Control method for improving single weight consistency of neodymium iron boron green body

Abstract

The invention discloses a control method for improving single weight consistency of neodymium-iron-boron green bodies, and relates to the technical field of neodymium-iron-boron magnetic material production, which comprises the following steps: before powder filling, according to the particle size distribution and flow characteristics of superfine neodymium-iron-boron powder, the airflow velocity is preset, so that the airflow is kept stable in the filling process, and the powder can be effectively disturbed; therefore, the filling uniformity is improved. Through real-time monitoring, intelligent analysis and dynamic regulation and control, the single weight consistency of the neodymium iron boron green body is improved, and the problem of flow velocity mutation in the powder filling process is solved. Uniform filling is ensured by presetting the airflow velocity, the powder flowing state is intelligently judged in combination with data collection, feature extraction and a deep learning model, and precise control is achieved. When it is detected that the powder flow speed is abnormally increased, the system adjusts the airflow intensity in a self-adaptive mode and temporarily reduces the feeding amount, and powder accumulation is prevented. The powder filling uniformity is optimized, the green body quality, the magnetic performance stability and the production efficiency are improved, and the rejection rate and material waste are reduced.

Description

Technical Field

[0001] The invention relates to the technical field of production of NdFeB magnetic materials, and in particular to a control method for improving the unit weight consistency of NdFeB green bodies. Background Art

[0002] Improving the unit weight consistency of NdFeB green billets means that during the production process, the weight of each green billet (i.e., unsintered NdFeB magnet blank) is kept as consistent as possible to reduce subsequent processing errors and product performance fluctuations caused by weight deviations. This goal is usually achieved by optimizing the powder metallurgy process, including precisely controlling the particle size distribution of the alloy powder, optimizing the molding process parameters (such as pressing pressure, filling density), improving the automatic feeding and batching system, and reducing human operation errors. Improving unit weight consistency can not only improve the performance stability of the final magnet product, but also reduce material waste, improve production efficiency, and optimize the consistency and yield of subsequent processing (such as sintering and machining).

[0003] The prior art has the following deficiencies: In the prior art, a trace amount of airflow is usually introduced during the powder filling process to slightly disturb the powder, and a preset airflow velocity is used to ensure the uniformity of the powder distribution, while avoiding powder scattering or unstable filling due to excessive airflow. However, during the powder filling process, ultrafine NdFeB powder may form a temporary stagnant area inside the mold due to the powder accumulation effect. When a certain critical point is reached, the powder may suddenly change from a slow flow state to a fast flow state, causing a large amount of powder to flow into certain areas of the mold in a short period of time, causing local overfilling, while other areas may still be underfilled. Due to uneven powder filling, the powder density distribution in the mold deviates. In the subsequent pressing process, the powder quality in some areas exceeds the standard, while the powder in other areas is insufficient, which ultimately leads to a significant deviation in the unit weight of the green body. This deviation not only affects the quality consistency of the green body, but may also lead to problems such as uneven pressing density, deformation during sintering, and instability of the final magnetic properties.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide a control method for improving the consistency of the unit weight of NdFeB green billets, improve the consistency of the unit weight of NdFeB green billets through real-time monitoring, intelligent analysis and dynamic regulation, and solve the problems of sudden flow rate changes, overfilling or underfilling during powder filling. Uniform filling is ensured by presetting the air flow rate, and the powder flow state is intelligently judged by combining data acquisition, feature extraction and deep learning models to achieve precise control. When it is detected that the powder flow rate is abnormally accelerated, the system adaptively adjusts the air flow intensity and temporarily reduces the feed amount to prevent powder accumulation. The present invention optimizes the uniformity of powder filling, improves the quality of green billets, magnetic property stability and production efficiency, and reduces the scrap rate and material waste to solve the problems in the above-mentioned background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a control method for improving the unit weight consistency of NdFeB green billets, comprising the following steps: Before powder filling, the air flow rate is pre-set according to the particle size distribution and flow characteristics of the ultrafine NdFeB powder, so that the air flow can remain stable during the filling process and effectively disturb the powder to improve the filling uniformity; When the powder starts to be filled into the mold, the filling process is monitored in real time, the filling data is acquired in real time, and the dynamic process of the powder from entering the mold to distribution and molding is fully recorded; After all the collected real-time data are unified and summarized, the acquired data are pre-processed to finally form a complete data set that can be analyzed; Through the feature extraction algorithm, the feature vector reflecting the change of powder flow rate is screened and extracted from the data set, and the extracted feature vector is comprehensively analyzed to quantify the stability of powder filling; The analyzed feature vector is input into a pre-trained deep learning model, which calculates and predicts the powder flow state in real time and outputs a judgment result to determine whether the powder flow rate in the current mold is stable. When the deep learning model recognizes that the powder flow rate in the current mold is accelerating, it dynamically reduces the local airflow intensity in the area where the flow rate is accelerated to suppress the entry of excessive powder; at the same time, it temporarily reduces the powder supply amount to reduce the instantaneous powder inflow and prevent local powder accumulation.

[0007] Preferably, during the powder filling process, after the collected real-time data are uniformly summarized, the data needs to be preprocessed to ensure its integrity, accuracy and analyzability, and finally form a high-quality data set. The specific steps are as follows: First, the data acquisition system obtains key data from multiple sensors in real time during the powder filling process, and synchronizes the data from different sources to ensure that the data corresponds correctly on the same timeline. Next, we enter the data cleaning phase to identify and remove outliers, remove noise signals, and complete missing data to improve data continuity and reliability. Then, the data is normalized and standardized, converting data of different units and scales into a unified standard range for subsequent analysis and modeling; Subsequently, the data is formatted and structured for storage, and the data from different sensors are stored in a database or data stream processing according to logical classification to ensure its accessibility and efficient call; Ultimately, a complete data set is generated for real-time monitoring, trend analysis, anomaly detection, and intelligent control optimization of powder filling status, ensuring the stability of the filling process, improving the consistency of green body quality, and providing data support for subsequent production optimization.

[0008] Preferably, a feature vector reflecting the change in powder flow rate is screened and extracted from a data set through a feature extraction algorithm, the extracted feature vector includes the rebound effect of the powder caused by compression during the filling process and the degree of discreteness of the powder particles during the filling process, the rebound effect of the powder caused by compression during the filling process and the degree of discreteness of the powder particles during the filling process are comprehensively analyzed under a detection window, and a powder compression rebound reference value and a particle discreteness reference value are generated respectively, and the stability of powder filling is quantified through the powder compression rebound reference value and the particle discreteness reference value.

[0009] Preferably, the specific steps of comprehensively analyzing the rebound effect of the powder caused by compression during the filling process under the detection window to generate the powder compression rebound reference value are as follows: During the powder filling process, the powder in the local area will be subjected to compression force, resulting in a reduction in the particle gap, an increase in local density, and a compressed state. In order to quantify the degree of powder compression, the powder compression effect factor is defined to measure the compression effect of the powder during the filling process. The calculation expression is as follows: , where is the powder compression effect factor, The loose packing height of the powder before filling into the mold, It is the final height of the powder in the mold after being compressed. is the local contact pressure inside the powder particle, is the ambient pressure inside the mold; After powder filling, the powder will rebound due to the stress release between particles, resulting in a local decrease in filling density and a sudden change in flow rate. In order to quantify the rebound phenomenon, the powder compression rebound reference value is calculated to measure the rebound strength of the powder caused by compression. The calculation expression is as follows: , where is the reference value of powder compression rebound, is the expansion recovery rate of the powder, It is the shear resistance factor of the powder, which describes the degree to which the friction and shearing between the powder particles inhibit rebound.

[0010] Preferably, the specific steps of comprehensively analyzing the discreteness of the powder particles during the filling process under the detection window to generate a reference value of the particle discreteness are as follows: During the powder filling process, the distribution state of the particles is analyzed. First, the spatial distribution characteristics of the powder particles are constructed to identify the arrangement of the particles inside the mold. The detection window is divided into multiple micro-element areas. The particle density changes in each micro-element area are detected by laser scanning technology. The density ratio of the micro-element to the adjacent micro-element is calculated to obtain the local discrete offset rate. The calculation expression is as follows: , where It is a microelement The local discrete offset rate, is the target microelement The particle density inside is the neighboring microelement The particle density, is the target microelement The neighboring infinitesimal set, is the number of neighboring microelements, is the maximum value of the density of neighboring microelements, is a small constant that prevents the denominator from being zero; Obtaining the local discrete offset rate of all micro-element areas Finally, the powder filling state in the entire detection window is integrated to generate a reference value of particle dispersion. The generation formula is as follows: , where is the particle dispersion reference value, is the total number of microelements in the detection window, is the target microelement The particle motion intensity weight, is a smoothing factor to avoid the denominator being too small.

[0011] Preferably, the analyzed powder compression rebound reference value and particle discreteness reference value are input into a pre-trained deep learning model, and the powder flow rate variation coefficient is generated by the deep learning model. The powder flow rate variation coefficient is used to intelligently evaluate whether the powder flow rate in the current mold is stable and within a normal range.

[0012] Preferably, the powder flow rate variation coefficient generated when the pre-trained deep learning model is used to intelligently predict whether the powder flow rate in the current mold is stable is compared and analyzed with a pre-set reference threshold value of the powder flow rate variation coefficient, and the powder flow rate in the current mold is divided into stable and stable. The division steps are as follows: If the powder flow rate variation coefficient is greater than a preset powder flow rate variation coefficient reference threshold, it indicates that the powder flow rate in the current mold is accelerating; if the powder flow rate variation coefficient is less than or equal to a preset powder flow rate variation coefficient reference threshold, it indicates that the powder flow rate in the current mold is normal.

[0013] Preferably, when the deep learning model recognizes that the powder flow rate in the current mold is accelerated, the local airflow intensity in the area where the flow rate is accelerated is dynamically reduced, and at the same time, the specific steps of temporarily reducing the powder feed amount are as follows: When the deep learning model detects the coefficient of variation of the powder flow rate When it is greater than the preset powder flow rate variation coefficient reference threshold, it means that the powder flow rate in the current mold is accelerating, which will cause local overfilling. The local airflow intensity of the corresponding area is dynamically reduced to inhibit the rapid entry of powder. The airflow intensity adjustment formula is as follows: , where is the new airflow intensity value after dynamic adjustment. is the initial local airflow intensity value before adjustment, is the reference threshold value of the powder flow rate variation coefficient, is the natural base, is the adjustment sensitivity factor; While dynamically reducing the airflow intensity in the local area, it is also necessary to make a short adjustment to the powder feeding amount, that is, when the risk of rapid changes in the powder flow rate is found, the powder feeding amount should be reduced in a timely manner. The formula for adjusting the feeding amount is as follows; , where It is the dynamically adjusted powder feed amount, which is used to control the amount of powder delivered into the mold in real time. It is the reference value of powder feeding under normal and stable operation. is the powder feed adjustment factor, Feed sensitivity index; When the deep learning model recognizes that the powder flow rate has returned to the normal range, it gradually restores the local airflow intensity to the initial set value, and synchronously adjusts the powder feed amount to return it to a stable feed state to ensure the uniformity and continuity of the powder filling process.

[0014] In the above technical solution, the technical effects and advantages provided by the present invention are: The present invention effectively improves the consistency of the single weight of NdFeB green billets through real-time monitoring, intelligent analysis and dynamic control, and solves the problems of sudden change in flow rate, excessive or insufficient local filling caused by powder accumulation effect during powder filling. By presetting a suitable airflow velocity, while ensuring uniform filling of powder, powder scattering and filling instability are reduced; using real-time data acquisition and preprocessing technology, the dynamics of powder filling are fully recorded to build a high-quality data set for subsequent intelligent analysis; using feature extraction algorithms to screen and quantify the changes in powder flow rate, combined with deep learning models to intelligently judge the powder filling state, to ensure the stability of powder flow rate; when the abnormal acceleration of powder flow rate is detected, the system adaptively adjusts the airflow disturbance intensity, and temporarily reduces the powder feed amount, accurately controls the powder filling process, and avoids local powder accumulation and insufficient filling. Through intelligent and dynamic precise control, the present invention significantly improves the consistency of green billet quality, reduces the density deviation in the subsequent pressing and sintering process, thereby improving the dimensional accuracy and magnetic performance stability of NdFeB magnets, while reducing the scrap rate and material waste in the production process, and improving production efficiency and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0016] Figure 1 The present invention is a method flow chart of a control method for improving the unit weight consistency of NdFeB green bodies. DETAILED DESCRIPTION

[0017] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0018] The present invention provides Figure 1 The control method for improving the unit weight consistency of NdFeB green body shown in the figure comprises the following steps: Before powder filling, the air flow rate is pre-set according to the particle size distribution and flow characteristics of the ultrafine NdFeB powder, so that the air flow can remain stable during the filling process and effectively disturb the powder to improve the filling uniformity; Before powder filling, the airflow velocity is pre-set according to the particle size distribution and flow characteristics of the ultrafine NdFeB powder. Before filling begins, the appropriate airflow parameters (such as speed, direction, and pressure) are selected by analyzing the particle size, particle morphology, surface characteristics, fluidity, and electrostatic effect of the powder to optimize the filling process. Its function is to ensure that the powder maintains a stable flow during the filling process and is sufficiently disturbed to improve the filling uniformity. Stable airflow can prevent powder scattering or unstable filling, while appropriate disturbance can destroy the electrostatic adsorption and cohesion between powder particles, prevent powder from forming accumulation or bridging, and improve the uniformity of powder density in the filling area. In addition, reasonable airflow velocity setting can also reduce the local powder flow velocity mutation phenomenon, reduce the local overfilling or underfilling caused by powder accumulation collapse during the filling process, thereby ensuring the consistency of the green unit weight and improving the dimensional accuracy and magnetic performance stability of the final product.

[0019] Use a small amount of airflow to scatter or vibrate the powder, thereby destroying the cohesive force and electrostatic effect between the powders and helping the powders to form a uniform distribution state inside the mold. This preset airflow is usually not too large to avoid powder scattering or airflow turbulence inside the mold, but it cannot be too small, otherwise it will be difficult to overcome the adhesion or agglomeration problem of ultrafine powders.

[0020] When the powder starts to be filled into the mold, the filling process is monitored in real time, the filling data is acquired in real time, and the dynamic process of the powder from entering the mold to distribution and molding is fully recorded; During the powder filling process, the filling process is monitored in real time, that is, the key parameters such as the flow state, filling rate, and distribution uniformity of the powder are continuously collected through high-precision sensors (such as optical monitoring, laser ranging, electrostatic sensors, ultrasonic density scanning, image acquisition devices, etc.), and the dynamic data of the powder after entering the mold is obtained in real time. The role of this process is to comprehensively record the entire process from the powder entering the mold to the final filling, ensure the traceability of the production process, and provide accurate data support for subsequent intelligent regulation. Through this monitoring mechanism, it is possible to detect in real time whether the powder filling is uniform, whether there is a problem of local accumulation or insufficient filling, and when the powder filling state is abnormal (such as sudden change in flow rate, accumulation collapse, etc.), the filling parameters can be quickly adjusted, such as dynamically adjusting the airflow disturbance and feeding rate, so as to improve the consistency and stability of the filling, and ultimately ensure the quality uniformity and magnetic stability of the green body.

[0021] After all the collected real-time data are unified and summarized, the acquired data are pre-processed to finally form a complete data set that can be analyzed; During the powder filling process, after the collected real-time data is unified and summarized, the data needs to be pre-processed to ensure its integrity, accuracy and analyzability, and finally form a high-quality data set. The specific steps are as follows: First, the data acquisition system acquires key data in the powder filling process, such as powder flow rate, filling density, local distribution state, etc., from multiple sensors (such as optical cameras, laser rangefinders, electrostatic sensors, ultrasonic density scanning, etc.) in real time, and synchronizes the data from different sources to ensure that the data corresponds correctly on the same time axis. Next, enter the data cleaning stage to identify and remove outliers, remove noise signals, and fill in missing data (such as interpolation or mean filling) to improve the continuity and reliability of the data. Then, the data is normalized and standardized, and data of different units and scales are converted to a unified standard range for subsequent analysis and modeling. Subsequently, the data is formatted and structured for storage, and the data of different sensors are stored in a database or data stream processing according to logical classification (such as time sequence, spatial distribution, process batch, etc.) to ensure its accessibility and efficient call. Finally, the system generates a complete data set for real-time monitoring, trend analysis, anomaly detection, and intelligent control optimization of powder filling status, ensuring the stability of the filling process, improving the consistency of green body quality, and providing data support for subsequent production optimization.

[0022] Through the feature extraction algorithm, the feature vector reflecting the change of powder flow rate is screened and extracted from the data set, and the extracted feature vector is comprehensively analyzed to quantify the stability of powder filling; Through the feature extraction algorithm, the characteristic vector reflecting the change of powder flow rate is screened and extracted from the data set. The extracted characteristic vector includes the rebound effect caused by compression of the powder during the filling process and the discrete degree of the powder particles during the filling process. The rebound effect caused by compression of the powder during the filling process and the discrete degree of the powder particles during the filling process are comprehensively analyzed under the detection window to generate the powder compression rebound reference value and the particle discreteness reference value respectively. The powder filling stability is quantified by the powder compression rebound reference value and the particle discreteness reference value.

[0023] The increased rebound caused by compression during the filling process indicates that the powder may suddenly develop from a slow flow to a fast flow trend. The fundamental reason lies in the stress release between powder particles and the instantaneous adjustment of the stacking structure. During the filling process, the powder is usually slightly compressed by the mold wall or external airflow. At this time, the gaps between the particles are reduced and the local density increases. However, since ultrafine powders have high cohesion and elasticity, when the external force decreases or the powder reaches a critical stacking state, the elastic potential energy inside the powder is suddenly released, resulting in the breaking of the close arrangement between the particles, causing the powder as a whole to rebound quickly, which in turn causes the instantaneous loosening and accelerated flow of the powder in the local area. This phenomenon is similar to the rebound effect of elastic materials. When the powder filling density is too high and there is a lack of appropriate flow buffer, the powder in the local area may suddenly release stress, causing the particles to accelerate to diffuse to the low-density area, forming a high flow state in a short time. In addition, during the rebound process, if the airflow disturbance or external force intervention on the powder is small, the inertial effect between the particles will further amplify the sudden change in flow rate, causing sudden flow instability in the filling process. Therefore, the increased rebound of powder after compression is often a precursor signal that the powder is developing from slow flow to fast flow. In production control, it is necessary to monitor and dynamically adjust the filling parameters in real time to prevent the occurrence of local uneven filling or excessive accumulation problems.

[0024] The specific steps for comprehensively analyzing the rebound effect of powder caused by compression during the filling process under the detection window to generate the powder compression rebound reference value are as follows: During the powder filling process, the powder in the local area will be subjected to compression force, resulting in a reduction in the gap between particles, an increase in local density, and a compressed state. In order to quantify the degree of compression of the powder, the powder compression effect factor is defined to measure the compression effect of the powder during the filling process. The powder compression effect factor is based on the ratio of the initial filling height of the powder to the height after compression, as well as the microscopic pressure changes between the particles inside the powder. The calculation expression is as follows: , where is the powder compression effect factor, It is the loose stacking height of the powder before filling into the mold, reflecting the natural state of the powder before filling. It is the final height of the powder in the mold after being compressed, indicating the degree to which the powder is compacted. It is the local contact pressure inside the powder particles, which is usually determined by the particle distribution, particle shape and external compression force of the powder. is the ambient pressure inside the mold, that is, the external pressure state of the powder during the filling process; This step measures the overall compression of the powder. If the height of the powder changes greatly, it means that it has been significantly compressed. At the same time, the stress effect between particles is corrected to ensure that the microscopic stress changes inside the powder are taken into account. When the powder compression effect factor is large, it means that the powder has been strongly compressed during the filling process, which may cause a large rebound effect, thus affecting the stability of the flow rate.

[0025] After powder filling, the powder will rebound due to the stress release between particles, resulting in a local decrease in filling density and a sudden change in flow rate. In order to quantify the rebound phenomenon, the powder compression rebound reference value is calculated to measure the rebound strength of the powder caused by compression. The calculation expression is as follows: , where is the reference value of powder compression rebound, It is the expansion recovery rate of the powder, which indicates the degree of rebound of the powder after filling. It is the shear resistance factor of the powder, which describes the degree to which the friction and shearing between the powder particles inhibit rebound.

[0026] when When it is higher, it means that the powder rebounds strongly after being compressed, causing the powder in the local area to loosen and flow faster, which may cause a sudden change in filling rate or local uneven filling. This indicates that the powder rebound effect is weak, the filling state is stable, and no sudden flow rate changes will occur. It can be used as a key parameter to predict sudden changes in powder flow rate and can be used in intelligent filling control systems to adjust air flow disturbances or feed rates in advance to ensure the stability and consistency of the filling process.

[0027] The larger the powder compression-rebound reference value generated by comprehensive analysis of the rebound effect caused by compression of the powder during the filling process under the detection window, the greater the powder may suddenly develop from a slow flow to a fast flow trend. Conversely, it indicates that the powder flow trend is relatively stable and there will be no sudden acceleration. The fundamental mechanism of this phenomenon lies in the change in flow state caused by the compression, deformation and rebound release of the powder particles during the filling process. When the powder is filled into the mold, the powder in the local area is affected by gravity, the force of the mold wall or the airflow disturbance, which will form a certain degree of compression, resulting in a reduction in the gap between the particles and an increase in density. However, during the filling process, as the external force decreases or the particles accumulate to a certain extent, the powder may rebound, that is, the stress stored in the compressed state is suddenly released, causing a sudden change in the arrangement structure of the particles inside the powder, resulting in rapid deagglomeration of the local powder and accelerated flow. When the powder compression rebound reference value is high, it means that the powder is greatly affected by compression and the released rebound energy is strong. At this time, the flow state may change from slow filling to fast flow, and may even cause instantaneous accumulation collapse or uneven filling of the powder. On the contrary, when the powder compression rebound reference value is low, it indicates that the potential energy stored in the powder compression process is small, the structural adjustment between particles is relatively smooth, the filling state is stable, and the powder will not undergo sudden acceleration.

[0028] Excessive dispersion of powder particles during the filling process usually indicates that the powder may suddenly develop from a slow flow to a fast flow trend. The fundamental reason is the decrease in cohesion between powder particles and the sudden change in particle distribution state. Under normal filling conditions, powder particles rely on van der Waals forces, electrostatic forces or mechanical interlocking between particles to maintain a relatively stable flow state. However, when these interactions are weakened or external disturbances (such as airflow enhancement, mold wall slip, vibration impact, etc.) act on the powder, the particles may enter a discrete state, resulting in a sudden increase in fluidity in local areas, causing the powder to flow into the mold uncontrollably and accelerate. Especially in a high filling density environment, the arrangement of powder particles is limited. When local particles break through the critical density or are suddenly dispersed by external forces, the powder will lose its stable filling mode and instantly change from a slow accumulation state to a high-speed filling state, and may even cause local powder collapse, resulting in uneven filling. In addition, over-discrete powder particles are more likely to form fast flow channels under the action of aerodynamics, accelerating the movement of other particles, making the overall powder filling speed exceed expectations. Therefore, excessive dispersion of powder particles is a key signal of a sudden change in powder flow from slow flow to fast flow, which requires real-time monitoring and dynamic control to prevent uneven filling or local overfilling.

[0029] The specific steps for comprehensively analyzing the dispersion degree of powder particles during the filling process under the detection window to generate a reference value for particle dispersion are as follows: During the powder filling process, the distribution state of the particles is analyzed. First, the spatial distribution characteristics of the powder particles are constructed to identify the arrangement of the particles inside the mold. The detection window is divided into multiple micro-element areas. The particle density changes in each micro-element area are detected by laser scanning technology. The density ratio of the micro-element to the adjacent micro-element is calculated to obtain the local discrete offset rate. The calculation expression is as follows: , where It is a microelement The local discrete deviation rate of is the target microelement The particle density refers to the number of particles per unit volume. is the neighboring microelement The particle density, is the target microelement The neighboring infinitesimal set, is the number of neighboring microelements, is the maximum value of the density of neighboring microelements, is a small constant that prevents the denominator from being zero; This step is used to quantify the local density variation of powder particles in space. A higher value indicates that the particles in this area are arranged more discretely and the gaps between particles are larger, which means that the powder filling may enter a fast flow trend. It is low, indicating that the powder particles are evenly distributed in the micro-element area and the flow trend is relatively stable.

[0030] Obtaining the local discrete offset rate of all micro-element areas Finally, the powder filling state in the entire detection window is integrated to generate a reference value of particle dispersion. The generation formula is as follows: , where is the particle dispersion reference value, is the total number of microelements in the detection window, is the target microelement The particle motion intensity weight represents the dynamic change degree of particles in the micro-element area. is a smoothing factor to avoid the denominator being too small.

[0031] This step is used to calculate the overall particle dispersion during the entire filling process, where Represents the motion state of the particles, such as the velocity gradient or shear stress of the powder. This parameter ensures that higher weights are given to areas of high fluidity, making It not only reflects the degree of spatial distribution dispersion, but also reflects the powder flow state. If the powder particle size is higher, it means that the arrangement of powder particles tends to be loose, the fluidity is enhanced, and the filling rate may suddenly change; if A lower value indicates that the powder is evenly filled, the flow rate is stable, and sudden flow changes are not likely to occur.

[0032] The larger the particle discreteness reference value generated by comprehensive analysis of the discreteness of powder particles during the filling process under the detection window, the weaker the interaction force between powder particles (such as van der Waals force, electrostatic force or mechanical locking), and the particles tend to move more freely, making them more susceptible to external factors (such as airflow disturbance, gravity, vibration or shear force) and causing sudden increases in flow rate. When the particle discreteness reference value reaches a certain threshold, the powder may quickly change from a slow accumulation or restricted flow state to a high-speed flow state, resulting in a sudden increase in local filling rate, and may even cause uneven filling or local powder collapse. On the contrary, if the particle discreteness reference value is small, it means that the powder particles still maintain a high cohesion and stability, there is still a strong binding force between the particles, the flow rate is relatively stable, and it will not easily enter a rapid flow trend.

[0033] The analyzed feature vector is input into a pre-trained deep learning model, which calculates and predicts the powder flow state in real time and outputs a judgment result to determine whether the powder flow rate in the current mold is stable. The analyzed powder compression rebound reference value and particle discreteness reference value are input into the pre-trained deep learning model, and the powder flow rate variation coefficient is generated by the deep learning model. The powder flow rate variation coefficient is used to intelligently evaluate whether the powder flow rate in the current mold is stable and within the normal range.

[0034] A pre-trained deep learning model refers to a deep learning model that has been trained based on a large amount of historical data and has generalization capabilities before the powder filling system is deployed. During the offline training phase, the model uses a large amount of data from the powder filling process, such as powder compression rebound reference value, particle discreteness reference value, flow rate change trend, stacking damage index, flow stability index and other features, combined with supervised learning or unsupervised learning methods to train a model that can predict changes in powder flow rate. During the training process, long short-term memory networks (LSTM), convolutional neural networks (CNN), autoencoders (Autoencoder) or hybrid models (such as CNN-LSTM) are usually used to learn the time series change pattern of powder flow rate and construct a mathematical relationship that can accurately predict changes in powder flow rate. After multiple rounds of iterative optimization, the model can identify powder flow patterns under different filling conditions, and after deployment, it can be used for real-time reasoning to intelligently determine whether the powder flow rate is stable.

[0035] During the online inference phase, the pre-trained deep learning model receives real-time input data, such as the reference value of powder compression rebound and the reference value of particle discreteness, and automatically calculates the powder flow rate variation coefficient. This coefficient reflects the stability of the powder flow rate in the current mold and whether it is within the normal range. When the powder flow rate variation coefficient exceeds the set threshold, the system triggers an intelligent control mechanism, such as reducing the local airflow intensity and reducing the instantaneous feed amount to ensure the uniformity of powder filling. Since the model has learned a large amount of historical filling data during the training phase, it can adapt to the powder flow characteristics of different batches, different particle sizes, and different environmental conditions to achieve accurate prediction and intelligent adjustment. This pre-trained deep learning model can significantly improve the stability of the powder filling process, reduce the problem of local accumulation or insufficient filling, thereby ensuring the consistency of the green body weight and improving the final performance stability of the NdFeB magnet.

[0036] The deep learning model is not limited here and can achieve the reference value of powder compression rebound and particle dispersion reference value Comprehensive analysis to generate coefficient of variation of powder flow rate The machine learning model can be used. In order to realize the technical solution of the present invention, the present invention provides a specific implementation method; Coefficient of variation of powder flow rate The generation formula is as follows: , where and They are the reference values ​​of powder compression and rebound. and particle dispersion reference value The preset scaling factor of and Both are greater than 0.

[0037] Preset scale factor and As a weight parameter, it is used to measure the reference value of powder compression rebound and particle dispersion reference value Coefficient of variation of powder flow rate These coefficients are usually preset or optimized through experiments and data training to ensure that the calculated Can accurately reflect the changing trend of powder flow rate.

[0038] In practical applications, the role of the preset proportionality coefficient is to adjust the contribution of different parameters to match the characteristics of different types of powders. For example, the compression rebound effect of some powders has a greater impact on the flow rate change. The value may be larger, and if the particle dispersion has a more significant effect on the powder filling stability, then In addition, these coefficients can also be optimized through deep learning models or regression analysis to dynamically adjust them under different working conditions to improve The accuracy of the calculation is ultimately used to intelligently control the powder filling process to ensure the stability of the green body quality.

[0039] It can be seen from the powder flow rate variation coefficient that the larger the powder compression rebound reference value generated after comprehensive analysis of the rebound effect caused by compression of the powder during the filling process under the detection window, and the larger the particle discreteness reference value generated after comprehensive analysis of the discreteness of the powder particles during the filling process under the detection window, the larger the powder flow rate variation coefficient generated when the pre-trained deep learning model is used to intelligently predict whether the powder flow rate in the current mold is stable, indicating that the probability of accelerating the powder flow rate of the current mold is greater, and vice versa, the probability of accelerating the powder flow rate of the current mold is smaller.

[0040] The powder flow rate variation coefficient generated by the pre-trained deep learning model when intelligently predicting whether the powder flow rate in the current mold is stable is compared and analyzed with the pre-set reference threshold of the powder flow rate variation coefficient, and the powder flow rate in the current mold is divided into stable and stable. The division steps are as follows: If the powder flow rate variation coefficient is greater than a preset powder flow rate variation coefficient reference threshold, it indicates that the powder flow rate in the current mold is accelerating; if the powder flow rate variation coefficient is less than or equal to a preset powder flow rate variation coefficient reference threshold, it indicates that the powder flow rate in the current mold is normal.

[0041] When the deep learning model recognizes that the powder flow rate in the current mold is accelerating, it dynamically reduces the local airflow intensity in the area where the flow rate is accelerating to suppress the entry of excessive powder; at the same time, it temporarily reduces the powder feed amount to reduce the instantaneous powder inflow and prevent local powder accumulation; When the deep learning model recognizes that the powder flow rate in the current mold is accelerating, the system takes two measures: dynamically reducing the local airflow intensity in the area where the flow rate is accelerated and temporarily reducing the powder feed amount. Its core function is to accurately control the powder filling rate and avoid local overfilling, thereby ensuring filling uniformity and improving the quality consistency of the green body.

[0042] During the powder filling process, due to factors such as powder accumulation effect, static electricity release, and air flow disturbance changes, the powder flow rate may suddenly increase, causing powder to rush into certain areas in a short period of time, resulting in local overfilling. If not intervened in time, it will cause uneven powder density inside the mold, different local powder compaction levels, and may even affect the subsequent pressing and sintering processes.

[0043] First, the role of dynamically reducing the local airflow intensity is to reduce the flow dynamics of the powder in that area, so that the powder slowly settles, rather than suddenly filling to the bottom of the mold due to excessive airflow. This method can effectively balance the powder filling rate, preventing excessive accumulation of powder in some areas and insufficient filling in other areas. At the same time, the locality of airflow adjustment ensures that other areas of the mold still maintain a suitable powder flow state to avoid affecting the overall filling efficiency.

[0044] Secondly, the effect of temporarily reducing the powder feed rate is to reduce the amount of powder entering the mold from the source, further suppressing the phenomenon of sudden increase in instantaneous powder flow. When the powder flow rate is accelerated, if the original feed rate is still maintained, it may cause excessive filling of powder or even overflow of the mold, making the filling control ineffective. A temporary reduction in the feed rate can provide a self-regulating time window for the powder flow state, allowing it to return to a stable state in a shorter time. Afterwards, the feed rate can be gradually restored to avoid affecting the overall filling efficiency.

[0045] In addition, the intelligent control of this step improves the adaptive ability of powder filling, avoiding problems such as uneven filling and powder waste caused by delayed manual intervention. By combining the real-time monitoring and prediction of the deep learning model, this method can adjust the powder filling rate at an early stage of sudden change, reduce the occurrence of abnormal situations, make the unit weight of the green body more consistent, ensure the stability of the subsequent processing technology, and improve the quality and yield of the final product.

[0046] When the deep learning model recognizes that the powder flow rate in the current mold is accelerating, the local airflow intensity in the area where the flow rate is accelerating is dynamically reduced. At the same time, the specific steps for temporarily reducing the powder feed amount are as follows: When the deep learning model detects the coefficient of variation of the powder flow rate When it is greater than the preset powder flow rate variation coefficient reference threshold, it means that the powder flow rate in the current mold is accelerating, which will cause local overfilling. The local airflow intensity of the corresponding area is dynamically reduced to inhibit the rapid entry of powder. The airflow intensity adjustment formula is as follows: , where It is the new airflow intensity value after dynamic adjustment, which is used to adjust the local airflow intensity in real time to accurately control the powder flow rate. It is the initial local airflow intensity value before adjustment, that is, the preset stable working airflow intensity under normal circumstances, which is used to ensure that the powder flow is basically stable and prevent initial accumulation. is the reference threshold value of the powder flow rate variation coefficient, is the natural base, It is the adjustment sensitivity factor, which is used to adjust the airflow adjustment amplitude; By dynamically reducing the local airflow intensity in the area where the flow rate is accelerated, the risk of a large amount of powder rushing into the mold instantly due to a sudden change in flow rate is reduced, thereby suppressing overfilling, ensuring that the powder enters the mold evenly, and preventing local accumulation or uneven density. At the same time, this step uses a nonlinear airflow control mechanism to adaptively adjust the airflow intensity according to the degree of change in the powder flow rate, so that when the powder flow rate changes slightly, the airflow adjustment is gentle, and when the powder flow rate changes drastically, the airflow disturbance can be quickly reduced, achieving efficient and accurate intelligent control, and maintaining the stability and consistency of the filling process.

[0047] While dynamically reducing the airflow intensity in the local area, it is also necessary to make a short adjustment to the powder feeding amount, that is, when the risk of rapid changes in the powder flow rate is found, the powder feeding amount should be reduced in a timely manner. The formula for adjusting the feeding amount is as follows; , where It is the dynamically adjusted powder feed amount, which is used to control the amount of powder delivered into the mold in real time. It is the reference value of powder feeding under normal and stable operation. It is the powder feed adjustment factor, which is used to determine the magnitude of the reduction in feed amount. Feed sensitivity index is used to adjust the nonlinearity of feed control, so that the reduction of feed will show an exponential response with the change of powder flow rate, thus enhancing the control accuracy. By temporarily reducing the powder feed rate, the instantaneous rate of powder entering the mold is reduced, and the dynamic changes of powder filling are controlled from the source to prevent local powder accumulation or overfilling. This strategy can not only respond quickly to sudden changes in powder flow rate and reduce the impact effect of instantaneous feed rate, but also combine with airflow control to achieve dual precise control of powder flow rate and feed rate, thereby improving the uniformity of powder filling and the consistency of green unit weight.

[0048] When the deep learning model recognizes that the powder flow rate returns to the normal range (i.e., the powder flow rate variation coefficient ), gradually restore the local airflow intensity to the initial set value, and adjust the powder feed amount synchronously to return it to a stable feeding state to ensure the uniformity and continuity of the powder filling process.

[0049] The present invention effectively improves the consistency of the single weight of NdFeB green billets through real-time monitoring, intelligent analysis and dynamic control, and solves the problems of sudden change in flow rate, excessive or insufficient local filling caused by powder accumulation effect during powder filling. By presetting a suitable airflow velocity, while ensuring uniform filling of powder, powder scattering and filling instability are reduced; using real-time data acquisition and preprocessing technology, the dynamics of powder filling are fully recorded to build a high-quality data set for subsequent intelligent analysis; using feature extraction algorithms to screen and quantify the changes in powder flow rate, combined with deep learning models to intelligently judge the powder filling state, to ensure the stability of powder flow rate; when the abnormal acceleration of powder flow rate is detected, the system adaptively adjusts the airflow disturbance intensity, and temporarily reduces the powder feed amount, accurately controls the powder filling process, and avoids local powder accumulation and insufficient filling. Through intelligent and dynamic precise control, the present invention significantly improves the consistency of green billet quality, reduces the density deviation in the subsequent pressing and sintering process, thereby improving the dimensional accuracy and magnetic performance stability of NdFeB magnets, while reducing the scrap rate and material waste in the production process, and improving production efficiency and product quality.

[0050] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0051] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0052] It should be noted that, in this article, if there are relational terms such as first and second, etc., they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0053] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0054] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or 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.

[0055] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0056] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0057] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0058] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0059] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A control method for improving the unit weight consistency of NdFeB green billets, characterized in that: The following steps are involved: Before powder filling, the air flow rate is pre-set according to the particle size distribution and flow characteristics of the ultrafine NdFeB powder, so that the air flow can remain stable during the filling process and effectively disturb the powder to improve the filling uniformity; When the powder starts to be filled into the mold, the filling process is monitored in real time, the filling data is acquired in real time, and the dynamic process of the powder from entering the mold to distribution and molding is fully recorded; After all the collected real-time data are unified and summarized, the acquired data are pre-processed to finally form a complete data set that can be analyzed; Through the feature extraction algorithm, the feature vector reflecting the change of powder flow rate is screened and extracted from the data set, and the extracted feature vector is comprehensively analyzed to quantify the stability of powder filling; The analyzed feature vector is input into a pre-trained deep learning model, which calculates and predicts the powder flow state in real time and outputs a judgment result to determine whether the powder flow rate in the current mold is stable. When the deep learning model recognizes that the powder flow rate in the current mold is accelerating, it dynamically reduces the local airflow intensity in the area where the flow rate is accelerated to suppress the entry of excessive powder; at the same time, it temporarily reduces the powder supply amount to reduce the instantaneous powder inflow and prevent local powder accumulation.

2. The control method for improving the unit weight consistency of NdFeB green billets according to claim 1, characterized in that: During the powder filling process, after the collected real-time data is unified and summarized, the data needs to be pre-processed to ensure its integrity, accuracy and analyzability, and finally form a high-quality data set. The specific steps are as follows: First, the data acquisition system obtains key data from multiple sensors in real time during the powder filling process, and synchronizes the data from different sources to ensure that the data corresponds correctly on the same timeline. Next, we enter the data cleaning phase to identify and remove outliers, remove noise signals, and complete missing data to improve data continuity and reliability. Then, the data is normalized and standardized, converting data of different units and scales into a unified standard range for subsequent analysis and modeling; Subsequently, the data is formatted and structured for storage, and the data from different sensors are stored in a database or data stream processing according to logical classification to ensure its accessibility and efficient call; Ultimately, a complete data set is generated for real-time monitoring, trend analysis, anomaly detection, and intelligent control optimization of powder filling status, ensuring the stability of the filling process, improving the consistency of green body quality, and providing data support for subsequent production optimization.

3. The control method for improving the unit weight consistency of NdFeB green billets according to claim 1, characterized in that: Through the feature extraction algorithm, the characteristic vector reflecting the change of powder flow rate is screened and extracted from the data set. The extracted characteristic vector includes the rebound effect caused by compression of the powder during the filling process and the discrete degree of the powder particles during the filling process. The rebound effect caused by compression of the powder during the filling process and the discrete degree of the powder particles during the filling process are comprehensively analyzed under the detection window to generate the powder compression rebound reference value and the particle discreteness reference value respectively. The powder filling stability is quantified by the powder compression rebound reference value and the particle discreteness reference value.

4. The control method for improving the unit weight consistency of NdFeB green billets according to claim 3, characterized in that: The specific steps for comprehensively analyzing the rebound effect of powder caused by compression during the filling process under the detection window to generate the powder compression rebound reference value are as follows: During the powder filling process, the powder in the local area will be subjected to compression force, resulting in a reduction in the particle gap, an increase in local density, and a compressed state. In order to quantify the degree of powder compression, the powder compression effect factor is defined to measure the compression effect of the powder during the filling process. The calculation expression is as follows: , where is the powder compression effect factor, The loose packing height of the powder before filling into the mold, It is the final height of the powder in the mold after being compressed. is the local contact pressure inside the powder particle, is the ambient pressure inside the mold; After powder filling, the powder will rebound due to the stress release between particles, resulting in a local decrease in filling density and a sudden change in flow rate. In order to quantify the rebound phenomenon, the powder compression rebound reference value is calculated to measure the rebound strength of the powder caused by compression. The calculation expression is as follows: , where is the powder compression rebound reference value, is the expansion recovery rate of the powder, It is the shear resistance factor of the powder, which describes the degree to which the friction and shearing between the powder particles inhibit rebound.

5. The control method for improving the unit weight consistency of NdFeB green billets according to claim 3, characterized in that: The specific steps for comprehensively analyzing the dispersion degree of powder particles during the filling process under the detection window to generate a reference value for particle dispersion are as follows: During the powder filling process, the distribution state of the particles is analyzed. First, the spatial distribution characteristics of the powder particles are constructed to identify the arrangement of the particles inside the mold. The detection window is divided into multiple micro-element areas. The particle density changes in each micro-element area are detected by laser scanning technology. The density ratio of the micro-element to the adjacent micro-element is calculated to obtain the local discrete offset rate. The calculation expression is as follows: , where It is a microelement The local discrete offset rate, is the target microelement The particle density inside is the neighboring microelement The particle density, is the target microelement The neighboring infinitesimal set, is the number of neighboring microelements, is the maximum value of the density of neighboring microelements, is a small constant that prevents the denominator from being zero; Obtaining the local discrete offset rate of all micro-element areas Finally, the powder filling state in the entire detection window is integrated to generate a reference value of particle dispersion. The generation formula is as follows: , where is the particle dispersion reference value, is the total number of microelements in the detection window, is the target microelement The particle motion intensity weight, is a smoothing factor to avoid the denominator being too small.

6. The control method for improving the unit weight consistency of NdFeB green billets according to claim 3, characterized in that: The analyzed powder compression rebound reference value and particle discreteness reference value are input into the pre-trained deep learning model, and the powder flow rate variation coefficient is generated by the deep learning model. The powder flow rate variation coefficient is used to intelligently evaluate whether the powder flow rate in the current mold is stable and within the normal range.

7. The control method for improving the unit weight consistency of NdFeB green billets according to claim 6, characterized in that: The powder flow rate variation coefficient generated by the pre-trained deep learning model when intelligently predicting whether the powder flow rate in the current mold is stable is compared and analyzed with the pre-set reference threshold of the powder flow rate variation coefficient, and the powder flow rate in the current mold is divided into stable and stable. The division steps are as follows: If the powder flow rate variation coefficient is greater than a preset powder flow rate variation coefficient reference threshold, it indicates that the powder flow rate in the current mold is accelerating; if the powder flow rate variation coefficient is less than or equal to a preset powder flow rate variation coefficient reference threshold, it indicates that the powder flow rate in the current mold is normal.

8. The control method for improving the unit weight consistency of NdFeB green billets according to claim 1, characterized in that: When the deep learning model recognizes that the powder flow rate in the current mold is accelerating, the local airflow intensity in the area where the flow rate is accelerating is dynamically reduced. At the same time, the specific steps for temporarily reducing the powder feed amount are as follows: When the deep learning model detects the coefficient of variation of the powder flow rate When it is greater than the preset powder flow rate variation coefficient reference threshold, it means that the powder flow rate in the current mold is accelerating, which will cause local overfilling. The local airflow intensity of the corresponding area is dynamically reduced to inhibit the rapid entry of powder. The airflow intensity adjustment formula is as follows: , where is the new airflow intensity value after dynamic adjustment. is the initial local airflow intensity value before adjustment, is the reference threshold value of the powder flow rate variation coefficient, is the natural base, is the adjustment sensitivity factor; While dynamically reducing the airflow intensity in the local area, it is also necessary to make a short adjustment to the powder feeding amount, that is, when the risk of rapid changes in the powder flow rate is found, the powder feeding amount should be reduced in a timely manner. The formula for adjusting the feeding amount is as follows; , where It is the dynamically adjusted powder feed amount, which is used to control the amount of powder delivered into the mold in real time. It is the reference value of powder feeding under normal and stable operation. is the powder feed adjustment factor, Feed sensitivity index; When the deep learning model recognizes that the powder flow rate has returned to the normal range, it gradually restores the local airflow intensity to the initial set value, and synchronously adjusts the powder feed amount to return it to a stable feed state to ensure the uniformity and continuity of the powder filling process.

Images