prediction model receives the feature vectors, and the nonlinear relationship in the data is extracted through the hidden layer. Finally, the output layer of the crystal orientation prediction model calculates the probability distribution of the crystal orientation matrix through the softmax activation function, and outputs the crystal orientation matrix corresponding to the maximum probability as the final prediction result.

[0166] It's important to note that changes in crystal orientation typically evolve over time. As processing progresses, new crystal planes are constantly exposed. Time series modeling can capture the changing patterns of the historical crystal orientation matrix and, in turn, predict future crystal orientations. Specifically, the evolution of crystal orientation is time-dependent, meaning the crystal orientation matrix at a previous point in time determines the state of the crystal orientation at subsequent points in time.

[0167] Furthermore, physical parameters determine the evolutionary mechanisms of crystal orientation. For example, material hardness and elastic modulus influence deformation behavior, determining lattice rotation in stress-concentrated areas; fracture toughness determines the path of microcrack propagation, which in turn influences local crystal orientation; and thermal conductivity and specific heat capacity influence temperature distribution, regulating the effect of thermal stress on the lattice. These physical parameters, as inputs to machine learning models, can be used to establish physical constraints on crystal orientation changes, thereby improving prediction accuracy.

[0168] By comprehensively considering the time series characteristics of the crystal orientation matrix and the material property constraints of physical parameters, a mapping relationship between the change of crystal orientation over time is established. Then, given the current state and material properties, the crystal orientation matrix per unit time in the future is predicted, providing a theoretical basis and optimization strategy for precisely controlling the microstructural evolution of processed materials.

[0169] The intelligent optimization module performs intelligent adaptive adjustment of the blade's processing parameters based on physical parameters, processing parameters, crystal orientation matrix set and crystal orientation matrix of future unit time.

[0170] like Figure 3 As shown, the method for intelligently and adaptively adjusting the processing parameters of the blade includes:

[0171] Count the occurrence frequency of each crystal orientation matrix in the crystal orientation matrix set, select the crystal orientation matrix with the highest occurrence frequency, and record it as the crystal main orientation matrix;

[0172] The crystal orientation angle difference is calculated based on the crystal main orientation matrix and the crystal orientation matrix of the future unit time;

[0173] The method for obtaining the crystal orientation angle difference includes:

[0174]

[0175] Wherein, JCZ is the crystal orientation angle difference, cos -1 () is the arc cosine function, ZJZ is the main orientation matrix of the crystal, WLJZ is the crystal orientation matrix per unit time in the future, WLJZ T is the transposed matrix of the crystal orientation matrix per unit time in the future, ZJZ×WLJZ T The transposed matrix representing the crystal main orientation matrix and the crystal orientation matrix of the future unit time is multiplied to obtain a new matrix, which is recorded as the change matrix, Tr(ZJZ×WLJZ T ) represents the trace of the change matrix, which is the sum of the main diagonal elements of the change matrix. For example, Figure 6 This is a schematic diagram of a curve showing the change of the crystal orientation angle difference over time, where the horizontal axis is time and the vertical axis is the crystal orientation angle difference.

[0176] If the crystal orientation angle difference is greater than or equal to a preset crystal orientation angle difference threshold, it is considered that the crystal orientation has changed and intelligent adaptive adjustment is required; for example, the crystal orientation angle difference threshold can be set to 5°.

[0177] Obtaining crystal type from physical parameters;

[0178] If the crystal type is single crystal material, the processing parameters are intelligently and adaptively adjusted for the single crystal material;

[0179] If the crystal type is polycrystalline material, the processing parameters are intelligently and adaptively adjusted for the polycrystalline material.

[0180] Methods for intelligent adaptive adjustment of processing parameters for single crystal materials include:

[0181] Step 1: setting a single crystal orientation angle difference threshold value 1 and a single crystal orientation angle difference threshold value 2 for the single crystal material; the single crystal orientation angle difference threshold value 1 is smaller than the single crystal orientation angle difference threshold value 2;

[0182] Step 2: If the crystal orientation angle difference is less than the single crystal orientation angle difference threshold 1, there is no need to adjust the processing parameters of the single crystal material;

[0183] If the crystal orientation angle difference is greater than or equal to a single crystal orientation angle difference threshold value 1 and less than a single crystal orientation angle difference threshold value 2, inputting the crystal type, the crystal orientation angle difference, and the processing parameters into a blade processing parameter setting model to obtain target processing parameters, wherein the target processing parameters include a target cutting force, a target cutting speed, a target cutting depth, a target tool temperature, and a target vibration amplitude; and adjusting the blade processing parameters to the target processing parameters;

[0184] If the crystal orientation angle difference is greater than or equal to the single crystal orientation angle difference threshold value 2, the crystal plane of the currently processed single crystal material is not suitable for processing, and a crystal plane switching operation is performed to adjust to the crystal plane of the single crystal material adjacent to the crystal plane of the currently processed single crystal material;

[0185] Step 3: Repeat step 2 until the processing of the single crystal material is completed.

[0186] It should be noted that the crystal orientation of single-crystal materials is continuous and stable, meaning that the orientation of the same crystal plane is uniform throughout the material. Because different crystal planes of single-crystal materials have different physical properties (hardness, elastic modulus, coefficient of friction, etc.), different thresholds can be used to assess whether to continue processing or change planes.

[0187] Methods for intelligent adaptive adjustment of processing parameters for polycrystalline materials include:

[0188] Step 1: Set the polycrystalline orientation angle difference threshold for polycrystalline materials;

[0189] Step 2: If the crystal orientation angle difference is less than the polycrystalline orientation angle difference threshold, there is no need to adjust the processing parameters of the polycrystalline material;

[0190] If the crystal orientation angle difference is greater than or equal to the polycrystalline orientation angle difference threshold, the crystal type, the crystal orientation angle difference and the processing parameters are input into the blade processing parameter setting model to obtain the target processing parameters;

[0191] Step 3: Adjust the processing parameters of the blade to the target processing parameters;

[0192] Step 4: Repeat steps 2 to 3 until the processing of the polycrystalline material is completed.

[0193] It should be noted that polycrystalline materials are composed of a large number of randomly distributed grains with different orientations, and the internal crystal orientation of polycrystalline materials is highly discrete and random. During the machining process, the tool will continuously cut multiple grains with different orientations, causing the crystal orientation to change rapidly in a local area. Therefore, compared with single crystal materials, polycrystalline materials are not suitable for relying on the difference in crystal orientation angles to determine whether the surface needs to be changed. Instead, it is more suitable to adopt a method of dynamically adjusting the machining parameters to adapt to the influence of different grain orientations on cutting forces, cutting temperatures and tool wear, thereby optimizing machining stability and improving machining quality.

[0194] The training method of the blade processing parameter setting model includes:

[0195] Pre-constructing a blade processing parameter setting data set, the blade processing parameter setting data set including a group B of blade processing parameter setting data and target processing parameters corresponding to the group B of blade processing parameter setting data, where B is a positive integer greater than 0, and the blade processing parameter setting data including equipment operation characteristic data; dividing the blade processing parameter setting data set into a blade processing parameter setting data training set and a blade processing parameter setting data validation set, wherein the blade processing parameter setting data training set is used for parameter learning of a blade processing parameter setting model, and the blade processing parameter setting data validation set is used for real-time evaluation of the generalization ability of the blade processing parameter setting model;

[0196] During the training process of the blade processing parameter setting model, a deep neural network structure based on multi-layer perceptron is adopted to convert the blade processing parameter setting data into a feature vector as input, extract the nonlinear features in the data through the hidden layer, and finally use the softmax activation function in the output layer to generate the probability distribution of the target processing parameters, and output the target processing parameters corresponding to the maximum probability as the final prediction result; the training process aims to minimize the cross entropy loss function, and at the same time introduces an early stopping strategy to monitor the performance of the blade processing parameter setting data validation set. When the prediction accuracy on the blade processing parameter setting data validation set reaches the preset accuracy, the blade processing parameter setting model is considered to have converged and the training stops immediately.

[0197] An example of adjusting processing parameters for polycrystalline materials is as follows:

[0198] When processing WC-Co cemented carbide (polycrystalline material), due to the randomness of different grain orientations within the polycrystalline material, the cutting force in the local area suddenly increases to 150N, causing the cutting temperature to rise to 500°C, causing overheating and wear of the tool. At the same time, the vibration amplitude increases to 20μm, affecting the processing stability.

[0199] The processing parameters of the current blade are shown in Table 1;

[0200] Table 1 Processing parameters of current blades

[0201] cutting force 120N cutting speed 80m / min Cutting depth 0.2mm Tool temperature 450℃ Vibration amplitude 12μm

[0202] The processing parameters of the adjusted blade are shown in Table 2;

[0203] Table 2 Processing parameters of the adjusted blade

[0204] cutting force 120N cutting speed 70m / min (reduce heat accumulation) Cutting depth 0.15mm (reduce cutting load) Tool temperature 430℃(reduce tool wear) Vibration amplitude 10μm (to improve processing stability)

[0205] Example 2

[0206] See also Figure 2 As shown, this embodiment provides an intelligent self-adaptive method in the blade processing process, including:

[0207] Collect physical parameters of the blade processing material;

[0208] Get the real-time blade processing parameters;

[0209] Real-time acquisition of surface images of processed materials within a unit of time;

[0210] Processing the surface image of the processed material within a unit time to obtain a set of crystal orientation matrices;

[0211] Input the physical parameters and crystal orientation matrix set into the crystal orientation prediction model to obtain the crystal orientation matrix per unit time in the future;

[0212] Based on physical parameters, processing parameters, crystal orientation matrix set and crystal orientation matrix of future unit time, the processing parameters of the blade are intelligently and adaptively adjusted.

[0213] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

[0214] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. Intelligent adaptive method in blade processing, characterized by: include: Collect physical parameters of the blade processing material; Get the real-time blade processing parameters; Real-time acquisition of surface images of processed materials within a unit of time; Processing the surface image of the processed material within a unit time to obtain a set of crystal orientation matrices; The method for obtaining the crystal orientation matrix set includes: S100: Divide the unit time into N time points, set the initial value of n to 1, and set the value range of n to 1 to N; S101: Acquire a surface image of a processed material at the nth time point; divide the surface image of the processed material into M sub-regions, which are recorded as surface sub-images of the processed material; S102: performing diffraction band detection processing on M sub-images of the processed material surface to obtain Kikuchi diffraction bands corresponding to the M sub-images of the processed material surface; S103: obtaining crystal orientation matrices corresponding to M surface sub-images of the processed material based on the M Kikuchi diffraction bands; S104: performing matrix numerical comparison on the M crystal orientation matrices to obtain the crystal orientation matrix of the surface image of the processed material at the nth time point; S105: Let n=n+1. If n is less than or equal to N, continue to execute S101 to S104. If n is greater than N, obtain the crystal orientation matrix of the surface image of the processed material corresponding to N time points, and execute S106. S106: constructing the crystal orientation matrices of the processed material surface images corresponding to N time points into a crystal orientation matrix set; Input the physical parameters and crystal orientation matrix set into the crystal orientation prediction model to obtain the crystal orientation matrix per unit time in the future; Based on physical parameters, processing parameters, a crystal orientation matrix set, and a crystal orientation matrix for a future unit time, the processing parameters of the blade are intelligently and adaptively adjusted. The method for intelligently and adaptively adjusting the processing parameters of the blade includes: Count the occurrence frequency of each crystal orientation matrix in the crystal orientation matrix set, select the crystal orientation matrix with the highest occurrence frequency, and record it as the crystal main orientation matrix; The crystal orientation angle difference is calculated based on the crystal main orientation matrix and the crystal orientation matrix of the future unit time; If the crystal orientation angle difference is greater than or equal to the preset crystal orientation angle difference threshold, it is considered that the crystal orientation has changed and intelligent adaptive adjustment is required; Obtaining crystal type from physical parameters; If the crystal type is single crystal material, the processing parameters are intelligently and adaptively adjusted for the single crystal material; If the crystal type is polycrystalline material, the processing parameters are intelligently and adaptively adjusted for the polycrystalline material.

2. The intelligent self-adaptive method in the blade processing process according to claim 1, characterized in that: Methods for intelligent adaptive adjustment of processing parameters for single crystal materials include: Step 1: setting a single crystal orientation angle difference threshold value 1 and a single crystal orientation angle difference threshold value 2 for the single crystal material; the single crystal orientation angle difference threshold value 1 is smaller than the single crystal orientation angle difference threshold value 2; Step 2: If the crystal orientation angle difference is less than the single crystal orientation angle difference threshold 1, there is no need to adjust the processing parameters of the single crystal material; If the crystal orientation angle difference is greater than or equal to a single crystal orientation angle difference threshold value 1 and less than a single crystal orientation angle difference threshold value 2, inputting the crystal type, the crystal orientation angle difference, and the processing parameters into a blade processing parameter setting model to obtain target processing parameters, wherein the target processing parameters include a target cutting force, a target cutting speed, a target cutting depth, a target tool temperature, and a target vibration amplitude; and adjusting the blade processing parameters to the target processing parameters; If the crystal orientation angle difference is greater than or equal to the single crystal orientation angle difference threshold value 2, the crystal plane of the currently processed single crystal material is not suitable for processing, and a crystal plane switching operation is performed to adjust to the crystal plane of the single crystal material adjacent to the crystal plane of the currently processed single crystal material; Step 3: Repeat step 2 until the processing of the single crystal material is completed.

3. The intelligent self-adaptive method in the blade processing process according to claim 2, characterized in that: Methods for intelligent adaptive adjustment of processing parameters for polycrystalline materials include: Step 1: Set the polycrystalline orientation angle difference threshold for polycrystalline materials; Step 2: If the crystal orientation angle difference is less than the polycrystalline orientation angle difference threshold, there is no need to adjust the processing parameters of the polycrystalline material; If the crystal orientation angle difference is greater than or equal to the polycrystalline orientation angle difference threshold, the crystal type, the crystal orientation angle difference and the processing parameters are input into the blade processing parameter setting model to obtain the target processing parameters; Step 3: Adjust the processing parameters of the blade to the target processing parameters; Step 4: Repeat steps 2 to 3 until the processing of the polycrystalline material is completed.

4. The intelligent self-adaptive method in the blade processing process according to claim 1, characterized in that: The method for obtaining Kikuchi diffraction bands corresponding to M surface sub-images of a processed material includes: S200: Let the initial value of m be 1, and the value range of m be 1 to M; S201: Acquire the mth sub-image of the surface of the processed material; update the mth sub-image of the surface of the processed material into a sub-image of the surface of the processed material with two-dimensional coordinates through an image processing library; S202: Record the number of pixels in the mth processed material surface sub-image as R; calculate the corresponding diffraction band gradient matrix for each of the R pixels; S203: Inputting the physical parameters of the blade processing material and R diffraction band gradient matrices into a diffraction band gradient threshold setting model to obtain a diffraction band gradient threshold; S204: constructing a Kikuchi diffraction band of the mth processed material surface sub-image based on R diffraction band gradient matrices and diffraction band gradient thresholds; S205: Let m=m+1. If m is less than or equal to M, continue executing S201 to S204. If m is greater than M, obtain the Kikuchi diffraction bands corresponding to the M sub-images of the processed material surface, and end the current process.

5. The intelligent self-adaptive method in the blade processing process according to claim 4, characterized in that: The method for constructing the Kikuchi diffraction band of the mth processed material surface sub-image based on R diffraction band gradient matrices and diffraction band gradient thresholds includes: S300: Let the initial value of r be 1, and the value range of r be 1 to R; S301: Obtain the rth diffraction zone gradient matrix, and perform diffraction zone gradient threshold determination on each element value in the matrix, record the elements whose element values ​​are greater than or equal to the diffraction zone gradient threshold as diffraction zone elements, and count the number of diffraction zone elements, which is recorded as the number of diffraction zone elements; record the elements whose element values ​​are less than the diffraction zone gradient threshold as non-diffraction zone elements, and count the number of non-diffraction zone elements, which is recorded as the number of non-diffraction zone elements; S302: summing the number of diffraction zone elements and the number of non-diffraction zone elements to obtain the total number of elements; dividing the number of diffraction zone elements by the total number of elements to obtain the diffraction zone element ratio; S303: If the diffraction zone element ratio is greater than or equal to a preset diffraction zone element ratio threshold, then mark the pixel corresponding to the rth diffraction zone gradient matrix as a diffraction zone pixel; if the diffraction zone element ratio is less than the preset diffraction zone element ratio threshold, then mark the pixel corresponding to the rth diffraction zone gradient matrix as a non-diffraction zone pixel; S304: Let r = r + 1. If r is less than or equal to R, continue executing S301 to S303. If r is greater than R, execute S305. S305: Based on all diffraction band pixels, a pixel connection algorithm is used to connect the discrete diffraction band pixels into complete diffraction band lines to obtain the Kikuchi diffraction band of the mth processed material surface sub-image.

6. The intelligent self-adaptive method in the blade processing process according to claim 1, characterized in that: The method for obtaining the crystal orientation matrix corresponding to the M surface sub-images of the processed material includes: S400: Let the initial value of m be 1, and the value range of m be 1 to M; S401: Obtaining the Kikuchi diffraction band of the mth processed material surface sub-image; selecting three independent diffraction band normal vectors from the Kikuchi diffraction band, and recording them as diffraction band normal vector 1, diffraction band normal vector 2, and diffraction band normal vector 3, respectively; S402: constructing a diffraction zone normal vector matrix from the first diffraction zone normal vector, the second diffraction zone normal vector, and the third diffraction zone normal vector; S403: Calculating a first diffraction direction angle, a second diffraction direction angle, and a third diffraction direction angle based on the diffraction zone normal vector matrix; S404: constructing a diffraction direction cosine matrix 1 based on the diffraction direction angle 1, constructing a diffraction direction cosine matrix 2 based on the diffraction direction angle 2, and constructing a diffraction direction cosine matrix 3 based on the diffraction direction angle 3; S405: performing matrix multiplication on the diffraction direction cosine matrix 1, the diffraction direction cosine matrix 2, and the diffraction direction cosine matrix 3 to obtain a crystal orientation matrix corresponding to the mth processed material surface sub-image; S406: Let m=m+1. If m is less than or equal to M, continue executing S401 to S405. If m is greater than M, obtain the crystal orientation matrices corresponding to the M sub-images of the processed material surface, and end the current process.

7. The intelligent self-adaptive method in the blade processing process according to claim 1, characterized in that: The method for obtaining the crystal orientation matrix of the surface image of the processed material at the nth time point includes: S500: Let the initial value of m be 1, and the value range of m be 1 to M; pre-construct a crystal orientation matrix key-value pair set; the crystal orientation matrix key-value pair set includes a crystal orientation matrix key-value pair; the crystal orientation matrix key-value pair includes a key and a value, the key is the crystal orientation matrix, the key is initially empty, the value is the number corresponding to the crystal orientation matrix, and the initial value of the value is 0; S501: Obtain the mth crystal orientation matrix; if the mth crystal orientation matrix has the same key as the crystal orientation matrix key-value pair in the crystal orientation matrix key-value pair set, then increase the value corresponding to the crystal orientation matrix key-value pair by one; if the mth crystal orientation matrix has different keys from the crystal orientation matrix key-value pair in the crystal orientation matrix key-value pair set, then create a new crystal orientation matrix key-value pair, use the mth crystal orientation matrix as the key of the new crystal orientation matrix key-value pair, increase the value of the new crystal orientation matrix key-value pair by one; and add the new crystal orientation matrix key-value pair to the crystal orientation matrix key-value pair set; S502: Let m = m + 1. If m is less than or equal to M, continue to execute S501; if m is greater than M, execute S503; S503: Retrieve the crystal orientation matrix key-value pair with the maximum value from the crystal orientation matrix key-value pair set, use the key of the crystal orientation matrix key-value pair with the maximum value as the crystal orientation matrix of the surface image of the processed material at the nth time point, and end the current process.

8. An intelligent self-adaptive system for blade processing, implementing the intelligent self-adaptive method for blade processing according to any one of claims 1 to 7, characterized in that: include: The first acquisition module collects physical parameters of the blade processing material; The second acquisition module is used to obtain the real-time processing parameters of the blade; The third acquisition module is used to collect the surface image of the processed material in unit time in real time; The first processing module processes the surface image of the processed material within a unit time to obtain a crystal orientation matrix set; An orientation prediction module is used to input the physical parameters and the crystal orientation matrix set into the crystal orientation prediction model to obtain the crystal orientation matrix per unit time in the future; The intelligent optimization module performs intelligent adaptive adjustment of the blade's processing parameters based on physical parameters, processing parameters, crystal orientation matrix set and crystal orientation matrix of future unit time.

Images