Superfine high-purity spherical silica powder particle size distribution regulation and control system and method

Abstract

The invention discloses an ultrafine high-purity spherical silica powder particle size distribution regulation and control system and method, and belongs to the technical field of spherical silica powder, the system comprises: a process parameter acquisition module configured to acquire real-time data of an ultrafine high-purity spherical silica powder preparation process; the process parameter processing module is configured to process the collected superfine high-purity spherical silica powder preparation process real-time data; and the particle size distribution regulation and control module is configured to construct a particle size distribution prediction model of the superfine high-purity spherical silica powder, predict the particle size distribution condition of the superfine high-purity spherical silica powder and carry out closed-loop regulation and control on the particle size distribution of the superfine high-purity spherical silica powder. The problems that in the prior art, the particle size distribution of the superfine high-purity spherical silica powder cannot be effectively regulated and controlled, and the use requirement cannot be well met are solved. According to the method, the particle size distribution of the superfine high-purity spherical silica powder can be effectively regulated and controlled, the using effect of the prepared superfine high-purity spherical silica powder is improved, and the using requirements can be well met.

Description

Technical Field

[0001] The present invention relates to the technical field of spherical silica powder, and specifically to a system and method for regulating the particle size distribution of ultra-fine and high-purity spherical silica powder. Background Art

[0002] Spherical silica powder, with its high purity, fine particle characteristics, excellent dielectric properties and thermal conductivity, and also having advantages such as a low coefficient of thermal expansion, plays an irreplaceable and important role in many fields such as integrated circuit packaging, aerospace, coating manufacturing, pharmaceutical production, and daily cosmetics.

[0003] Chinese Patent Application with Publication No. CN109455726A discloses a preparation method of spherical silica powder for electronic packaging. The method is to use the flame combustion method to prepare spherical silica powder with different particle sizes from angular silica powder with different particle sizes, and then perform coarse grading and fine grading on the spherical silica powder product, and finally perform particle size grading. By processes such as coarse grading and fine grading, large particles in the powder are removed, and the content of large particles is controlled to be less than 10, so as to effectively control large particles and avoid blockage of the encapsulation injection port or poor encapsulation caused by large particles during the use of downstream products. However, this patent has the following defects:

[0004] The existing technology cannot effectively regulate the particle size distribution of ultra-fine and high-purity spherical silica powder, resulting in poor use effects of the prepared ultra-fine and high-purity spherical silica powder and being unable to better meet the use requirements. Summary of the Invention

[0005] The purpose of the present invention is to provide a system and method for regulating the particle size distribution of ultra-fine and high-purity spherical silica powder, which can effectively regulate the particle size distribution of ultra-fine and high-purity spherical silica powder, improve the use effects of the prepared ultra-fine and high-purity spherical silica powder, and can better meet the use requirements, and solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] A system for regulating the particle size distribution of ultra-fine and high-purity spherical silica powder, comprising:

[0008] A process parameter acquisition module configured to acquire real-time data of the preparation process of ultra-fine and high-purity spherical silica powder;

[0009] A process parameter processing module configured to process the real-time data of the preparation process of ultra-fine and high-purity spherical silica powder acquired and determine the characteristic data of the preparation process of ultra-fine and high-purity spherical silica powder;

[0010] The particle size distribution control module is configured to build a prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder, analyze the process characteristic data of the preparation process of ultra-fine high-purity spherical silica powder, predict the particle size distribution of ultra-fine high-purity spherical silica powder, and perform closed-loop control on the particle size distribution of ultra-fine high-purity spherical silica powder.

[0011] Preferably, real-time data of the preparation process of ultra-fine high-purity spherical silica powder is collected, including:

[0012] The raw material particle size, melting temperature, melting time, cooling rate, air classification speed, air pressure, classifier rotation speed, sieve aperture of the sieve machine and vibration frequency during the preparation process of ultra-fine high-purity spherical silica powder are monitored and collected in real time to determine the real-time data of the preparation process of ultra-fine high-purity spherical silica powder.

[0013] Preferably, the real-time data of the preparation process of ultra-fine high-purity spherical silica powder is processed, including:

[0014] Clean the real-time data of the preparation process of ultra-fine high-purity spherical silica powder to remove the noise that is useless for the particle size distribution control of ultra-fine high-purity spherical silica powder in the real-time data of the preparation process of ultra-fine high-purity spherical silica powder;

[0015] Check the real-time data of the preparation process of ultra-fine high-purity spherical silica powder, identify the duplicate values, missing values and outliers in the real-time data of the preparation process of ultra-fine high-purity spherical silica powder, and process the duplicate values, missing values and outliers in the real-time data of the preparation process of ultra-fine high-purity spherical silica powder;

[0016] Among them, remove the duplicate values in the real-time data of the preparation process of ultra-fine high-purity spherical silica powder, and judge whether the missing values and outliers in the real-time data of the preparation process of ultra-fine high-purity spherical silica powder are useful for the particle size distribution control of ultra-fine high-purity spherical silica powder. If useful, fill the missing values with the average value and replace the outliers with the median value. If useless, directly delete the missing values and outliers.

[0017] Preferably, the processing of the real-time data of the preparation process of ultra-fine high-purity spherical silica powder further includes:

[0018] Normalize the real-time data of the preparation process of ultra-fine high-purity spherical silica powder to convert the real-time data of the preparation process of ultra-fine high-purity spherical silica powder into a unified data format, remove the dimension difference in the real-time data of the preparation process of ultra-fine high-purity spherical silica powder, and determine the standardized real-time data of the preparation process of ultra-fine high-purity spherical silica powder;

[0019] Extract features from the real-time data of the preparation process of ultra-fine high-purity spherical silica powder, extract the features useful for the particle size distribution control of ultra-fine high-purity spherical silica powder from the real-time data of the preparation process of ultra-fine high-purity spherical silica powder, and determine the process characteristic data of the preparation process of ultra-fine high-purity spherical silica powder.

[0020] Preferably, a prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder is constructed, including:

[0021] According to the regulation requirements of the particle size distribution of ultra-fine high-purity spherical silica powder, historical data of the preparation process of ultra-fine high-purity spherical silica powder is collected, including the particle size distribution of ultra-fine high-purity spherical silica powder;

[0022] The historical data of the preparation process of ultra-fine high-purity spherical silica powder collected is divided into a training set and a test set;

[0023] Based on deep learning technology, the training set is used to train the deep learning model, enabling the deep learning model to autonomously learn the relationship between the particle size distribution of ultra-fine high-purity spherical silica powder and the preparation process of ultra-fine high-purity spherical silica powder, and automatically learn the prediction behavior of the particle size distribution of ultra-fine high-purity spherical silica powder, so as to determine a prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder based on deep learning;

[0024] The test set is used to perform performance testing on the prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder based on deep learning, and evaluate whether the prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder based on deep learning can achieve the effect of predicting the particle size distribution of ultra-fine high-purity spherical silica powder;

[0025] When the prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder based on deep learning cannot achieve the effect of predicting the particle size distribution of ultra-fine high-purity spherical silica powder, the parameters of the prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder based on deep learning are adjusted, and the prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder based on deep learning is continuously optimized until the prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder based on deep learning can achieve the effect of predicting the particle size distribution of ultra-fine high-purity spherical silica powder, and the best prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder is determined.

[0026] Preferably, the characteristic data of the preparation process of ultra-fine high-purity spherical silica powder is analyzed to predict the particle size distribution of ultra-fine high-purity spherical silica powder, including:

[0027] The best prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder is obtained and deployed in the actual prediction environment of the particle size distribution of ultra-fine high-purity spherical silica powder;

[0028] Input the characteristic data of the preparation process of ultrafine high-purity spherical silica powder into the optimal prediction model for the particle size distribution of ultrafine high-purity spherical silica powder, analyze the characteristic data of the preparation process of ultrafine high-purity spherical silica powder according to the optimal prediction model for the particle size distribution of ultrafine high-purity spherical silica powder, predict the particle size distribution of ultrafine high-purity spherical silica powder, and determine the prediction result of the particle size distribution of ultrafine high-purity spherical silica powder.

[0029] Preferably, perform closed-loop regulation on the particle size distribution of ultrafine high-purity spherical silica powder, including:

[0030] Compare and analyze the prediction result of the particle size distribution of ultrafine high-purity spherical silica powder with the preset threshold of the particle size distribution of ultrafine high-purity spherical silica powder;

[0031] When the prediction result of the particle size distribution of ultrafine high-purity spherical silica powder is not within the threshold range of the particle size distribution of ultrafine high-purity spherical silica powder, regulate the particle size distribution of ultrafine high-purity spherical silica powder;

[0032] Among them, adjust the real-time data of the preparation process of ultrafine high-purity spherical silica powder, monitor the particle size distribution of ultrafine high-purity spherical silica powder after the process adjustment in real time, and perform feedback adjustment and optimization on the real-time data of the preparation process of ultrafine high-purity spherical silica powder according to the monitoring situation to form a closed-loop regulation of the particle size distribution of ultrafine high-purity spherical silica powder until the particle size distribution of the prepared ultrafine high-purity spherical silica powder is uniform.

[0033] Preferably, adjust the real-time data of the preparation process of ultrafine high-purity spherical silica powder, including:

[0034] When the prediction result of the particle size distribution of ultrafine high-purity spherical silica powder is not within the threshold range of the particle size distribution of ultrafine high-purity spherical silica powder, extract the deviation value between the prediction result of the particle size distribution of ultrafine high-purity spherical silica powder and the threshold range of the particle size distribution of ultrafine high-purity spherical silica powder;

[0035] Process the ratio of the deviation value to the span of the threshold range of the particle size distribution of ultrafine high-purity spherical silica powder to obtain a deviation ratio value;

[0036] Adjust the real-time data of the preparation process of ultrafine high-purity spherical silica powder according to the adjustment gradient of the initial process real-time data;

[0037] Extract the deviation value between the prediction result of the particle size distribution of ultrafine high-purity spherical silica powder after each adjustment and the threshold range of the particle size distribution of ultrafine high-purity spherical silica powder;

[0038] Process the ratio of the deviation value between the prediction result of the particle size distribution of ultrafine high-purity spherical silica powder after each adjustment and the threshold range of the particle size distribution of ultrafine high-purity spherical silica powder to the span of the threshold range of the particle size distribution of ultrafine high-purity spherical silica powder to obtain a dynamic deviation ratio value;

[0039] Compare the dynamic deviation ratio value with the deviation ratio value;

[0040] When the dynamic deviation ratio value exceeds the deviation ratio value, adjust the adjustment gradient of the process real-time data to reduce the adjustment gradient of the process real-time data, and prevent problems such as poor regulation stability and adjustment imbalance caused by excessive fluctuations in the adjustment of the process real-time data.

[0041] Preferably, when the dynamic deviation ratio value exceeds the deviation ratio value, adjusting the adjustment gradient of the process real-time data includes:

[0042] When the dynamic deviation ratio value exceeds the deviation ratio value, obtain the ratio deviation value between the dynamic deviation ratio value and the deviation ratio value;

[0043] Retrieve the real-time reaction temperature during the current preparation process of ultrafine high-purity spherical silica powder;

[0044] Compare the real-time reaction temperature during the current preparation process of ultrafine high-purity spherical silica powder with the reference temperature to obtain the temperature deviation value;

[0045] Retrieve the real-time gas pressure in the reaction chamber during the current preparation process of ultrafine high-purity spherical silica powder;

[0046] Compare the real-time gas pressure in the reaction chamber during the current preparation process of ultrafine high-purity spherical silica powder with the reference gas pressure to obtain the gas pressure deviation value;

[0047] Standardize the temperature deviation value and the gas pressure deviation value to obtain the standardized temperature deviation value and gas pressure deviation value;

[0048] Use the standardized temperature deviation value and gas pressure deviation value in combination with the ratio deviation value between the dynamic deviation ratio value and the deviation ratio value to obtain the gradient adjustment coefficient;

[0049] Among them, the gradient adjustment coefficient is obtained through the following formula:

[0050]

[0051] Among them, δ represents the gradient adjustment coefficient; P t represents the standardized temperature deviation value; P a represents the standardized gas pressure deviation value; B represents the ratio deviation value between the dynamic deviation ratio value and the deviation ratio value; D represents the dynamic deviation ratio value;

[0052] Use the gradient adjustment coefficient to adjust the adjustment gradient of the process real-time data. Among them, the adjusted adjustment gradient of the process real-time data is obtained through the following formula:

[0053]

[0054] Among them, G t represents the adjusted real-time process data adjustment gradient; G0 represents the real-time process data adjustment gradient before adjustment; δ represents the gradient adjustment coefficient; D b represents the standard deviation of the dynamic deviation ratio value; e represents a preset minimum coefficient to prevent ineffective gradient adjustment when the standard deviation of the dynamic deviation ratio value is 0.

[0055] According to another aspect of the present invention, there is provided a method for regulating the particle size distribution of ultra-fine high-purity spherical silica powder, which is implemented based on the above-mentioned system for regulating the particle size distribution of ultra-fine high-purity spherical silica powder, and includes the following steps:

[0056] Collect the real-time data of the ultra-fine high-purity spherical silica powder preparation process and determine the characteristic data of the ultra-fine high-purity spherical silica powder preparation process after processing;

[0057] Construct a prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder, analyze the characteristic data of the ultra-fine high-purity spherical silica powder preparation process, and determine the prediction result of the particle size distribution of ultra-fine high-purity spherical silica powder;

[0058] Analyze the prediction result of the particle size distribution of ultra-fine high-purity spherical silica powder, and close-loop regulate the particle size distribution of ultra-fine high-purity spherical silica powder according to the analysis situation until the particle size distribution of the prepared ultra-fine high-purity spherical silica powder is uniform.

[0059] Compared with the prior art, the beneficial effects of the present invention are:

[0060] The present invention monitors and collects in real time the raw material particle size, melting temperature, melting time, cooling rate, air classification speed, air pressure, classifier rotation speed, sieve aperture and vibration frequency of the ultra-fine high-purity spherical silica powder preparation process, determines the real-time data of the ultra-fine high-purity spherical silica powder preparation process, processes the real-time data of the ultra-fine high-purity spherical silica powder preparation process, determines the characteristic data of the ultra-fine high-purity spherical silica powder preparation process, constructs a prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder according to the requirements of regulating the particle size distribution of ultra-fine high-purity spherical silica powder, analyzes the characteristic data of the ultra-fine high-purity spherical silica powder preparation process, determines the prediction result of the particle size distribution of ultra-fine high-purity spherical silica powder, and analyzes the prediction result of the particle size distribution of ultra-fine high-purity spherical silica powder, and close-loop regulates the particle size distribution of ultra-fine high-purity spherical silica powder according to the analysis situation until the particle size distribution of the prepared ultra-fine high-purity spherical silica powder is uniform, can effectively regulate the particle size distribution of ultra-fine high-purity spherical silica powder, improve the use effect of the prepared ultra-fine high-purity spherical silica powder, and can better meet the use requirements. Description of the Drawings

[0061] Figure 1 This is a module diagram of the particle size distribution regulation system for ultrafine high-purity spherical silica powder of the present invention;

[0062] Figure 2 This is a flowchart of the method for regulating the particle size distribution of ultrafine high-purity spherical silica powder of the present invention. Detailed implementation manners

[0063] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0064] In order to solve the problem that the existing technology cannot effectively regulate the particle size distribution of ultrafine high-purity spherical silica powder, resulting in poor use effect of the prepared ultrafine high-purity spherical silica powder and inability to better meet the use requirements, please refer to Figure 1 - Figure 2 This embodiment provides the following technical solutions:

[0065] An ultrafine high-purity spherical silica powder particle size distribution regulation system includes: a process parameter acquisition module, a process parameter processing module, and a particle size distribution regulation module.

[0066] Specifically, through the interaction between the process parameter acquisition module, the process parameter processing module, and the particle size distribution regulation module, the particle size distribution of ultrafine high-purity spherical silica powder can be effectively regulated, the use effect of the prepared ultrafine high-purity spherical silica powder can be improved, and the use requirements can be better met.

[0067] Among them, the process parameter acquisition module is used to acquire the real-time data of the ultrafine high-purity spherical silica powder preparation process;

[0068] In this embodiment, acquiring the real-time data of the ultrafine high-purity spherical silica powder preparation process includes:

[0069] Real-time monitoring and acquisition of the raw material particle size, melting temperature, melting time, cooling rate, air classification speed, air pressure, classifier rotation speed, sieve aperture of the sieve machine, and vibration frequency during the preparation process of ultrafine high-purity spherical silica powder to determine the real-time data of the ultrafine high-purity spherical silica powder preparation process.

[0070] It should be noted that the raw material particle size is the initial crushing size of the raw material silica, which affects the subsequent melting and spheroidization effects; the melting temperature is the temperature of the particles in the molten state, and the melting temperature of the silica powder directly affects the spheroidization effect of the particles. Too high a temperature may cause excessive melting of the particles, while too low a temperature may prevent the formation of spheres; the melting time is the residence time of the particles in the molten state, which affects the integrity of spheroidization and the particle size; the cooling rate is the cooling speed of the molten particles, which affects the stability of the spherical structure and the crystallization state of the particles; the air classification speed is the air flow speed of the air classifier, which determines the classification effect of the particles and affects the uniformity of the final particle size distribution; the air pressure is the air pressure in the air classifier, which affects the classification accuracy of the particles; the classifier rotation speed is the rotation speed of the internal rotor of the classifier, which affects the classification accuracy of the particles; the sieve aperture and vibration frequency of the sieve determine the size range of the particles after screening.

[0071] Among them, the process parameter processing module is used to process the real-time data of the ultra-fine high-purity spherical silica powder preparation process to determine the characteristic data of the ultra-fine high-purity spherical silica powder preparation process;

[0072] In this embodiment, processing the real-time data of the ultra-fine high-purity spherical silica powder preparation process includes:

[0073] Cleaning the real-time data of the ultra-fine high-purity spherical silica powder preparation process to remove the noise that is useless for regulating the particle size distribution of the ultra-fine high-purity spherical silica powder in the real-time data of the ultra-fine high-purity spherical silica powder preparation process;

[0074] Checking the real-time data of the ultra-fine high-purity spherical silica powder preparation process to identify duplicate values, missing values, and outliers in the real-time data of the ultra-fine high-purity spherical silica powder preparation process, and processing the duplicate values, missing values, and outliers in the real-time data of the ultra-fine high-purity spherical silica powder preparation process;

[0075] Among them, removing the duplicate values in the real-time data of the ultra-fine high-purity spherical silica powder preparation process, and judging whether the missing values and outliers in the real-time data of the ultra-fine high-purity spherical silica powder preparation process are useful for regulating the particle size distribution of the ultra-fine high-purity spherical silica powder. If useful, fill the missing values with the average value and replace the outliers with the median value. If useless, directly delete the missing values and outliers;

[0076] It should be noted that by cleaning the real-time data of the ultra-fine high-purity spherical silica powder preparation process, the data quality can be improved.

[0077] Normalizing the real-time data of the ultra-fine high-purity spherical silica powder preparation process to convert the real-time data of the ultra-fine high-purity spherical silica powder preparation process into a unified data format, removing the dimensional differences in the real-time data of the ultra-fine high-purity spherical silica powder preparation process, and determining the standardized real-time data of the ultra-fine high-purity spherical silica powder preparation process;

[0078] Extract the features of the real-time data of the preparation process of ultrafine high-purity spherical silica powder, extract the features useful for regulating the particle size distribution of ultrafine high-purity spherical silica powder from the real-time data of the preparation process of ultrafine high-purity spherical silica powder, and determine the characteristic data of the preparation process of ultrafine high-purity spherical silica powder.

[0079] Among them, the particle size distribution regulation module is used to construct a prediction model for the particle size distribution of ultrafine high-purity spherical silica powder, analyze the characteristic data of the preparation process of ultrafine high-purity spherical silica powder, predict the particle size distribution of ultrafine high-purity spherical silica powder, and perform closed-loop regulation on the particle size distribution of ultrafine high-purity spherical silica powder.

[0080] In this embodiment, constructing a prediction model for the particle size distribution of ultrafine high-purity spherical silica powder includes:

[0081] According to the requirements for regulating the particle size distribution of ultrafine high-purity spherical silica powder, collect the historical data of the preparation process of ultrafine high-purity spherical silica powder, including the particle size distribution of ultrafine high-purity spherical silica powder;

[0082] Divide the collected historical data of the preparation process of ultrafine high-purity spherical silica powder into a training set and a test set;

[0083] Based on deep learning technology, use the training set to train the deep learning model, enable the deep learning model to autonomously learn the relationship between the particle size distribution of ultrafine high-purity spherical silica powder and the preparation process of ultrafine high-purity spherical silica powder, and automatically learn the prediction behavior of the particle size distribution of ultrafine high-purity spherical silica powder, and determine the prediction model for the particle size distribution of ultrafine high-purity spherical silica powder based on deep learning;

[0084] Use the test set to perform performance testing on the prediction model for the particle size distribution of ultrafine high-purity spherical silica powder based on deep learning, and evaluate whether the prediction model for the particle size distribution of ultrafine high-purity spherical silica powder based on deep learning can achieve the effect of predicting the particle size distribution of ultrafine high-purity spherical silica powder;

[0085] When the prediction model for the particle size distribution of ultrafine high-purity spherical silica powder based on deep learning cannot achieve the effect of predicting the particle size distribution of ultrafine high-purity spherical silica powder, adjust the parameters of the prediction model for the particle size distribution of ultrafine high-purity spherical silica powder based on deep learning, and continuously optimize the prediction model for the particle size distribution of ultrafine high-purity spherical silica powder based on deep learning until the prediction model for the particle size distribution of ultrafine high-purity spherical silica powder based on deep learning can achieve the effect of predicting the particle size distribution of ultrafine high-purity spherical silica powder, and determine the optimal prediction model for the particle size distribution of ultrafine high-purity spherical silica powder.

[0086] In this embodiment, the characteristic data of the preparation process of ultra-fine high-purity spherical silica powder is analyzed to predict the particle size distribution of ultra-fine high-purity spherical silica powder, including:

[0087] Obtain the optimal prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder, and deploy the optimal prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder in the actual prediction environment of the particle size distribution of ultra-fine high-purity spherical silica powder;

[0088] Input the characteristic data of the preparation process of ultra-fine high-purity spherical silica powder into the optimal prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder, analyze the characteristic data of the preparation process of ultra-fine high-purity spherical silica powder according to the optimal prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder, and predict the particle size distribution of ultra-fine high-purity spherical silica powder to determine the prediction result of the particle size distribution of ultra-fine high-purity spherical silica powder.

[0089] In this embodiment, a closed-loop control of the particle size distribution of ultra-fine high-purity spherical silica powder is performed, including:

[0090] Compare and analyze the prediction result of the particle size distribution of ultra-fine high-purity spherical silica powder with the preset threshold of the particle size distribution of ultra-fine high-purity spherical silica powder;

[0091] When the prediction result of the particle size distribution of ultra-fine high-purity spherical silica powder is not within the range of the threshold of the particle size distribution of ultra-fine high-purity spherical silica powder, then adjust the particle size distribution of ultra-fine high-purity spherical silica powder;

[0092] Among them, adjust the real-time data of the preparation process of ultra-fine high-purity spherical silica powder, monitor the particle size distribution of ultra-fine high-purity spherical silica powder after the process adjustment in real time, and perform feedback adjustment and optimization on the real-time data of the preparation process of ultra-fine high-purity spherical silica powder according to the monitoring situation to form a closed-loop control of the particle size distribution of ultra-fine high-purity spherical silica powder until the particle size distribution of the prepared ultra-fine high-purity spherical silica powder is uniform.

[0093] To better show the control process of the particle size distribution of ultra-fine high-purity spherical silica powder, this embodiment now provides a method for controlling the particle size distribution of ultra-fine high-purity spherical silica powder, which is implemented based on the above-mentioned control system for the particle size distribution of ultra-fine high-purity spherical silica powder, and includes the following steps:

[0094] Collect the real-time data of the preparation process of ultra-fine high-purity spherical silica powder, and determine the characteristic data of the preparation process of ultra-fine high-purity spherical silica powder after processing; construct a prediction model for the particle size distribution of ultra-fine high-purity spherical silica powder, analyze the characteristic data of the preparation process of ultra-fine high-purity spherical silica powder, and determine the prediction result of the particle size distribution of ultra-fine high-purity spherical silica powder; analyze the prediction result of the particle size distribution of ultra-fine high-purity spherical silica powder, and closed-loop control the particle size distribution of ultra-fine high-purity spherical silica powder according to the analysis situation until the particle size distribution of the prepared ultra-fine high-purity spherical silica powder is uniform, so as to effectively control the particle size distribution of ultra-fine high-purity spherical silica powder, improve the use effect of the prepared ultra-fine high-purity spherical silica powder, and better meet the use requirements.

[0095] Specifically, the adjustment of the real-time data of the preparation process of ultra-fine high-purity spherical silica powder includes:

[0096] When the prediction result of the particle size distribution of ultra-fine high-purity spherical silica powder is not within the threshold range of the particle size distribution of ultra-fine high-purity spherical silica powder, extract the deviation value between the prediction result of the particle size distribution of ultra-fine high-purity spherical silica powder and the threshold range of the particle size distribution of ultra-fine high-purity spherical silica powder;

[0097] Perform a ratio process on the deviation value and the span of the threshold range of the particle size distribution of ultra-fine high-purity spherical silica powder to obtain a deviation ratio value;

[0098] Adjust the real-time data of the preparation process of ultra-fine high-purity spherical silica powder according to the adjustment gradient of the initial process real-time data;

[0099] Extract the deviation value between the prediction result of the particle size distribution of ultra-fine high-purity spherical silica powder after each adjustment and the threshold range of the particle size distribution of ultra-fine high-purity spherical silica powder;

[0100] Perform a ratio process on the deviation value between the prediction result of the particle size distribution of ultra-fine high-purity spherical silica powder after each adjustment and the threshold range of the particle size distribution of ultra-fine high-purity spherical silica powder and the span of the threshold range of the particle size distribution of ultra-fine high-purity spherical silica powder to obtain a dynamic deviation ratio value;

[0101] Compare the dynamic deviation ratio value with the deviation ratio value;

[0102] When the dynamic deviation ratio value exceeds the deviation ratio value, adjust the adjustment gradient of the process real-time data to reduce the adjustment gradient of the process real-time data, and prevent problems such as poor control stability and adjustment imbalance caused by excessive fluctuations in the adjustment of the process real-time data.

[0103] The technical effects of the above technical solution are as follows: By real-time monitoring the prediction results of the particle size distribution of ultrafine high-purity spherical silica powder and comparing them with the preset threshold range, it is possible to promptly detect whether the particle size distribution deviates from the target range. Extract the deviation value and perform a ratio process to obtain the deviation ratio value, providing an accurate quantitative basis for subsequent adjustments. Continuously extract and adjust the deviation values for dynamic comparison to ensure that the particle size distribution continuously approaches and remains within the target threshold range, thereby improving the control accuracy of the particle size distribution. The setting of the adjustment gradient of the initial process real-time data is to enable timely adjustment when deviations are detected. By dynamically comparing the dynamic deviation ratio value with the deviation ratio value, when the dynamic deviation ratio value exceeds the deviation ratio value, appropriately reduce the adjustment gradient of the process real-time data, which helps prevent process fluctuations caused by excessive adjustment. Reducing the adjustment gradient can reduce the sharp changes in process parameters, thereby enhancing the stability of the entire preparation process. This technical solution can more efficiently identify and solve particle size distribution deviation problems through real-time data feedback and dynamic adjustment mechanisms. By gradually adjusting and monitoring the adjustment effects, it can be ensured that each adjustment is in the correct direction, avoiding ineffective or reverse adjustments. The optimized adjustment strategy not only improves the adjustment efficiency but also ensures the quality and performance of the final product. By precisely controlling the particle size distribution, waste caused by unqualified products can be reduced. A stable process also helps reduce equipment failures and downtime, thereby reducing maintenance costs and production costs.

[0104] In summary, this technical solution significantly improves the control accuracy of the particle size distribution, enhances process stability, optimizes the adjustment efficiency and effect, and reduces resource waste and costs in terms of performance indicators. These technical effects are of great significance for improving the production quality and efficiency of ultrafine high-purity spherical silica powder.

[0105] Specifically, when the dynamic deviation ratio value exceeds the deviation ratio value, the adjustment of the adjustment gradient of the process real-time data includes:

[0106] When the dynamic deviation ratio value exceeds the deviation ratio value, obtain the ratio deviation value between the dynamic deviation ratio value and the deviation ratio value;

[0107] Retrieve the real-time reaction temperature during the current preparation process of ultrafine high-purity spherical silica powder;

[0108] Compare the real-time reaction temperature during the current preparation process of ultrafine high-purity spherical silica powder with the reference temperature to obtain the temperature deviation value;

[0109] Retrieve the real-time gas pressure in the reaction chamber during the current preparation process of ultrafine high-purity spherical silica powder;

[0110] Compare the real-time gas pressure in the reaction chamber during the current preparation process of ultrafine high-purity spherical silica powder with the reference gas pressure to obtain the gas pressure deviation value;

[0111] Normalize the temperature deviation value and the gas pressure deviation value to obtain the normalized temperature deviation value and gas pressure deviation value;

[0112] Use the normalized temperature deviation value and gas pressure deviation value, combined with the proportional deviation value between the dynamic deviation ratio value and the deviation ratio value, to obtain the gradient adjustment coefficient;

[0113] Among them, the gradient adjustment coefficient is obtained through the following formula:

[0114]

[0115] Among them, δ represents the gradient adjustment coefficient; P t represents the normalized temperature deviation value; P a represents the normalized gas pressure deviation value; B represents the proportional deviation value between the dynamic deviation ratio value and the deviation ratio value; D represents the dynamic deviation ratio value;

[0116] Use the gradient adjustment coefficient to adjust the adjustment gradient of the process real-time data. Among them, the adjusted adjustment gradient of the process real-time data is obtained through the following formula:

[0117]

[0118] Among them, G t represents the adjusted adjustment gradient of the process real-time data; G0 represents the adjustment gradient of the process real-time data before adjustment; δ represents the gradient adjustment coefficient; D b represents the standard deviation of the dynamic deviation ratio value; e represents a preset minimum coefficient to prevent ineffective gradient adjustment when the standard deviation of the dynamic deviation ratio value is 0.

[0119] The technical effect of the above technical solution is as follows: By real-time monitoring of the dynamic deviation ratio value, temperature deviation value, gas pressure deviation value, etc., abnormal fluctuations in the preparation process of ultrafine high-purity spherical silica powder can be captured in a timely manner. Once the dynamic deviation ratio value exceeds the set value, the gradient adjustment coefficient is calculated based on the relevant deviation values to adjust the adjustment gradient of the process real-time data, so that the process parameters can quickly return to a reasonable range, reducing the problem of unstable product quality caused by parameter fluctuations and improving the consistency and stability of product quality.

[0120] This formula comprehensively considers the temperature deviation, gas pressure deviation, and the proportional deviation value between the dynamic deviation ratio value and the deviation ratio value to determine the gradient adjustment coefficient. The exponential functions exp(-P t ), exp(-P a)It is used to perform non - linear conversion on the standardized temperature deviation value and gas pressure deviation value to highlight the influence degree of the deviation value on the adjustment coefficient. Taking the maximum value of the two is to emphasize the key consideration of the deviation factor with greater influence, then multiplying it by the proportional deviation value B and dividing by the dynamic deviation proportional value D to finally obtain the gradient adjustment coefficient δ. At the same time, the gradient adjustment coefficient reflects the intensity coefficient of process parameter adjustment considering temperature, gas pressure deviation, and dynamic deviation proportional deviation comprehensively. The larger the δ value, the more serious the current process parameter deviates from the ideal state, and a greater adjustment of the process real - time data adjustment gradient is required.

[0121] By calculating the proportional deviation value between the dynamic deviation proportional value and the deviation proportional value, the deviation degree between the current process state and the target state can be quantified more precisely, so as to achieve a finer adjustment of the process real - time data adjustment gradient. Introducing the real - time reaction temperature and reaction chamber gas pressure as adjustment parameters not only considers the influence of particle size distribution but also other process parameters that may affect product quality, enhancing the comprehensiveness and flexibility of the adjustment. By standardizing the temperature deviation value and gas pressure deviation value, the influence of dimension and value range between different parameters is eliminated, making these parameters comparable in the calculation of the gradient adjustment coefficient, thus improving the stability and controllability of process parameters. Using the gradient adjustment coefficient to adjust the process real - time data adjustment gradient can ensure that each adjustment is based on the precise quantitative analysis of the current process state, avoiding the risks of blind adjustment and over - adjustment, and improving the stability and controllability of the process. Through precise gradient adjustment, the waste of raw materials and energy consumption caused by process parameter fluctuations can be reduced, thus improving the resource utilization efficiency. At the same time, due to the stability and optimization of process parameters, the rework and scrap caused by product quality problems can be reduced, further lowering the production cost. By real - time monitoring and adjusting process parameters, it can be ensured that the particle size distribution and other performance indicators of ultrafine high - purity spherical silica powder always remain within the target range, thus improving the quality and consistency of the product. This technical solution enhances the adaptability and robustness of the system to process condition changes by introducing a real - time monitoring and adjustment mechanism for multiple process parameters. Even when the process conditions change greatly, the system can maintain the stability and optimization of process parameters through precise gradient adjustment, thus ensuring the stability and consistency of product quality.

[0122] Meanwhile, through the above technical solution, the adjustment gradient of process real-time data can be timely reduced, enabling the maximized matching between the adjusted adjustment gradient and the current situation of process data adjustment, preventing the problem of reduced process adjustment stability caused by process fluctuations due to excessive adjustment. At the same time, the standard deviation of the dynamic deviation ratio value during the process adjustment is used to restrict the reduction amplitude of the gradient, which can control the process adjustment efficiency to the greatest extent while reducing the fluctuation gradient, preventing the problem of too long adjustment cycle caused by too low process adjustment efficiency.

[0123] In summary, this technical solution significantly enhances the accuracy and flexibility of adjustment in performance indicators, improves process stability and controllability, optimizes resource utilization and reduces production costs, enhances product quality and consistency, and strengthens system adaptability and robustness. These technical effects are of great significance for improving the production quality and efficiency of ultra-fine high-purity spherical silica powder.

[0124] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0125] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A system for controlling the particle size distribution of ultrafine high-purity spherical silicon micropowder, characterized in that: include: A process parameter acquisition module configured to collect real-time data of the ultrafine high-purity spherical silicon powder preparation process; A process parameter processing module is configured to process the collected real-time data of the ultrafine high-purity spherical silicon micropowder preparation process and determine the characteristic data of the ultrafine high-purity spherical silicon micropowder preparation process; The particle size distribution control module is configured to construct an ultrafine high-purity spherical silicon micropowder particle size distribution prediction model, analyze the ultrafine high-purity spherical silicon micropowder preparation process characteristic data, predict the ultrafine high-purity spherical silicon micropowder particle size distribution, and perform closed-loop control of the ultrafine high-purity spherical silicon micropowder particle size distribution.

2. The ultrafine high-purity spherical silicon powder particle size distribution control system according to claim 1, characterized in that: Collect real-time data of ultra-fine high-purity spherical silicon powder preparation process, including: The raw material particle size, melting temperature, melting time, cooling rate, airflow classification speed, airflow pressure, classifier speed, screening machine mesh aperture and vibration frequency in the preparation process of ultrafine high-purity spherical silicon powder are monitored and collected in real time to determine the real-time data of the ultrafine high-purity spherical silicon powder preparation process.

3. The ultrafine high-purity spherical silicon powder particle size distribution control system according to claim 1, characterized in that: Processing of real-time data of ultrafine high-purity spherical silicon powder preparation process, including: Clean the real-time data of the preparation process of ultrafine high-purity spherical silicon micropowder to remove the noise that is useless for the particle size distribution control of ultrafine high-purity spherical silicon micropowder in the real-time data of the preparation process of ultrafine high-purity spherical silicon micropowder; Check the real-time data of the ultrafine high-purity spherical silicon micropowder preparation process, identify the duplicate values, missing values ​​and abnormal values ​​in the real-time data of the ultrafine high-purity spherical silicon micropowder preparation process, and process the duplicate values, missing values ​​and abnormal values ​​in the real-time data of the ultrafine high-purity spherical silicon micropowder preparation process; Among them, the duplicate values ​​in the real-time data of the preparation process of ultrafine high-purity spherical silicon micropowder are removed, and it is judged whether the missing values ​​and outliers in the real-time data of the preparation process of ultrafine high-purity spherical silicon micropowder are useful for the regulation of the particle size distribution of ultrafine high-purity spherical silicon micropowder. If useful, the missing values ​​are filled with the mean and the outliers are replaced with the median. If useless, the missing values ​​and outliers are directly deleted.

4. The ultrafine high-purity spherical silicon powder particle size distribution control system according to claim 3, characterized in that: Processing of real-time data of ultrafine high-purity spherical silicon powder preparation process, including: Normalize the real-time data of the ultrafine high-purity spherical silicon micropowder preparation process, convert the real-time data of the ultrafine high-purity spherical silicon micropowder preparation process into a unified data format, remove the dimension difference in the real-time data of the ultrafine high-purity spherical silicon micropowder preparation process, and determine the standardized real-time data of the ultrafine high-purity spherical silicon micropowder preparation process; Feature extraction is performed on the real-time data of the ultrafine high-purity spherical silicon micropowder preparation process, and features useful for regulating the particle size distribution of the ultrafine high-purity spherical silicon micropowder are extracted from the real-time data of the ultrafine high-purity spherical silicon micropowder preparation process to determine the characteristic data of the ultrafine high-purity spherical silicon micropowder preparation process.

5. The ultrafine high-purity spherical silicon powder particle size distribution control system according to claim 1, characterized in that: Construct a prediction model for the particle size distribution of ultrafine high-purity spherical silicon powder, including: According to the demand for regulating the particle size distribution of ultrafine high-purity spherical silicon micropowder, collect the historical data of the preparation process of ultrafine high-purity spherical silicon micropowder, including the particle size distribution of ultrafine high-purity spherical silicon micropowder; The collected historical data of the preparation process of ultrafine high-purity spherical silicon micropowder are divided into a training set and a test set; Based on deep learning technology, the deep learning model is trained with a training set, so that the deep learning model can autonomously learn the relationship between the particle size distribution of ultrafine high-purity spherical silicon micropowder and the preparation process of ultrafine high-purity spherical silicon micropowder, and automatically learn the prediction behavior of the particle size distribution of ultrafine high-purity spherical silicon micropowder, and determine the prediction model of the particle size distribution of ultrafine high-purity spherical silicon micropowder based on deep learning; The test set is used to test the performance of the ultrafine high-purity spherical silicon micropowder particle size distribution prediction model based on deep learning, and to evaluate whether the ultrafine high-purity spherical silicon micropowder particle size distribution prediction model based on deep learning can achieve the effect of predicting the particle size distribution of ultrafine high-purity spherical silicon micropowder; When the ultrafine high-purity spherical silicon micropowder particle size distribution prediction model based on deep learning cannot achieve the effect of predicting the particle size distribution of ultrafine high-purity spherical silicon micropowder, the parameters of the ultrafine high-purity spherical silicon micropowder particle size distribution prediction model based on deep learning are adjusted, and the ultrafine high-purity spherical silicon micropowder particle size distribution prediction model based on deep learning is continuously optimized until the ultrafine high-purity spherical silicon micropowder particle size distribution prediction model based on deep learning can achieve the effect of predicting the particle size distribution of ultrafine high-purity spherical silicon micropowder, and the optimal ultrafine high-purity spherical silicon micropowder particle size distribution prediction model is determined.

6. The ultrafine high-purity spherical silicon powder particle size distribution control system according to claim 5, characterized in that: Analyze the process characteristic data of ultrafine high-purity spherical silicon powder preparation and predict the particle size distribution of ultrafine high-purity spherical silicon powder, including: Obtain the best ultrafine high-purity spherical silicon micropowder particle size distribution prediction model, and deploy the best ultrafine high-purity spherical silicon micropowder particle size distribution prediction model in the actual ultrafine high-purity spherical silicon micropowder particle size distribution prediction environment; The ultrafine high-purity spherical silicon micropowder preparation process characteristic data are input into the optimal ultrafine high-purity spherical silicon micropowder particle size distribution prediction model, and the ultrafine high-purity spherical silicon micropowder preparation process characteristic data are analyzed according to the optimal ultrafine high-purity spherical silicon micropowder particle size distribution prediction model, and the ultrafine high-purity spherical silicon micropowder particle size distribution is predicted to determine the ultrafine high-purity spherical silicon micropowder particle size distribution prediction result.

7. The ultrafine high-purity spherical silicon powder particle size distribution control system according to claim 6, characterized in that: Closed-loop control of the particle size distribution of ultrafine high-purity spherical silicon powder, including: Compare and analyze the prediction results of the particle size distribution of ultrafine high-purity spherical silicon micropowder with the pre-set particle size distribution threshold of ultrafine high-purity spherical silicon micropowder; When the prediction result of the particle size distribution of the ultrafine high-purity spherical silicon micropowder is not within the threshold range of the particle size distribution of the ultrafine high-purity spherical silicon micropowder, the particle size distribution of the ultrafine high-purity spherical silicon micropowder is regulated; Among them, the real-time data of the ultrafine high-purity spherical silicon micropowder preparation process is adjusted, and the particle size distribution of the ultrafine high-purity spherical silicon micropowder after the process adjustment is monitored in real time, and the real-time data of the ultrafine high-purity spherical silicon micropowder preparation process is fed back, adjusted and optimized according to the monitoring conditions to form a closed-loop control of the particle size distribution of ultrafine high-purity spherical silicon micropowder until the prepared ultrafine high-purity spherical silicon micropowder has a uniform particle size distribution.

8. The ultrafine high-purity spherical silicon powder particle size distribution control system according to claim 7, characterized in that: Adjust the real-time data of the ultra-fine high-purity spherical silicon powder preparation process, including: When the predicted result of the particle size distribution of the ultrafine high-purity spherical silicon micropowder is not within the threshold range of the particle size distribution of the ultrafine high-purity spherical silicon micropowder, extracting the deviation value between the predicted result of the particle size distribution of the ultrafine high-purity spherical silicon micropowder and the threshold range of the particle size distribution of the ultrafine high-purity spherical silicon micropowder; The deviation value is ratioed with the threshold range span of the ultrafine high-purity spherical silicon powder particle size distribution to obtain a deviation ratio value; Adjust the real-time data of the ultrafine high-purity spherical silicon powder preparation process according to the initial process real-time data adjustment gradient; Extract the deviation value between the predicted result of the particle size distribution of the ultrafine high-purity spherical silicon micropowder after each adjustment and the threshold range of the particle size distribution of the ultrafine high-purity spherical silicon micropowder; The deviation value between the predicted result of the particle size distribution of the ultrafine high-purity spherical silicon micropowder after each adjustment and the threshold range of the particle size distribution of the ultrafine high-purity spherical silicon micropowder and the threshold range span of the particle size distribution of the ultrafine high-purity spherical silicon micropowder are processed by ratio, so as to obtain a dynamic deviation ratio value; comparing the dynamic deviation ratio value with the deviation ratio value; When the dynamic deviation ratio value exceeds the deviation ratio value, the process real-time data adjustment gradient is adjusted.

9. The ultrafine high-purity spherical silicon powder particle size distribution control system according to claim 8, characterized in that: When the dynamic deviation ratio value exceeds the deviation ratio value, the process real-time data adjustment gradient is adjusted, including: When the dynamic deviation ratio value exceeds the deviation ratio value, obtaining a proportional deviation value between the dynamic deviation ratio value and the deviation ratio value; Retrieve the real-time reaction temperature during the preparation of ultrafine high-purity spherical silicon powder; Comparing the real-time reaction temperature in the current ultrafine high-purity spherical silicon powder preparation process with the reference temperature to obtain a temperature deviation value; Retrieve the real-time reaction chamber gas pressure during the current preparation process of ultrafine high-purity spherical silicon powder; Comparing the real-time reaction chamber gas pressure during the current ultrafine high-purity spherical silicon powder preparation process with the reference gas pressure to obtain a gas pressure deviation value; Performing standardization processing on the temperature deviation value and the gas pressure deviation value to obtain the temperature deviation value and the gas pressure deviation value after the standardization processing; The gradient adjustment coefficient is obtained by using the standardized temperature deviation value and the gas pressure deviation value combined with the proportional deviation value between the dynamic deviation proportional value and the deviation proportional value; The gradient adjustment coefficient is used to adjust the process real-time data adjustment gradient.

10. A method for regulating the particle size distribution of ultrafine high-purity spherical silicon micropowder, which is implemented based on the ultrafine high-purity spherical silicon micropowder particle size distribution regulation system according to claim 9, characterized in that: The steps include: Collect real-time data of the ultrafine high-purity spherical silicon micropowder preparation process and determine the characteristic data of the ultrafine high-purity spherical silicon micropowder preparation process after processing; Construct a prediction model for the particle size distribution of ultrafine high-purity spherical silicon micropowder, analyze the characteristic data of the preparation process of ultrafine high-purity spherical silicon micropowder, and determine the prediction results of the particle size distribution of ultrafine high-purity spherical silicon micropowder; The prediction results of the particle size distribution of ultrafine high-purity spherical silicon micropowder are analyzed, and the particle size distribution of ultrafine high-purity spherical silicon micropowder is closed-loop controlled according to the analysis results until the particle size distribution of the prepared ultrafine high-purity spherical silicon micropowder is uniform.

Images