Quick-setting drying method and device for silicate materials

Abstract

The present application relates to the technical field of solid drying, and discloses a rapid setting and drying method and device for silicate materials. The method includes: performing stress pre-regulation on raw materials through three-dimensional network analysis and double-axis stirring to obtain a slurry; preparing a preform by using partition pressure control and temperature gradient regulation; collecting acoustic emission signals and performing time-frequency analysis to evaluate the stress field; optimizing air flow drying by using an orthogonal fan array; performing differential treatment by a phased array microwave source; and finally obtaining a finished product through ultrasonic stress elimination and speckle strain monitoring. The present application realizes precise stress regulation in the drying process through multi-dimensional data acquisition, dynamic feedback regulation, and intelligent control strategies.

Description

Technical Field

[0001] This application relates to the field of solid drying, and particularly to a rapid setting and drying method and device for silicate materials. Background Art

[0002] In the field of rapid setting and drying of silicate materials, traditional drying processes mainly rely on conventional heating and natural drying methods to remove moisture from products. Currently, a variety of drying technologies have been developed in the industry, including hot air drying, vacuum drying, and microwave drying. Among them, hot air drying removes moisture in the material by heating the air, vacuum drying uses the pressure difference to achieve moisture evaporation, and microwave drying uses electromagnetic waves to excite the vibration of water molecules to generate heat. These methods have been widely used in industrial production and achieved certain effects.

[0003] However, the existing drying technologies have obvious deficiencies. Firstly, traditional drying methods often result in large stress gradients inside the material, causing quality problems such as product cracking and deformation. Secondly, a single drying method is difficult to adapt to the drying requirements of different regions, resulting in uneven drying and affecting the quality stability of products. In addition, the existing technology lacks real-time monitoring and precise control means for the internal stress state of the material, unable to effectively prevent and eliminate stress concentration during the drying process, while having low energy utilization efficiency, long drying cycles, and limited production efficiency. Summary of the Invention

[0004] This application provides a rapid setting and drying method and device for silicate materials. Aiming at the problems of inaccurate stress control and uneven drying in the existing silicate material drying technology, through multi-dimensional data acquisition, dynamic feedback regulation, and intelligent control strategies, precise stress regulation during the drying process is achieved.

[0005] In a first aspect, the present application provides a rapid setting and drying method for silicate materials. The rapid setting and drying method for silicate materials includes: performing stress pre-regulation treatment on silicate raw materials, polypropylene fibers, and nano-silica through three-dimensional network construction analysis, and performing variable-frequency dual-axis stirring according to the shear stress monitoring data to obtain pre-regulated slurry; according to the pre-regulated slurry, using a partition pressure control system to perform gradient injection treatment on the core area, transition area, and surface area, and obtaining a silicate preform with an initial stress field through temperature gradient co-control; collecting acoustic emission signals of the silicate preform, dynamically evaluating the stress field distribution through a time-frequency feature analysis algorithm, and adjusting the temperature and humidity parameters using a closed-loop feedback system to obtain a pre-dried silicate workpiece; according to the stress field distribution data of the pre-dried silicate workpiece, dynamically optimizing the air flow intensity and direction through an orthogonal fan array control algorithm to obtain an air-dried silicate workpiece; performing stress field scanning on the air-dried silicate workpiece, and performing differential energy input treatment on high and low stress areas through a phased array microwave source to obtain a microwave-dried silicate workpiece; placing the microwave-dried silicate workpiece in an ultrasonic stress elimination system, and dynamically monitoring the surface strain field through a speckle strain detection algorithm to obtain a target silicate product.

[0006] In a second aspect, the present application provides a rapid setting and drying device for silicate materials. The rapid setting and drying device for silicate materials includes:

[0007] A stirring module for performing stress pre-regulation treatment on silicate raw materials, polypropylene fibers, and nano-silica through three-dimensional network construction analysis, and performing variable-frequency dual-axis stirring according to the shear stress monitoring data to obtain pre-regulated slurry;

[0008] An injection module for, according to the pre-regulated slurry, using a partition pressure control system to perform gradient injection treatment on the core area, transition area, and surface area, and obtaining a silicate preform with an initial stress field through temperature gradient co-control;

[0009] An adjustment module for collecting acoustic emission signals of the silicate preform, dynamically evaluating the stress field distribution through a time-frequency feature analysis algorithm, and adjusting the temperature and humidity parameters using a closed-loop feedback system to obtain a pre-dried silicate workpiece;

[0010] A drying module for, according to the stress field distribution data of the pre-dried silicate workpiece, dynamically optimizing the air flow intensity and direction through an orthogonal fan array control algorithm to obtain an air-dried silicate workpiece;

[0011] A processing module for performing stress field scanning on the air-dried silicate workpiece, and performing differential energy input treatment on high and low stress areas through a phased array microwave source to obtain a microwave-dried silicate workpiece;

[0012] A monitoring module, which is used to place the microwave-dried silicate workpiece in an ultrasonic stress relief system, dynamically monitor the surface strain field through a speckle strain detection algorithm, and obtain a target silicate product.

[0013] In the technical solution provided by this application, through the design of stress pre-regulation treatment for silicate raw materials, polypropylene fibers and nano-silica by three-dimensional network construction analysis, precise stress control during the raw material mixing process is achieved, effectively avoiding the problem of uneven stress distribution in traditional mixing methods; the design of gradient injection treatment for the core area, transition area and surface area by using a partition pressure control system establishes a complete pressure gradient control system to ensure the uniformity of pressure distribution in each area of the workpiece; the design of dynamically evaluating the stress field distribution by using acoustic emission signal acquisition and time-frequency feature analysis algorithms realizes the real-time monitoring and precise evaluation of the stress field distribution, providing an accurate basis for subsequent process parameter adjustment; the design of dynamically optimizing the air flow intensity and direction based on the orthogonal fan array control algorithm realizes the precise regulation of the air flow field and improves the drying uniformity; the design of differential energy input treatment for high and low stress areas by a phased array microwave source realizes the precise control of energy input and avoids local overheating or underheating phenomena; the design of combining ultrasonic stress relief technology with a speckle strain detection algorithm realizes the precise elimination and real-time monitoring of the stress field. Especially in the application of artificial intelligence algorithms, this invention adopts various intelligent algorithms such as time-frequency feature analysis algorithms, orthogonal fan array control algorithms and speckle strain detection algorithms. The organic combination of these algorithms not only improves the automation level of the process, but also significantly enhances the optimization ability and control precision of process parameters. Through the intelligent optimization and dynamic adjustment of the algorithms, the coordinated control of the temperature field, pressure field and stress field during the drying process is realized, ensuring the stability and consistency of product quality. At the same time, the application of these algorithms also greatly improves the energy utilization efficiency, shortens the production cycle and reduces the production cost. Description of the Drawings

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0015] Figure 1 It is a schematic diagram of an embodiment of the rapid setting and drying method of silicate materials in the embodiments of this application;

[0016] Figure 2Schematic flow chart of stress pre - regulation treatment of silicate raw materials, polypropylene fibers and nano - silica by three - dimensional network construction analysis in the embodiments of the present application;

[0017] Figure 3 Schematic diagram of an embodiment of the quick - setting drying device for silicate materials in the embodiments of the present application. Detailed implementation manners

[0018] The embodiments of the present application provide a quick - setting drying method and device for silicate materials. Terms such as "first", "second", "third", "fourth", etc. (if any) in the specification, claims and the above - mentioned drawings of the present application are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments described herein can be implemented in an order different from that shown or described herein. In addition, the terms "comprising" or "having" and any variation thereof are intended to cover non - exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily limit to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0019] For ease of understanding, the specific process of the embodiments of the present application is described below. Please refer to Figure 1 One embodiment of the quick - setting drying method for silicate materials in the embodiments of the present application includes:

[0020] Step S101: Perform stress pre - regulation treatment on silicate raw materials, polypropylene fibers and nano - silica by three - dimensional network construction analysis, and perform variable - frequency dual - axis stirring according to the shear stress monitoring data to obtain pre - regulated slurry;

[0021] Step S102: According to the pre - regulated slurry, use the partition pressure control system to perform gradient injection treatment on the core area, transition area and surface area, and obtain a silicate pre - form with an initial stress field through temperature gradient co - control;

[0022] Step S103: Collect acoustic emission signals of the silicate pre - form, dynamically evaluate the stress field distribution through the time - frequency feature analysis algorithm, and use the closed - loop feedback system to adjust the temperature and humidity parameters to obtain a pre - dried silicate part;

[0023] Step S104: According to the stress field distribution data of the pre - dried silicate part, dynamically optimize the air flow intensity and direction through the orthogonal fan array control algorithm to obtain an air - dried silicate part;

[0024] Step S105: Perform stress field scanning on the pneumatically dried silicate parts, and perform differential energy input processing on the high and low stress areas through a phased array microwave source to obtain microwave-dried silicate parts;

[0025] Step S106: Place the microwave-dried silicate parts in an ultrasonic stress relief system, and dynamically monitor the surface strain field through a speckle strain detection algorithm to obtain the target silicate product.

[0026] It can be understood that the execution subject of this application can be a quick-setting drying device for silicate materials, or a terminal or a server. Specifically, it is not limited here. In this embodiment of the application, the server is used as the execution subject for illustration.

[0027] Specifically, a three-dimensional network construction analysis system is used to perform stress pre-regulation on the raw materials. Specifically, stress distribution data of silicate raw materials, polypropylene fibers, and nano-silica are collected through a sensor array, and real-time monitoring values of shear stress are obtained by a network composed of strain gauges and pressure sensors. Based on these data, the rotation speed and direction of the biaxial stirring device are adjusted through a frequency converter to achieve uniform mixing of the materials. During the data processing process, the collected stress data is transformed into the frequency domain through Fourier transform, the main frequency components are extracted, and a stress-frequency relationship model is established to guide the dynamic adjustment of the stirring parameters.

[0028] After obtaining the pre-regulated slurry, the partition pressure control system performs gradient injection on different regions of the parts. This system includes multiple groups of independently controlled pressure pumps and temperature control units, and the pressure distributions in the core area, transition area, and surface area are monitored in real time through digital pressure sensors. The temperature gradient collaborative control uses multi-point temperature measurement elements and heater arrays, and dynamically adjusts the heating power according to the temperature feedback data of each region to ensure the uniformity of the temperature field. Subsequently, acoustic emission signal acquisition and analysis are performed, and a piezoelectric sensor array is used to detect the acoustic signals generated by the silicate prefabricated parts during the drying process. The time-frequency feature analysis algorithm performs wavelet transform on the collected acoustic emission signals, and extracts time-domain and frequency-domain feature parameters, including signal energy, main frequency, and frequency spectrum distribution, etc. By establishing the mapping relationship between the acoustic emission characteristics and the stress field distribution, the internal stress state of the prefabricated parts is evaluated. The closed-loop feedback system adjusts the environmental temperature and humidity parameters according to the evaluation results, and uses the PID control algorithm to achieve precise adjustment of the parameters.

[0029] After the pre-drying stage is completed, the orthogonal fan array control algorithm optimizes the airflow parameters. Based on the computational fluid dynamics model, the fan array is divided into multiple independent control regions, and the rotational speed of the fans and the angle of the deflector plates in each region can be adjusted individually. By establishing a correlation model between the airflow field distribution and the stress field, the operating parameters of the fans in each region are optimized to achieve precise control of the airflow intensity and direction. After the airflow drying is completed, the phased array microwave source performs differential energy input processing on the workpiece. A directional microwave field is generated by the microwave emission array. According to the stress field scan data, a lower power density is used for the high-stress regions and a higher power density is used for the low-stress regions to achieve spatial control of energy input. The distribution of microwave power is based on the stress field distribution data and the dielectric properties of the material, and directional transmission of energy is achieved through phase modulation.

[0030] In the ultrasonic stress relief system, the speckle strain detection algorithm is used to monitor the surface strain field. The displacement field information on the surface of the workpiece is obtained through laser speckle interferometry, and the strain distribution is calculated in combination with the digital image correlation algorithm. This algorithm preprocesses the speckle images, extracts the feature points, and calculates the strain field distribution by tracking the displacements of the feature points to achieve real-time evaluation of the stress state.

[0031] For example, in the actual production process, for the processing of a batch of silicate workpieces, the shear stress data of the raw materials are collected by strain gauges, and the spectral characteristics are obtained through Fourier transform to guide the dynamic adjustment of the rotational speed of the biaxial stirring device within the range of 50 - 200 rpm. In the partition injection stage, the pressure in the core area is maintained at 2.5 MPa, 2.0 MPa in the transition area, and 1.5 MPa in the surface layer area to form a reasonable pressure gradient. After the signals collected in the acoustic emission detection stage are wavelet-transformed, the characteristic signals with the main frequency components in the range of 20 - 100 kHz are extracted to evaluate the internal stress distribution. In the airflow drying stage, the fan array adjusts the wind speed within the range of 5 - 15 m / s according to the stress distribution data. The power density of the phased array microwave source is dynamically adjusted within the range of 0.5 - 2.0 kW / cm² to achieve differential energy input. Finally, the surface strain distribution is obtained through speckle strain detection, and the strain value is controlled within the range of 0.1% - 0.5% to ensure the product quality. In each process, the collection, processing, and feedback of data form a closed-loop control, ensuring the precise regulation of process parameters and the stability of product quality.

[0032] In the embodiments of the present application, through the design of stress pre-regulation treatment for silicate raw materials, polypropylene fibers and nano-silica by three-dimensional network construction analysis, precise stress control during the raw material mixing process is achieved, effectively avoiding the problem of uneven stress distribution in traditional mixing methods; through the design of gradient injection treatment for the core area, transition area and surface area using a partitioned pressure control system, a complete pressure gradient control system is established to ensure the uniformity of pressure distribution in each area of the workpiece; through the design of dynamically evaluating the stress field distribution using acoustic emission signal acquisition and time-frequency feature analysis algorithms, real-time monitoring and precise evaluation of the stress field distribution are realized, providing an accurate basis for subsequent process parameter adjustment; through the design of dynamically optimizing the air flow intensity and direction based on the orthogonal fan array control algorithm, precise regulation of the air flow field is achieved, improving the drying uniformity; through the design of differentially inputting energy to high and low stress areas using a phased array microwave source, precise control of energy input is realized, avoiding local overheating or underheating; through the design of combining ultrasonic stress elimination technology with speckle strain detection algorithms, precise elimination and real-time monitoring of the stress field are realized. Especially in the application of artificial intelligence algorithms, the present invention adopts a variety of intelligent algorithms such as time-frequency feature analysis algorithms, orthogonal fan array control algorithms and speckle strain detection algorithms. The organic combination of these algorithms not only improves the automation level of the process, but also significantly enhances the optimization ability and control accuracy of process parameters. Through the intelligent optimization and dynamic adjustment of the algorithms, coordinated control of the temperature field, pressure field and stress field during the drying process is achieved, ensuring the stability and consistency of product quality. At the same time, the application of these algorithms also greatly improves the energy utilization efficiency, shortens the production cycle and reduces the production cost.

[0033] In a specific embodiment, the process of executing step S101 may specifically include the following steps:

[0034] (1) Through a high-precision mass metering system, the silicate raw materials, polypropylene fibers and nano-silica are proportioned according to the mass fractions of 98.4%, 1.0% and 0.6% to obtain the standard material proportion data;

[0035] (2) Substitute the standard material proportion data into the three-dimensional network stress analysis equation, calculate the inter-particle forces of the mixture, and obtain the three-dimensional stress distribution data through response surface modeling to get the optimal proportion parameters;

[0036] (3) Based on the optimal proportion parameters, use a shear force sensing array to perform a 360-degree all-round dynamic scan of the mixture, collect stress data at 15 spatial points, and obtain a stress monitoring data set;

[0037] (4) Extract the time-domain features and frequency-domain features from the stress monitoring data set, establish a stress-time curve, and determine the key stress inflection points through wavelet analysis to obtain the stress peak feature vector;

[0038] (5) Construct a rotational speed optimization function based on the stress peak eigenvector, calculate the best rotational speed decline curve within the range of 150 - 80 revolutions per minute, and obtain a segmented rotational speed control sequence;

[0039] (6) Input the segmented rotational speed control sequence into the twin - shaft stirring system, collect the shear stress value every 0.5 seconds. When the shear stress of 30 consecutive sampling points is stable at 2.8 ± 0.2 MPa, a pre - regulated slurry is obtained.

[0040] Specifically, as Figure 2 shown, it is a schematic flow chart of stress pre - regulation treatment of silicate raw materials, polypropylene fibers, and nano - silica through three - dimensional network construction analysis in the embodiment of this application. The silicate raw materials (98.4%), polypropylene fibers (1.0%), and nano - silica (0.6%) are accurately proportioned through a high - precision mass metering system to generate standard proportioning data; the proportioning data is input into the three - dimensional network stress analysis equation, and the optimal proportioning parameters are obtained through particle force calculation and response surface modeling; a shear force sensing array is used to perform a 360 - degree dynamic scan at 15 spatial points, with a sampling frequency of 1 kHz; time - domain and frequency - domain feature extraction is performed on the collected stress monitoring data, and the key stress inflection points and peak eigenvectors are determined through wavelet analysis; a rotational speed optimization function is constructed based on the eigenvector within the range of 150 - 80 revolutions per minute, the best rotational speed decline curve is calculated, and a segmented rotational speed control sequence is generated; the control sequence is input into the twin - shaft stirring system, the shear stress value is collected every 0.5 seconds, and when the shear stress of 30 consecutive sampling points is stable within the set range, the preparation of the pre - regulated slurry is completed.

[0041] The raw materials are proportioned through a high - precision mass metering system. Specifically, the silicate raw materials, polypropylene fibers, and nano - silica are accurately weighed through an electronic balance and a microbalance, and the weighing data is input into the digital control unit to generate the standard proportioning data of the materials.

[0042] The material proportioning data is input into the three - dimensional network stress analysis equation for particle - to - particle force calculation. The three - dimensional network stress analysis equation is expressed as:

[0043] Wherein, is the three - dimensional stress tensor, representing the stress state of any point in the material; is the particle type weight coefficient, reflecting the contribution of different types of particles to the total stress; is the particle potential energy function, describing the mutual interaction potential energy between particles; is the Laplace operator, used to calculate the second - order spatial derivative of the potential energy; is the density correction factor, adjusting the influence of density distribution on stress; is the local density distribution function, describing the material density at each point in space; is the force vector, representing the interaction force between particles; is the time response coefficient, reflecting the dependence of stress on time; is the strain, representing the degree of deformation of the material. The integral term calculates the comprehensive effect of density and force within the entire volume. n is the total number of particle types, represents the region of volume integration, and t represents the time variable.

[0044] Based on the optimal ratio parameters, a 360-degree dynamic scan is performed using a shear force sensing array. The sensing array consists of 15 stress sensors, each with a sampling frequency of 1 kHz, and stress data at spatial points is collected in real time. The collected data is subjected to time-domain and frequency-domain feature extraction, and wavelet analysis is applied to determine the key stress inflection points:

[0045] Among them, is the wavelet transform coefficient, representing time-frequency domain features; a is the scale parameter, controlling the stretching of the wavelet; b is the translation parameter, controlling the translation of the wavelet; is the stress time-domain signal; is the wavelet basis function, used for signal decomposition; is the feature weight coefficient, adjusting the importance of different features; is the stress peak amplitude. The integral term realizes the time-frequency analysis of the signal, weights the feature peaks, is the number of feature peaks.

[0046] Construct a rotational speed optimization function based on the stress peak feature vector:

[0047]

[0048] Among them, is the function of rotational speed varying with time; is the maximum rotational speed value, setting the initial rotational speed of stirring; is the rotational speed decay coefficient, controlling the rate of rotational speed decrease; is the weight coefficient for each stage, adjusting the rotational speed change in different stages; is the time window function, defining the time range for each stage; is the shear stress increment, reflecting the influence of stress change on rotational speed. The exponential term describes the overall decay trend of rotational speed, and the summation term realizes segmented fine regulation, represents the total number of stages.

[0049] Taking the processing of a certain batch of silicate parts as an example, 9.84 kg of silicate raw materials, 0.10 kg of polypropylene fibers, and 0.06 kg of nano-silica were weighed respectively by a high-precision electronic balance. The material data was substituted into the three-dimensional network stress analysis equation, and the inter-particle forces of the mixture were iteratively calculated by the finite element method to obtain the spatial stress distribution data. Subsequently, a shear force sensing array was used for scanning. 15 sensors were distributed at different azimuth angles and elevation angles in the spherical coordinate system, and each sensor collected stress data every 1 ms. The collected data sequence was subjected to wavelet transform, the characteristic peak values were extracted, and a stress-time curve was established. Based on the curve characteristics, a rotational speed optimization function was constructed, and the optimal regulation sequence for the rotational speed gradually decreasing from 150 revolutions per minute to 80 revolutions per minute was calculated. The sequence was input into the biaxial stirring device, and the shear stress value was collected every 0.5 seconds. When the shear stress of 30 consecutive sampling points was stable within the range of 2.8 ± 0.2 MPa, the preparation of the pre-regulated slurry was completed.

[0050] In a specific embodiment, the process of executing step S102 may specifically include the following steps:

[0051] (1) The pre-regulated slurry was scanned in a 32×32 dot matrix by a pressure data acquisition array. According to the spatial spectral density analysis, the spatial distribution parameters of the pressure field were calculated, and the sampling data was three-dimensionally reconstructed by the stress field reconstruction algorithm to obtain a three-dimensional pressure distribution map;

[0052] (2) The three-dimensional pressure distribution map was imported into the intelligent pressure controller. Through multiple iterative regression calculations, the pressure control curve with the core area pressure set at 18 - 20 MPa, the transition area pressure set at 15 - 17 MPa, and the surface area pressure set at 12 - 14 MPa was obtained. The pressure gradient characteristics were extracted to obtain the zoning pressure optimization scheme;

[0053] (3) According to the zoning pressure optimization scheme, combined with the pressure-time response characteristics, a pressure control compensation function was established. 24 pressure sensing nodes were arranged in each of the three zones, the sampling period was 0.01 seconds, and a dynamic compensation matrix for pressure data was constructed to obtain real-time feedback data for pressure control;

[0054] (4) Based on the real-time feedback data for pressure control, through temperature-pressure coupling optimization calculations, the core area temperature was adjusted to 35 ± 0.2 °C, the transition area temperature was adjusted to 38 ± 0.2 °C, and the surface area temperature was adjusted to 40 ± 0.2 °C. A boundary characteristic curve for temperature zoning was established to obtain multi-region temperature regulation data;

[0055] (5) The multi-region temperature regulation data was subjected to time series reconstruction, the evolution characteristics of the temperature field were extracted, a self-adaptive optimization model for the boundary temperature gradient was established, and a temperature regulation optimization curve was constructed through temperature fluctuation variance analysis to obtain an intelligent temperature compensation sequence;

[0056] (6) Input the intelligent temperature compensation sequence into the temperature gradient controller. When the temperature stability indices of the core area, transition area, and surface area are greater than 0.98 and last for 180 seconds, and the pressure fluctuation coefficient is less than 0.02, a silicate preform with an initial stress field is obtained.

[0057] Specifically, perform a 32×32 dot matrix scan on the pre-regulated slurry. The pressure data acquisition array consists of 1024 micro pressure sensors, with the measurement range of each sensor being 0 - 50 MPa and the accuracy being 0.01 MPa. Calculate the pressure field distribution parameters through spatial spectral density analysis, and perform three-dimensional reconstruction on the sampled data using the stress field reconstruction algorithm. Spatial spectral density analysis extracts the spatial distribution characteristics of the pressure field by calculating the spatial correlation function and power spectral density of the pressure data.

[0058] The stress field reconstruction algorithm adopts a layer-by-layer iterative method to reconstruct the three-dimensional structure of the pressure field from the bottom layer to the top layer in sequence. In the reconstruction process, the least squares method is used to fit the sampled data, and the pressure values of the unsampled points are filled through the interpolation algorithm. Finally, a three-dimensional pressure distribution map with a resolution of 256×256×128 is generated. Based on this map, the pressure control curves of the three regions are determined through multiple iterative regression calculations. The regression calculation uses piecewise polynomial fitting to model the pressure change law of each region and extract the pressure gradient characteristics to form a zoning pressure optimization scheme. The pressure control compensation function is established based on the pressure-time response characteristics. 24 pressure sensing nodes are arranged in the core area, transition area, and surface area respectively, and the sampling period is 0.01 seconds. The sampled data is fitted in real time through the least squares method to construct a 72×72 dynamic compensation matrix for pressure data, realizing the real-time feedback of pressure control. Each element of the compensation matrix represents the pressure deviation value at the corresponding position and is used to dynamically adjust the pressure control parameters.

[0059] The temperature-pressure coupling optimization calculation is based on thermodynamics theory to establish a correlation model between temperature and pressure. The coupled equations are solved through the finite element method to obtain the optimal temperature zoning control strategy. When implementing temperature zoning control, the PID algorithm is used to precisely adjust the heating power to achieve stable temperature control. At the same time, a temperature zoning boundary characteristic curve is established to describe the temperature transition law between regions.

[0060] The time series reconstruction technology is used to analyze the dynamic evolution characteristics of the temperature field. The phase space of the temperature field is reconstructed using the delay coordinate method, and the stability of the temperature field is evaluated by calculating the correlation dimension and Lyapunov exponent. The boundary temperature gradient adaptive optimization model is based on fuzzy control theory, and the control parameters are dynamically adjusted according to the temperature fluctuation variance to generate an intelligent temperature compensation sequence.

[0061] Taking the preparation of a batch of silicate prefabricated parts as an example, the pressure data of the pre-regulated slurry is collected by 32×32 dot matrix scanning. After the sampled data is analyzed by spatial spectral density, the spatial distribution characteristics of the pressure field are obtained, and the three-dimensional pressure distribution map is reconstructed. Through multiple iterative regression, the pressure control curves of 18 - 20 MPa in the core area, 15 - 17 MPa in the transition area, and 12 - 14 MPa in the surface area are calculated. 72 pressure sensing nodes collect pressure data in real time, and a dynamic compensation matrix is constructed for pressure control. The temperature - pressure coupling optimization determines the temperature set values of the three regions, and the precise regulation of temperature is achieved through PID control. After 180 seconds of stable operation, when the temperature stability index in the core area, transition area, and surface area exceeds 0.98 and the pressure fluctuation coefficient is less than 0.02, the preparation of the silicate prefabricated parts with an initial stress field is completed. The whole process realizes the precise regulation of silicate materials through multi-level data acquisition, analysis, and control. The sampled data of each pressure sensor enters the data processing unit after analog-to-digital conversion. The spatial spectral density analysis calculates the autocorrelation function of the pressure data, and then the power spectral density is obtained through fast Fourier transform. The stress field reconstruction adopts a hierarchical iterative strategy. The reconstruction of each layer is based on the results of the previous layer. The pressure values of the sampling points are fitted by the least squares method, and the data of the unsampled points are filled by cubic spline interpolation. In the construction process of the pressure control compensation matrix, the weighted least squares method is used to fit the real-time sampled data, and the weight coefficient is dynamically adjusted according to the reliability of the measurement points. The dynamic evolution characteristics of the temperature field are extracted by calculating the autocorrelation function and cross-correlation function of the temperature sequence, which are used to evaluate the stability and uniformity of the temperature field. The whole data processing process forms a complete closed-loop control system, ensuring the accuracy and controllability of the silicate material preparation process.

[0062] In a specific embodiment, the process of executing step S103 may specifically include the following steps:

[0063] (1) Perform a 360-degree three-dimensional scan on the silicate prefabricated parts through an acoustic emission sensor array. 32 signal acquisition points are set on each scan plane, the sampling frequency is 500 kHz, and the amplitude, frequency, and duration characteristic parameters of the acoustic emission signal are extracted to obtain the original acoustic emission data set;

[0064] (2) Input the original acoustic emission data set into the feature analysis processor, establish the mapping relationship between the acoustic emission signal and the stress field through the stress wave propagation theory, extract the stress characteristic values of each sampling point, construct a three-dimensional stress distribution matrix, and obtain the time-domain characteristic data of the stress field;

[0065] (3) Perform spectral conversion on the time-domain characteristic data of the stress field, extract the main frequency components in the range of 0 - 100 kHz, establish the frequency-domain mapping function of the stress field, calculate the spatial distribution characteristics of the stress field, and obtain the dynamic evaluation parameters of the stress field;

[0066] (4) Based on the dynamic evaluation parameters of the stress field, construct a closed-loop control equation for temperature and humidity, adjust the drying chamber temperature in segments within the range of 40 - 75 °C, dynamically compensate the relative humidity within the range of 45% - 65%, establish a temperature and humidity response curve, and obtain optimized environmental parameter data;

[0067] (5) Conduct multi-dimensional analysis on the optimized environmental parameter data, extract the variation rules of the temperature and humidity fields, establish a parameter compensation strategy, determine the optimal regulation interval through temperature and humidity gradient calculation, and obtain a closed-loop control sequence;

[0068] (6) Substitute the closed-loop control sequence into the temperature and humidity regulation system. When the stress field fluctuation index is less than 0.03 within 180 seconds of continuous monitoring, the temperature field stability is greater than 0.95, and the relative humidity change rate is less than 0.02 / min, a pre-dried silicate workpiece is obtained.

[0069] Specifically, an acoustic emission sensor array performs a 360-degree three-dimensional scan on the silicate preform. The acoustic emission sensors are piezoelectric, with a frequency response range of 0 - 1 MHz and a sensitivity of -65 dB. 32 signal acquisition points are arranged on each scanning surface, with a sampling frequency of 500 kHz. The amplitude, frequency, and duration characteristic parameters of the acoustic emission signals are extracted to form an original acoustic emission data set. A mapping relationship between the acoustic emission signals and the stress field is established through the stress wave propagation theory. The propagation speed of stress waves in materials is related to the material elastic modulus and density. By measuring the time difference of the sound waves reaching different sensors and combining the acoustic wave attenuation characteristics, the sound source position and stress distribution are calculated. The stress characteristic values of each sampling point are extracted to construct a three-dimensional stress distribution matrix, and the time-domain characteristic data of the stress field are obtained.

[0070] Perform spectral conversion on the time-domain characteristic data of the stress field and extract the main frequency component to establish a frequency-domain mapping function of the stress field:

[0071]

[0072] Among them, is the frequency-domain distribution function of the stress field, is the frequency response function, is the attenuation coefficient, is the spatial position vector, is the sound source intensity, is the frequency characteristic function, is the material acoustic parameter, is the displacement field. The integral term represents the comprehensive contribution of the sound sources within the volume, represents the influence of the displacement field on the stress, is the total number of sound sources.

[0073] Based on the dynamic evaluation parameters of the stress field, a closed-loop control equation for temperature and humidity is constructed to perform segmented adjustment on the temperature and relative humidity in the drying chamber. The multi-dimensional analysis of the temperature and humidity field uses the following equation:

[0074]

[0075] Among them, is the temperature and humidity field control function, is the temperature diffusion coefficient, is the humidity transfer coefficient, is the temperature field, is the humidity field, is the adjustment factor, is the temperature and humidity coupling term, is the energy change amount. Describes the spatial distribution of the temperature field, Represents the time evolution of the humidity field, and the summation term Realizes the coordinated regulation of temperature and humidity, Represents the total number of adjustment factors.

[0076] Taking the pre-drying treatment of a batch of silicate prefabricated parts as an example, a 360-degree scan is performed through an acoustic emission sensor array. 32 sensors are annularly distributed on each scanning plane, with an interval angle of 11.25 degrees. The sampling frequency is 500 kHz, and the amplitude, frequency, and duration of the acoustic emission signal are recorded. Through the analysis of the stress wave propagation theory, the corresponding relationship between the acoustic emission signal and the stress field is established, and the stress distribution matrix is calculated. The fast Fourier transform is performed on the time-domain data to extract the main frequency components in the range of 0 - 100 kHz, and the frequency-domain mapping function is applied to evaluate the stress field distribution. Based on the evaluation results, the drying parameters are adjusted through the temperature and humidity closed-loop control equation. The temperature is adjusted in segments within the range of 40 - 75 °C, and the relative humidity is dynamically compensated within the range of 45% - 65%. After 180 seconds of stable operation, the stress field fluctuation index, temperature field stability, and relative humidity change rate are monitored to complete the preparation of the pre-dried silicate parts. When processing the acoustic emission signal, noise is removed through band-pass filtering, and the amplitude, frequency, and duration characteristics of the signal are extracted. The time difference of arrival of the stress wave is determined by the threshold triggering method, and the sound source position is calculated in combination with the propagation speed of the sound wave in the material. The spectrum analysis uses the fast Fourier transform, the window function selects the Hanning window, and the frequency resolution is 1 Hz. The temperature and humidity control uses the segmented PID algorithm, and the control parameters are dynamically adjusted according to different temperature intervals to achieve precise control of the temperature and humidity field.

[0077] In a specific embodiment, the process of executing step S104 may specifically include the following steps:

[0078] (1) Extract the surface stress distribution parameters from the stress field distribution data of the pre-dried silicate workpiece. Construct a stress distribution vector through eight-point stress sampling, perform piecewise linear interpolation on the stress values at each sampling point, and obtain a complete stress field distribution curve;

[0079] (2) Establish an orthogonal air flow control equation based on the complete stress field distribution curve. Divide the fan speeds in the up, down, left, and right directions into zones for regulation within the range of 0 - 5 m / s, perform collaborative optimization calculations on the air flow velocities in each zone, and obtain an air flow field intensity distribution table;

[0080] (3) Dynamically adjust the air flow directions of the orthogonal fan array according to the air flow field intensity distribution table. Collect air flow direction data every 0.1 seconds, calculate the air flow vectors in each direction through wind speed field reconstruction, and obtain air flow guiding parameters;

[0081] (4) Input the air flow guiding parameters into the wind field optimization processing unit, calculate the optimal air flow distribution plan according to the coupling relationship between the wind field and the stress field, perform progressive attenuation processing on the air flow intensity in the high-stress area, and obtain an air flow optimization control sequence;

[0082] (5) Calculate the fan speed compensation value based on the air flow optimization control sequence, adjust the speeds and air outlet angles of each fan, construct a local stress release channel, and perform a wind field uniformity evaluation every 1 second to obtain wind field regulation data;

[0083] (6) Substitute the wind field regulation data into the orthogonal fan control system. When it is detected that the air flow velocity fluctuation coefficients in all directions are less than 0.05 and the wind field uniformity index is greater than 0.92 within 300 consecutive seconds, obtain the air flow dried silicate workpiece.

[0084] Specifically, extract the surface stress distribution parameters from the stress field distribution data of the pre-dried silicate workpiece. Use the eight-point stress sampling method to evenly arrange 8 stress measurement points along the circumferential direction on the surface of the workpiece. Each measurement point collects local stress values through a high-precision strain gauge. The stress distribution vector consists of these 8 measurement values. Interpolation calculations are performed on the stress values between adjacent sampling points through the cubic spline interpolation algorithm to generate a 360-degree complete stress field distribution curve. The interpolation process uses piecewise cubic polynomials to ensure the continuity and smoothness of the curve. Establish an orthogonal air flow control equation based on the complete stress field distribution curve. Orthogonal air flow control involves the fans in the up, down, left, and right directions, and the fan speed range in each direction is 0 - 5 m / s. By establishing a correlation model between the air flow velocity and the stress distribution, collaborative optimization calculations are performed on the air flows in the four directions. The mutual interference effect of the air flows is considered in the optimization process, and the optimal speed combination of the fans in each direction is determined through iterative calculations to form an air flow field intensity distribution table.

[0085] The air flow field intensity distribution table is used to guide the dynamic adjustment of the orthogonal fan array. An air flow direction sensor with high-frequency sampling is used to collect air flow direction data every 0.1 seconds. Through the air flow field reconstruction algorithm, the sampled data is converted into an air flow vector field, and the air flow velocity and direction components in each direction are calculated. The air flow guiding parameters include characteristic quantities such as velocity magnitude, direction angle, and turbulence intensity. The air flow guiding parameters are input into the wind field optimization processing unit, and the optimal air flow distribution is calculated according to the coupling relationship between the wind field and the stress field. For areas with high stress, a progressive attenuation strategy is adopted to promote stress release by adjusting the local air flow intensity. The progressive attenuation process is realized through a piecewise function, ensuring a smooth transition of the air flow intensity. The finally generated air flow optimization control sequence contains the detailed operating parameters of each fan at different time periods.

[0086] Based on the air flow optimization control sequence, the rotational speed compensation values of each fan are calculated. The compensation calculation takes into account factors such as the fan characteristic curve, air flow resistance, and local pressure loss. By adjusting the fan rotational speed and the angle of the guide vane, a local stress release channel is formed in the high-stress area. The uniformity of the wind field is evaluated every 1 second, and the uniformity of the wind field is quantified by calculating the variance and mean ratio of the velocity field.

[0087] Taking the air flow drying of a batch of silicate prefabricated parts as an example, 8 stress measurement points are arranged on the surface of the parts, and local stress values are collected through strain gauges. The cubic spline interpolation algorithm is applied to expand 8 discrete data points into 360 data points to form a continuous stress distribution curve. According to the stress distribution characteristics, the rotational speed configurations of the four-direction fans are calculated. Through high-frequency sampling at 0.1-second intervals, the dynamic change data of the air flow field is obtained. The wind field optimization processing implements progressive air flow regulation for high-stress areas according to the stress-air flow coupling model. After 300 seconds of stable operation, when the air flow velocity fluctuation coefficients in each direction are detected to be less than 0.05 and the wind field uniformity index is greater than 0.92, the preparation of the air flow-dried silicate parts is completed. The entire process realizes precise control of the air flow drying process through multi-level data collection, analysis, and control.

[0088] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0089] (1) Perform a 24-point array stress field scan on the air flow-dried silicate parts, record the stress distribution according to the sampling interval of 0.01 seconds for the scanned data, and form a three-dimensional stress distribution map through spatial interpolation processing to obtain the stress field spatial data;

[0090] (2) Based on the stress field spatial data, divide the high and low stress areas, divide the stress values into two gradients: a high stress area of 2.5 - 3.0 MPa and a low stress area of 1.0 - 2.0 MPa, and conduct statistical analysis of the stress values in different stress areas to obtain the stress partition data;

[0091] (3) Perform energy distribution on the phased array microwave source based on the stress partition data, set the phase difference of 24 microwave sources within the range of 0 - 180 degrees, perform collaborative optimization calculation on the energy output of each microwave source, and obtain the microwave energy distribution sequence;

[0092] (4) Based on the microwave energy distribution sequence, input energy to the high stress area with a power of 2 kW / m³ and a pulse ratio of 2 s:3 s, and input energy to the low stress area with a power of 4 kW / m³ and a pulse ratio of 3 s:2 s, to obtain the energy input control parameters;

[0093] (5) Substitute the energy input control parameters into the microwave control system, collect energy absorption data every 0.5 seconds, calculate the spatial distribution characteristics of the energy field, and perform dynamic compensation on the energy input intensity to obtain the optimized data of the energy field;

[0094] (6) Evaluate the microwave energy uniformity of the optimized data of the energy field. When it is detected that the energy field volatility of each area is less than 0.03 and the energy uniformity index is greater than 0.95 within 240 consecutive seconds, obtain the microwave-dried silicate parts.

[0095] Specifically, perform stress detection on the air-dried silicate parts through a 24-point array stress field scanner. The stress field scanning uses 24 high-precision strain sensors, arranged in a 4×6 matrix, covering the surface of the parts. The sampling interval is set to 0.01 seconds, and each sensor records the local stress value in real time. Perform three-dimensional reconstruction on the discrete sampling point data through the Kriging spatial interpolation algorithm to generate a three-dimensional stress distribution map with a resolution of 100×100×50. For the three-dimensional stress distribution map, set the stress threshold for area division. Define the stress value of 2.5 - 3.0 MPa as the high stress area, and 1.0 - 2.0 MPa as the low stress area. Use the region growing algorithm to determine the boundary of the stress area, and fit the boundary curve by the least squares method. Perform statistical analysis on different stress areas, calculate the stress mean value, standard deviation and spatial distribution characteristics of each area, and form the stress partition data.

[0096] Based on the stress partition data, energy is allocated to 24 phased array microwave sources. The phased array microwave sources adopt the magnetron method, with a working frequency of 2.45 GHz, and achieve directional energy transmission through phase modulation. The phase difference of each microwave source is adjusted within the range of 0 - 180 degrees, and the phase difference is dynamically calculated by the moving average algorithm to achieve precise control of the energy field. The power configuration of each microwave source is optimized by the genetic algorithm to obtain a microwave energy distribution sequence. According to the energy distribution sequence, a differential energy input strategy is implemented for different stress regions. The high stress region adopts a pulse mode with a power of 2 kW / m³ and a transmission for 2 seconds and a pause for 3 seconds, while the low stress region adopts a pulse mode with a power of 4 kW / m³ and a transmission for 3 seconds and a pause for 2 seconds. Pulse control uses a precision timer with a time error of less than 1 millisecond. By real-time monitoring the change of the dielectric parameters of the material, the energy absorption efficiency is calculated.

[0097] During the energy input process, energy absorption data is collected every 0.5 seconds. An infrared temperature sensor array is used to monitor the surface temperature distribution, and combined with the measurement results of the dielectric parameters, the spatial distribution characteristics of the energy field are calculated. The energy input intensity is compensated in real-time through the proportional-integral control algorithm, and the compensation period is synchronized with the sampling period to ensure the uniformity of the energy field.

[0098] Taking the microwave drying of a batch of silicate parts as an example, stress distribution data is obtained through a 24-point stress field scan. After spatial interpolation processing, two high stress regions and three low stress regions are identified. The phased array microwave sources configure the power according to the stress partition. The 8 microwave sources in the high stress region adopt a low power pulse mode, and the 16 microwave sources in the low stress region adopt a high power pulse mode. Through real-time monitoring at 0.5-second intervals, energy absorption data is obtained and dynamically compensated. After 240 seconds of stable operation, when the energy field volatility of each region is detected to be less than 0.03 and the energy uniformity index is greater than 0.95, the preparation of the microwave-dried silicate parts is completed. The stress field scan data is filtered by median filtering to remove noise, and then a continuous stress distribution map is generated through the Kriging interpolation algorithm. The phase calculation of the phased array microwave source uses the moving average method, and the power optimization uses the genetic algorithm. The energy field uniformity evaluation uses the variance analysis method, and the uniformity degree is quantified by calculating the coefficient of variation of the energy density in each region.

[0099] In a specific embodiment, the process of executing step S106 may specifically include the following steps:

[0100] (1) Place the microwave-dried silicate parts in an ultrasonic stress elimination system, and perform three-dimensional scanning through an ultrasonic vibrator with a power of 0.5 - 1.0 W / cm² to collect surface strain data and obtain an original strain data set;

[0101] (2) Extract spatial speckle feature points from the original strain dataset, digitally process the speckle image through frequency modulation at 20 - 40 kHz, construct the spatial distribution matrix of the surface strain field, and obtain the speckle feature data;

[0102] (3) Conduct dynamic response analysis on the speckle feature data, record the changes in the strain field at a sampling interval of 0.02 seconds, establish the strain - time relationship curve, and obtain the surface strain evolution data;

[0103] (4) Based on the surface strain evolution data, input the ultrasonic energy in zones, partition the strain field at a gradient of 0.05%, calculate the energy compensation for different strain regions, and obtain the strain field control parameters;

[0104] (5) Precisely control the ultrasonic output through the strain field control parameters, evaluate the uniformity of the strain field every 1 second, calculate the surface strain distribution characteristics, and obtain the strain field optimization data;

[0105] (6) Input the strain field optimization data into the ultrasonic control system. When it is detected that the surface strain value is less than 0.01% and the strain field uniformity is greater than 0.98 within 360 consecutive seconds, the target silicate product is obtained.

[0106] Specifically, place the microwave - dried silicate workpiece in the ultrasonic stress relief system. Use an ultrasonic vibrator with a power of 0.5 - 1.0 W / cm² for three - dimensional scanning. The vibrator is made of piezoelectric ceramic material and has a working frequency of 20 - 40 kHz. The data acquisition system consists of a high - speed digital image processor and a CCD camera. Collect the surface speckle image through the charge - coupled device and record the strain data to form the original strain dataset. The process of extracting spatial speckle feature points from the original dataset uses the digital image correlation algorithm. Perform grayscale processing on the speckle image, use median filtering to eliminate noise, and then extract feature points through the corner detection algorithm. The feature point extraction uses the Harris corner detection method, calculates the gray - level gradient of the local area of the image, and determines the position of the feature points. The frequency modulation uses amplitude modulation, and the modulation frequency scans within the range of 20 - 40 kHz to achieve high - quality digital processing of the speckle image. According to the extracted feature point coordinates, construct the spatial distribution matrix of the surface strain field, with a matrix dimension of 1024×1024, and each unit records the strain value at the corresponding position.

[0107] When performing dynamic response analysis on speckle feature data, the sampling interval is set to 0.02 seconds. The time-series change data of the strain field is obtained through continuous sampling, and the least squares method is used to fit the strain-time data to establish a strain field evolution model. The model calculation takes into account the elastic properties of the material and the strain hysteresis effect, and the model parameters are optimized through iterative calculation to obtain the surface strain evolution data. Based on the surface strain evolution data, the ultrasonic energy is controlled by zone input. The strain field is divided into zones according to a gradient value of 0.05%, and the region growing algorithm is used to determine the boundaries of each strain zone. For different strain zones, an energy compensation model is established to calculate the required ultrasonic power. The compensation calculation takes into account the acoustic impedance characteristics of the material and the energy attenuation law, and the energy distribution equation is solved by numerical integration to obtain the strain field regulation parameters.

[0108] The strain field regulation parameters are used for the precise control of ultrasonic output. The control system uses the digital PID algorithm to adjust the ultrasonic power according to the real-time feedback strain data. The uniformity of the strain field is evaluated every 1 second, and the analysis of variance method is used to calculate the dispersion degree of the strain distribution. The evaluation results are used to optimize the control parameters. The strain field optimization data includes a power adjustment sequence and frequency modulation parameters for realizing the dynamic regulation of the strain field.

[0109] Taking the stress relief of a certain batch of silicate parts as an example, surface scanning is carried out through an ultrasonic vibrator. After the speckle images collected by the CCD camera are digitally processed, about 10,000 feature points are extracted. The initial strain field distribution is obtained by fitting the feature point data with the least squares method. Based on a gradient value of 0.05%, the strain field is divided into 5 zones, and the ultrasonic energy required for each zone is calculated respectively. Through real-time monitoring at 1-second intervals, the strain field change data is obtained and dynamically compensated. After 360 seconds of stable operation, when the detected surface strain value is less than 0.01% and the strain field uniformity is greater than 0.98, the preparation of the target silicate product is completed. The speckle images are preprocessed by grayscale conversion and filtering, and then the feature points are extracted by the Harris corner detection algorithm. The strain field evolution model is fitted by the least squares method, and the energy compensation calculation is carried out by numerical integration. The strain field uniformity evaluation uses the analysis of variance, and the coefficient of variation is calculated to quantify the degree of uniformity.

[0110] The above describes the rapid setting and drying method of the silicate material in the embodiment of the present application. Next, the rapid setting and drying device of the silicate material in the embodiment of the present application will be described. Please refer to Figure 3 An embodiment of the rapid setting and drying device of the silicate material in the embodiment of the present application includes:

[0111] The stirring module 201 is used to perform stress pre-regulation processing on silicate raw materials, polypropylene fibers, and nano-silica through three-dimensional network construction analysis, and perform variable-frequency biaxial stirring according to the shear stress monitoring data to obtain pre-regulated slurry;

[0112] The injection module 202 is used to perform gradient injection processing on the core area, transition area, and surface area according to the pre-regulated slurry by using a partition pressure control system, and obtain a silicate preform with an initial stress field through temperature gradient co-control;

[0113] The adjustment module 203 is used to collect acoustic emission signals of the silicate preform, dynamically evaluate the stress field distribution through a time-frequency feature analysis algorithm, and adjust the temperature and humidity parameters by using a closed-loop feedback system to obtain a pre-dried silicate workpiece;

[0114] The drying module 204 is used to dynamically optimize the air flow intensity and direction according to the stress field distribution data of the pre-dried silicate workpiece through an orthogonal fan array control algorithm to obtain an air-dried silicate workpiece;

[0115] The processing module 205 is used to scan the stress field of the air-dried silicate workpiece, and perform differential energy input processing on high and low stress regions through a phased array microwave source to obtain a microwave-dried silicate workpiece;

[0116] The monitoring module 206 is used to place the microwave-dried silicate workpiece in an ultrasonic stress elimination system, and dynamically monitor the surface strain field through a speckle strain detection algorithm to obtain a target silicate product.

[0117] Through the collaborative cooperation of the above-mentioned various components, the design of stress pre-regulation treatment for silicate raw materials, polypropylene fibers and nano-silica through three-dimensional network construction analysis realizes precise stress control during the raw material mixing process, effectively avoiding the problem of uneven stress distribution in traditional mixing methods; the design of gradient injection treatment for the core area, transition area and surface area using a partitioned pressure control system establishes a complete pressure gradient control system, ensuring the uniformity of pressure distribution in each area of the workpiece; the design of dynamically evaluating the stress field distribution using acoustic emission signal acquisition and time-frequency feature analysis algorithms realizes the real-time monitoring and precise evaluation of the stress field distribution, providing an accurate basis for subsequent process parameter adjustment; the design of dynamically optimizing the air flow intensity and direction based on the orthogonal fan array control algorithm realizes precise regulation of the air flow field and improves drying uniformity; the design of differential energy input treatment for high and low stress areas using a phased array microwave source realizes precise control of energy input and avoids local overheating or underheating phenomena; the design of combining ultrasonic stress elimination technology with speckle strain detection algorithm realizes precise elimination and real-time monitoring of the stress field. Especially in the application of artificial intelligence algorithms, the present invention adopts various intelligent algorithms such as time-frequency feature analysis algorithm, orthogonal fan array control algorithm and speckle strain detection algorithm. The organic combination of these algorithms not only improves the automation level of the process, but also significantly enhances the optimization ability and control accuracy of process parameters. Through the intelligent optimization and dynamic adjustment of the algorithms, the coordinated control of the temperature field, pressure field and stress field during the drying process is realized, ensuring the stability and consistency of product quality. At the same time, the application of these algorithms also greatly improves the energy utilization efficiency, shortens the production cycle and reduces the production cost.

[0118] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the foregoing method embodiments and will not be described herein again.

[0119] As described above, the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or equivalently replace some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for rapid coagulation and drying of silicate materials, characterized in that: The rapid coagulation and drying method of the silicate material comprises: The silicate raw materials, polypropylene fibers and nano-silicon dioxide are subjected to stress pre-regulation through three-dimensional network construction analysis, and variable frequency biaxial stirring is performed according to shear stress monitoring data to obtain pre-regulated slurry; According to the pre-adjusted slurry, the core area, transition area and surface area are subjected to gradient injection treatment by using a zoned pressure control system, and a silicate preform with an initial stress field is obtained by coordinated control of the temperature gradient; Acoustic emission signals are collected from the silicate preform, stress field distribution is dynamically evaluated by a time-frequency characteristic analysis algorithm, and temperature and humidity parameters are adjusted by a closed-loop feedback system to obtain a pre-dried silicate preform; According to the stress field distribution data of the pre-dried silicate product, the airflow intensity and direction are dynamically optimized by an orthogonal fan array control algorithm to obtain an airflow dried silicate product; Scanning the stress field of the airflow dried silicate product, and performing differentiated energy input processing on high and low stress areas through a phased array microwave source to obtain a microwave dried silicate product; The microwave dried silicate product is placed in an ultrasonic stress elimination system, and the surface strain field is dynamically monitored by a speckle strain detection algorithm to obtain a target silicate product.

2. The rapid coagulation and drying method of silicate materials according to claim 1, characterized in that: The method of performing stress pre-regulation on silicate raw materials, polypropylene fibers and nano-silicon dioxide through three-dimensional network construction analysis, and performing variable frequency biaxial stirring according to shear stress monitoring data to obtain pre-regulated slurry includes: The silicate raw material, polypropylene fiber and nano-silicon dioxide were proportioned according to the mass fractions of 98.4%, 1.0% and 0.6% by a high-precision mass measurement system to obtain the standard proportion data of the materials; Substituting the standard material ratio data into the three-dimensional network stress analysis equation, calculating the force between the mixture particles, obtaining the three-dimensional stress distribution data through response surface modeling, and obtaining the optimal ratio parameters; Based on the optimal ratio parameters, the mixture is dynamically scanned 360 degrees in all directions using a shear force sensor array to collect stress data of 15 spatial points to obtain a stress monitoring data set; Extracting time domain features and frequency domain features from the stress monitoring data set, establishing a stress-time curve, determining key stress inflection points through wavelet analysis, and obtaining a stress peak feature vector; A speed optimization function is constructed according to the stress peak characteristic vector, an optimal speed reduction curve is calculated in the range of 150-80 rpm, and a segmented speed control sequence is obtained; The segmented speed control sequence is input into the biaxial stirring system, and the shear stress value is collected every 0.5 seconds. When the shear stress of 30 consecutive sampling points is stabilized at 2.8±0.2 MPa, the pre-regulated slurry is obtained.

3. The rapid coagulation and drying method of silicate materials according to claim 1, characterized in that: The method comprises: performing gradient injection treatment on the core area, transition area and surface area by using a zoned pressure control system according to the pre-adjusted slurry, and obtaining a silicate preform with an initial stress field by coordinated control of the temperature gradient, including: The pre-controlled slurry is scanned with a 32×32 dot matrix through a pressure data acquisition array, the spatial distribution parameters of the pressure field are calculated based on the spatial spectrum density analysis, and the sampling data is reconstructed in three dimensions using a stress field reconstruction algorithm to obtain a three-dimensional pressure distribution map; The pressure distribution stereogram is imported into an intelligent pressure controller, and a pressure control curve is calculated by multiple iterative regression, with the pressure in the core area set at 18-20MPa, the pressure in the transition area set at 15-17MPa, and the pressure in the surface area set at 12-14MPa, and the pressure gradient characteristics are extracted to obtain a zone pressure optimization scheme; According to the partition pressure optimization scheme, combined with the pressure-time response characteristics, a pressure control compensation function is established, 24 pressure sensing nodes are arranged in the three partitions respectively, the sampling period is 0.01 seconds, and a pressure data dynamic compensation matrix is ​​constructed to obtain real-time feedback data of pressure control; Based on the real-time feedback data of the pressure control, the temperature of the core zone is adjusted to 35±0.2°C, the temperature of the transition zone is adjusted to 38±0.2°C, and the temperature of the surface zone is adjusted to 40±0.2°C through temperature-pressure coupling optimization calculation, and a temperature zone boundary characteristic curve is established to obtain multi-zone temperature control data; Reconstructing the time series of the multi-region temperature control data, extracting the temperature field evolution characteristics, establishing a boundary temperature gradient adaptive optimization model, constructing a temperature control optimization curve through temperature fluctuation variance analysis, and obtaining an intelligent temperature compensation sequence; The intelligent temperature compensation sequence is input into the temperature gradient controller, and when the temperature stability index of the core zone, transition zone and surface zone is greater than 0.98 and lasts for 180 seconds, and the pressure fluctuation coefficient is less than 0.02, the silicate preform with the initial stress field is obtained.

4. The rapid coagulation and drying method of silicate materials according to claim 1, characterized in that: The method collects acoustic emission signals from the silicate preform, dynamically evaluates the stress field distribution by using a time-frequency characteristic analysis algorithm, and adjusts the temperature and humidity parameters by using a closed-loop feedback system to obtain a pre-dried silicate preform, including: The silicate preform was scanned 360 degrees by an acoustic emission sensor array. 32 signal collection points were set on each scanning surface with a sampling frequency of 500 kHz. The amplitude, frequency, and duration characteristic parameters of the acoustic emission signal were extracted to obtain the original acoustic emission data set. The acoustic emission raw data set is input into a feature analysis processor, a mapping relationship between the acoustic emission signal and the stress field is established through stress wave propagation theory, the stress characteristic value of each sampling point is extracted, a three-dimensional stress distribution matrix is ​​constructed, and time-domain characteristic data of the stress field is obtained; Performing spectrum conversion on the stress field time domain characteristic data, extracting the main frequency components in the range of 0-100kHz, establishing the stress field frequency domain mapping function, calculating the stress field spatial distribution characteristics, and obtaining the stress field dynamic evaluation parameters; Based on the stress field dynamic evaluation parameters, a temperature and humidity closed-loop control equation is constructed, the drying chamber temperature is segmentedly adjusted within the range of 40-75°C, the relative humidity is dynamically compensated within the range of 45%-65%, a temperature and humidity response curve is established, and environmental parameter optimization data is obtained; Perform multi-dimensional analysis on the environmental parameter optimization data, extract the variation law of temperature and humidity field, establish parameter compensation strategy, determine the optimal control range through temperature and humidity gradient calculation, and obtain a closed-loop control sequence; Substitute the closed-loop control sequence into the temperature and humidity adjustment system, and when the stress field fluctuation index is less than 0.03, the temperature field stability is greater than 0.95, and the relative humidity change rate is less than 0.02 / min within 180 seconds of continuous monitoring, the pre-dried silicate product is obtained.

5. The rapid coagulation and drying method of silicate materials according to claim 1, characterized in that: The method of dynamically optimizing the airflow intensity and direction according to the stress field distribution data of the pre-dried silicate product by using an orthogonal fan array control algorithm to obtain an airflow dried silicate product includes: Surface stress distribution parameters are extracted from the stress field distribution data of pre-dried silicate parts, stress distribution vectors are constructed through eight-point stress sampling, and the stress values ​​at each sampling point are piecewise linearly interpolated to obtain a complete stress field distribution curve. An orthogonal airflow control equation is established based on the complete stress field distribution curve, the fan speeds in the four directions of up, down, left and right are regulated in a zone within the range of 0-5 m / s, and the airflow speed in each zone is collaboratively optimized to obtain an airflow field intensity distribution table; The airflow direction of the orthogonal fan array is dynamically adjusted according to the airflow field intensity distribution table, the airflow direction data is collected every 0.1 seconds, and the airflow vectors in each direction are calculated by wind speed field reconstruction to obtain airflow guidance parameters; The airflow guiding parameters are input into the wind field optimization processing unit, the optimal airflow distribution scheme is calculated according to the coupling relationship between the wind field and the stress field, the airflow intensity in the high stress area is progressively attenuated, and an airflow optimization control sequence is obtained; Based on the airflow optimization control sequence, the fan speed compensation value is calculated, the speed and air outlet angle of each fan are adjusted, a local stress release channel is constructed, and the wind field uniformity is evaluated every 1 second to obtain wind field control data; The wind field control data is substituted into an orthogonal fan control system, and when it is detected that the airflow velocity fluctuation coefficient in each direction is less than 0.05 and the wind field uniformity index is greater than 0.92 for 300 consecutive seconds, the airflow dried silicate product is obtained.

6. The rapid coagulation and drying method of silicate materials according to claim 1, characterized in that: The stress field of the airflow dried silicate product is scanned, and the high and low stress regions are subjected to differentiated energy input processing by a phased array microwave source to obtain a microwave dried silicate product, including: The airflow dried silicate parts were scanned with 24-point array stress field, and the stress distribution of the scanned data was recorded at a sampling interval of 0.01 seconds. A three-dimensional stress distribution map was formed through spatial interpolation processing to obtain stress field spatial data. Based on the stress field spatial data, the boundaries of high and low stress areas are divided, and the stress values ​​are divided into two gradients: 2.5-3.0 MPa in the high stress area and 1.0-2.0 MPa in the low stress area. The stress values ​​of different stress areas are statistically analyzed to obtain stress partition data; The energy of the phased array microwave source is distributed by using the stress partition data, the phase difference of the 24 microwave sources is set within the range of 0-180 degrees, and the energy output of each microwave source is collaboratively optimized to obtain a microwave energy distribution sequence; Based on the microwave energy distribution sequence, a power of 2 kW / m³ and a pulse ratio of 2s:3s are used for energy input to the high stress area, and a power of 4 kW / m³ and a pulse ratio of 3s:2s are used for energy input to the low stress area, and energy input control parameters are obtained; Substituting the energy input control parameters into the microwave control system, collecting energy absorption data every 0.5 seconds, calculating the spatial distribution characteristics of the energy field, dynamically compensating the energy input intensity, and obtaining energy field optimization data; The microwave energy uniformity evaluation is performed on the energy field optimization data. When it is detected that the energy field fluctuation rate in each region is less than 0.03 and the energy uniformity index is greater than 0.95 for 240 consecutive seconds, the microwave dried silicate product is obtained.

7. The rapid coagulation and drying method of silicate materials according to claim 1, characterized in that: The microwave dried silicate product is placed in an ultrasonic stress relief system, and the surface strain field is dynamically monitored by a speckle strain detection algorithm to obtain a target silicate product, including: The microwave-dried silicate product is placed in an ultrasonic stress relief system, and three-dimensional scanning is performed using an ultrasonic exciter with a power of 0.5-1.0W / cm² to collect surface strain data and obtain an original strain data set; Extracting spatial speckle feature points from the original strain data set, digitally processing the speckle image through 20-40 kHz frequency modulation, constructing a surface strain field spatial distribution matrix, and obtaining speckle feature data; Performing dynamic response analysis on the speckle feature data, recording the strain field changes at a sampling interval of 0.02 seconds, establishing a strain-time relationship curve, and obtaining surface strain evolution data; Based on the surface strain evolution data, ultrasonic energy is input into partitions, the strain field is partitioned according to a gradient of 0.05%, energy compensation calculations are performed on different strain areas, and strain field control parameters are obtained; The ultrasonic output is precisely controlled by the strain field control parameters, the strain field uniformity is evaluated every 1 second, the surface strain distribution characteristics are calculated, and the strain field optimization data is obtained; The strain field optimization data is input into an ultrasonic control system, and when it is detected that the surface strain value is less than 0.01% and the strain field uniformity is greater than 0.98 for 360 consecutive seconds, the target silicate product is obtained.

8. A rapid coagulation and drying device for silicate materials, used to implement the rapid coagulation and drying method for silicate materials as claimed in any one of claims 1 to 7, characterized in that: The quick-setting and drying device for silicate materials comprises: A stirring module is used to perform stress pre-regulation on silicate raw materials, polypropylene fibers and nano-silicon dioxide through three-dimensional network construction analysis, and to perform variable frequency biaxial stirring according to shear stress monitoring data to obtain pre-regulated slurry; The injection module is used to perform gradient injection treatment on the core area, transition area and surface area according to the pre-adjusted slurry using a zoned pressure control system, and obtain a silicate preform with an initial stress field through coordinated control of the temperature gradient; An adjustment module is used to collect acoustic emission signals from the silicate preform, dynamically evaluate the stress field distribution through a time-frequency characteristic analysis algorithm, and adjust the temperature and humidity parameters using a closed-loop feedback system to obtain a pre-dried silicate preform; A drying module, used for dynamically optimizing the airflow intensity and direction through an orthogonal fan array control algorithm according to the stress field distribution data of the pre-dried silicate product to obtain an airflow dried silicate product; A processing module, used for scanning the stress field of the airflow dried silicate product, and performing differentiated energy input processing on high and low stress areas through a phased array microwave source to obtain a microwave dried silicate product; The monitoring module is used to place the microwave-dried silicate product in an ultrasonic stress relief system, and dynamically monitor the surface strain field through a speckle strain detection algorithm to obtain a target silicate product.

Images