A digital visual control system and method for a synthetic mica material production line

Abstract

The present application relates to the technical field of industrial production line control, and in particular to a digital visual control system and method for a synthetic mica material production line. The method comprises the following steps: obtaining mica material industrial data, and extracting a data feature vector to obtain a batch quality coefficient, temperature-pressure fitting data, and lattice distortion data; expanding the temperature-pressure fitting data along the kiln direction as the horizontal coordinate, and taking the lattice distortion data as the axis coordinate, and outputting a mica material defect distribution map in combination with the batch quality coefficient; therefore, the present application solves the key technical problems of difficult accurate control of process parameters, large product quality fluctuations, and high defect rates in the traditional mica material production process by constructing a multi-dimensional data fusion digital visual control system, and improves the production efficiency, product quality stability, and process control intelligence level.

Description

Technical Field

[0001] This invention relates to the field of industrial production line control technology, and in particular to a digital visualization control system and method for a synthetic mica material production line. Background Technology

[0002] Existing methods can only independently monitor kiln temperature, pressure, and crystal growth parameters (such as thermocouple gradients and pressure spectra), but lack correlation modeling between thermal data (axial temperature gradients and pressure pulsation spectra) and intrinsic material properties (lattice distortion and birefringence). In particular, they cannot construct a defect distribution model through the spatial mapping relationship between temperature-pressure fitting data and lattice distortion, making it difficult to locate key issues such as abnormal cold zone density (>15% threshold) and pinhole defects (probability >30%). Traditional methods require manually preset static density difference thresholds (e.g., nucleus density deviation >15%) and defect probability thresholds (e.g., pinhole defects >30%), but dynamic disturbances in actual production (e.g., fluctuations in raw material fluorine content and kiln thermal inertia) result in poor adaptability of fixed thresholds. Identification of suspended nuclei in crystalline phase regions relies on manual interpretation, and no quantitative correlation rules have been established between melt viscosity distribution maps (based on fluorine content-labeled nucleus data) and production line defects (e.g., triggering defect labeling when reaction rate <0.8 and viscosity standard deviation >50 Pa·s). Summary of the Invention

[0003] Therefore, it is necessary to provide a digital visualization control system and method for a synthetic mica material production line to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above objectives, a digital visualization control method for a synthetic mica material production line is provided, the method comprising the following steps:

[0005] Step S1: Obtain industrial data of mica materials and extract data feature vectors to obtain batch quality coefficients, temperature-pressure fitting data and lattice distortion data;

[0006] Step S2: Using the temperature-pressure fitting data along the kiln direction as the abscissa and the lattice distortion data as the axial coordinate, and combining the batch quality coefficient, output the mica material defect distribution map;

[0007] Step S3: Determine the cold temperature zone based on the mica material defect distribution map. If the density difference of the cold temperature zone is greater than the preset density difference threshold, perform axial temperature compensation to obtain the temperature compensation area. Calculate the pinhole probability based on the mica material defect distribution map. If the pinhole defect probability is greater than the preset defect probability threshold, perform fluorine compensation to obtain the fluorine compensation area.

[0008] Step S4: Obtain the actual mica crystal growth image; overlay the temperature compensation region and fluorine compensation region according to the current timestamp, and perform similarity matching with the actual mica crystal growth image to display a full-process visualization of mica materials and generate a full-process report of mica materials.

[0009] Step S5: Generate control instructions for the mica material production line based on the mica material full-process report, and perform full-process control on the mica material production line according to the control instructions.

[0010] This specification provides an information interaction control system for a vital signs monitor, used to execute the aforementioned information interaction control method based on the vital signs monitor. The information interaction control system for the vital signs monitor includes:

[0011] The data acquisition and feature construction module is used to acquire industrial data of mica materials and extract data feature vectors to obtain batch quality coefficients, temperature-pressure fitting data and lattice distortion data.

[0012] The defect modeling and probability analysis module is used to output a defect distribution map of mica material by unfolding temperature-pressure fitting data along the kiln direction as the horizontal axis and lattice distortion data as the axial axis, and combining the batch quality coefficient.

[0013] The defect compensation strategy generation module is used to determine the cold temperature zone based on the defect distribution map of mica material. If the density difference of the cold temperature zone is greater than the preset density difference threshold, axial temperature compensation is performed to obtain the temperature compensation area. The module also calculates the pinhole probability based on the defect distribution map of mica material. If the pinhole defect probability is greater than the preset defect probability threshold, fluorine compensation is performed to obtain the fluorine compensation area.

[0014] The visualization and report generation module is used to acquire actual mica crystal growth images; temperature compensation regions and fluorine compensation regions are superimposed according to the current timestamp, and similarity matching is performed with the actual mica crystal growth images to display a full-process visualization of mica materials and generate a full-process report of mica materials.

[0015] The control instruction module is used to generate control instructions for the mica material production line based on the full-process report of mica materials, and to perform full-process control of the mica material production line according to the control instructions.

[0016] The beneficial effects of this invention are as follows: By real-time acquisition of axial temperature gradient data (range 0.88-0.95°C / cm) and pressure pulsation spectrum data (range 0.32-0.41kPa) of six temperature zones in the kiln, a temperature-pressure fitting model was established, which effectively identified the cold temperature zone phenomenon in temperature zones three and four in the middle section of the kiln. The crystal nucleus density deviation reached negative 15%. After raising the temperature of this area by 2.3 degrees Celsius through the axial temperature compensation strategy, the uniformity of crystal nucleus density was improved by 22%, and the product quality coefficient was improved from 0.82 to 0.86.

[0017] Statistical analysis of twenty production batches showed a clear positive correlation between mica nucleus density and batch quality coefficient. When the nucleus density was maintained within the optimized range of 90-100 nuclei per meter, the batch quality coefficient remained stable above 0.85, and the product qualification rate reached over 95%. Defect probability analysis data indicated that the pinhole defect probability in temperature zone four under the traditional production mode was as high as 35%. After precisely adjusting the fluorine content by 0.024 percentage points using a fluorine compensation strategy, the pinhole defect probability decreased to 12%, the microcrack defect probability decreased from 28% to 8%, and the overall defect rate decreased from 31% to 18%.

[0018] Viscosity distribution data of mica melt shows that precise viscosity control along the kiln axis can be achieved, reducing the viscosity standard deviation from 75 Pa·s in traditional processes to 45 Pa·s, and improving viscosity distribution uniformity by 40%. This ensures the stability and consistency of the crystal growth process, ultimately resulting in a significant improvement in the precision of automated production line control and stable optimization of product quality. Therefore, this invention solves the key technical problems of difficult precise control of process parameters, large fluctuations in product quality, and high defect rates in traditional mica material production by constructing a multi-dimensional data fusion digital visualization control system, thereby improving production efficiency, product quality stability, and the level of intelligent process control. Attached Figure Description

[0019] Figure 1 This is a flowchart illustrating the steps of a digital visualization control method for a synthetic mica material production line.

[0020] Figure 2 This is a schematic diagram of the axial temperature gradient distribution in the kiln.

[0021] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] The technical method of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this invention.

[0023] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0024] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0025] To achieve the above objectives, please refer to Figures 1 to 2 A digital visualization control method for a synthetic mica material production line, the method comprising the following steps:

[0026] In this embodiment of the invention, reference is made to Figure 1 The diagram shown is a flowchart illustrating the steps of a digital visualization control method for a synthetic mica material production line according to the present invention. In this example, the digital visualization control method for a synthetic mica material production line includes the following steps:

[0027] Step S1: Obtain industrial data of mica materials and extract data feature vectors to obtain batch quality coefficients, temperature-pressure fitting data and lattice distortion data;

[0028] Preferably, step S1 includes the following steps:

[0029] Acquire industrial data for mica materials, including raw material feature vectors, thermal tensor data, and intrinsic crystal growth properties; the thermal tensor data includes the axial temperature gradients of thermocouples in six temperature zones and the pressure pulsation spectrum of pressure transmitters.

[0030] The batch quality coefficient is obtained by encoding the feature vector of raw materials with fluorine content as a benchmark.

[0031] Wavelet fusion is performed on the axial temperature gradient and pressure pulsation spectrum of the thermal tensor data to output temperature-pressure fitting data.

[0032] By analyzing the biaxial interference of the intrinsic eigenvalues ​​of crystal growth, lattice distortion data can be obtained.

[0033] In this embodiment of the invention, a raw material feature vector is obtained, including percentage content data of silicon dioxide, aluminum oxide, potassium oxide and fluorine, forming a four-dimensional chemical composition vector; thermal tensor data is collected, specifically including axial temperature gradient values ​​measured by six temperature zone thermocouple sensors arranged along the longitudinal axis of the kiln and pressure pulsation spectrum information detected by a pressure transmitter; in addition, intrinsic crystal growth data is also required, mainly lattice structure parameters obtained by X-ray diffraction detection.

[0034] In the data processing stage, a batch quality coding algorithm is established using fluorine content as a benchmark reference value. The batch quality coefficient is obtained by calculating the weighted deviation of each chemical component relative to the standard ratio. For thermal data processing, wavelet fusion technology is used to decompose and reconstruct the axial temperature gradient data of the six temperature zones with the corresponding pressure pulsation spectrum main frequency amplitude at multiple scales, generating a set of fitting parameters describing the temperature-pressure coupling relationship. In terms of lattice distortion analysis, the extraordinary refractive index and ordinary refractive index data are extracted by analyzing the biaxial interference phenomenon during crystal growth. The birefringence compensation is calculated by combining the crystal thickness information, and then quantitative lattice distortion characteristic data are obtained through optical path simulation.

[0035] In one implementation of this invention, assuming the raw material feature vector shows that the silicon dioxide content is 45.2%, the aluminum oxide content is 35.8%, the potassium oxide content is 10.5%, and the fluorine content is 4.3%, the batch quality coefficient is calculated to be 0.83 based on the standard fluorine content of 4.5%.

[0036] The axial temperature gradients measured by thermocouples in the six temperature zones are 0.88, 0.92, 0.95, 0.89, 0.85, and 0.91, respectively.

[0037] For every centimeter in Celsius, the corresponding pressure pulsation spectrum integral values ​​are 0.32, 0.38, 0.41, 0.35, 0.33, and 0.39 kPa.

[0038] After wavelet fusion processing, the output temperature and pressure fitting data are a fifth-order polynomial coefficient set; simultaneously, X-ray diffraction analysis shows that the crystal thickness is 120 micrometers, the extraordinary refractive index is 1.6012, and the ordinary refractive index is 1.5935. The birefringence compensation formula is then used. The calculated compensation amount was 0.924 micrometers, and the final lattice distortion data for this batch was obtained by optical path difference simulation as 0.25%.

[0039] Preferably, the biaxial interference of wavelet fusion and analysis of crystal growth eigenvalues ​​based on the axial temperature gradient and pressure pulsation spectrum of the thermal tensor data includes:

[0040] Six temperature zone acquisition points were set along the longitudinal axis of the kiln, and envelope extraction was performed on the six temperature zone acquisition points to obtain the axial temperature gradient; the pressure spectrum energy of the kiln was integrated by signal amplitude to obtain the pressure pulsation spectrum;

[0041] The axial temperature gradient and pressure pulsation spectrum are fused using wavelet fusing and sorted according to temperature-pressure to obtain temperature-pressure fitting data;

[0042] The thickness of the mica crystal was obtained; the extraordinary and ordinary refractive indices were extracted from the intrinsic properties of crystal growth, and the birefringence compensation data were calculated using the biaxial interference analytical formula, which is as follows:

[0043] ;

[0044] Where Δδ represents the birefringence compensation amount. It is a very high refractive index. d is the ordinary refractive index, and d is the thickness of the mica crystal. The birefringence of mica;

[0045] The optical path is simulated using birefringence compensation data, and the lattice distortion data is obtained by compensating for the difference based on the simulated optical path.

[0046] Please see Figure 2 The red line represents the axial temperature gradient; the blue line represents the pressure pulsation spectrum; and the blue line shows the distribution of the axial temperature gradient and pressure pulsation spectrum collected from six temperature zones within the kiln.

[0047] In one implementation of this invention, wavelet fusion uses the db4 wavelet basis for 5-level decomposition, extracts low-frequency coefficients to reconstruct the fused signal, and then arranges the data points in ascending order of temperature value, using a cubic polynomial to generate temperature-pressure fitting parameters.

[0048] In one implementation of this invention, the strain conversion coefficient is determined through a material calibration experiment.

[0049] In one implementation of this invention, it is assumed that the temperature envelope derivative... °C / cm, pressure spectrum integral kPa.

[0050] Wavelet fusion fitting coefficients .

[0051] Crystal thickness μm, at position (50, 50) ,theory ,

[0052] Calculated m.

[0053] Optical path difference simulation results Corresponding lattice distortion ( .

[0054] Step S2: Using the temperature-pressure fitting data along the kiln direction as the abscissa and the lattice distortion data as the axial coordinate, and combining the batch quality coefficient, output the mica material defect distribution map;

[0055] Preferably, step S2 includes the following steps:

[0056] Step S21: Construct a spatial mica evolution coordinate system by unfolding the temperature-pressure fitting data along the kiln direction as the abscissa and using the lattice distortion data as the axial coordinate;

[0057] Step S22: Locate the crystal phase region of the spatial mica evolution coordinate system, identify the suspended mica crystal nuclei in the crystal phase region, and generate mica crystal nuclei identification data; mark the mica crystal nuclei identification data according to the fluorine content, and thus output the mica melt viscosity distribution map;

[0058] Step S23: Based on the batch quality coefficient, find the production line defects in the mica melt viscosity distribution map to obtain the mica material defect distribution map.

[0059] In this embodiment of the invention, the temperature-pressure fitting data (usually containing polynomial coefficients or key fitting values) corresponding to each temperature zone is used as the representative value of that temperature zone at the axial position of the kiln (e.g., temperature zone 1 at 0-5 meters, temperature zone 2 at 5-10 meters, etc.), thereby establishing a horizontal axis (X-axis) covering the entire length of the kiln; at the same time, the lattice distortion data (such as average distortion rate or key point distortion) associated with the corresponding position or batch is used as the vertical axis (Y-axis), thereby constructing a two-dimensional coordinate system, where each data point represents the correlation between the process state (temperature-pressure fitting result) and the material structure state (lattice distortion) of a certain axial position (or temperature zone) of the kiln.

[0060] In this coordinate system, a threshold range (e.g., Y value between 0.1% and 0.3%) is set based on lattice distortion data (Y value) to define specific "crystal phase regions." These regions represent kiln locations where crystal structure characteristics conform to specific growth stages. Then, image analysis or pattern recognition algorithms (such as connected component analysis and feature point detection) are used to process the original crystal image data or interference data corresponding to these crystal phase regions, identifying tiny crystal nuclei exhibiting suspended, independent growth characteristics in the image. The position coordinates (X value in the coordinate system) of each identified crystal nucleus are output. Characteristic parameters (such as size and profile strength) are used as "mica nucleus identification data". Next, based on the fluorine content (scalar value or spatial distribution value) in the raw material data of the production batch, these identified nucleus data points are labeled with fluorine content (e.g., high fluorine area, low fluorine area). Finally, based on the material rheology model, the viscosity estimate of the mica melt at that location is calculated using the nucleus distribution density (e.g., the number of nuclei per unit axial length) labeled with fluorine content and the characteristic parameters, thereby generating a distribution map showing the viscosity variation of the melt at different locations along the kiln axis.

[0061] Using the batch quality coefficient (a comprehensive quality score Q, for example, in the range of 0-1) as a reference benchmark, regions on the generated viscosity distribution map where the viscosity values ​​significantly deviate from the expected range (e.g., too high viscosity leads to poor flowability, or too low viscosity leads to instability) are located. These deviation regions are identified as potential "production line defects". Combining the original lattice distortion data (Y value) and crystal nucleus distribution information at that location, a "mica material defect distribution map" is finally output, which integrates the kiln location, process status (temperature-pressure fitting), material structure status (lattice distortion), melt status (viscosity anomaly), and defect markers.

[0062] In one implementation of this invention, it is assumed that a 30-meter kiln is divided into 6 5-meter temperature zones (X-axis: temperature zone 1 = 0-5m, temperature zone 2 = 5-10m, ..., temperature zone 6 = 25-30m).

[0063] The temperature-pressure fitting value for temperature zone 4 (X=15-20m) is 0.75 (representing a specific process state), and its corresponding lattice distortion data is Y=0.22%.

[0064] The region with a lattice distortion Y value between 0.2% and 0.25% (including most of temperature zone 4 and parts of temperatures 3 and 5) was identified as the critical crystalline phase region. In the crystal image of temperature zone 4 (around X=17m), five suspended nuclei (average diameter 10μm) were identified, and the fluorine content in this region was marked as "moderate" (4.0%). Based on the nucleus density and fluorine content, the average melt viscosity of temperature zone 4 was calculated to be 1200 Pa·s.

[0065] The batch quality coefficient Q=0.85 (good). The viscosity distribution map revealed that temperature zone 2 (X=5-10m) had a viscosity as high as 1800 Pa·s (significantly higher than the normal range of 1200±200 Pa·s), and the lattice distortion Y=0.35% in this region was also high. Therefore, on the final defect distribution map, temperature zone 2 was clearly marked as a "high viscosity defect region," while temperature zone 4 was marked as a "normal region."

[0066] Preferably, step S23 includes the following steps:

[0067] Based on the viscosity distribution map of mica melt, the reaction rate and viscosity standard deviation were extracted to obtain mica reaction rate data and viscosity standard deviation data.

[0068] Obtain a historical defect database; perform cross-correlation processing on the mica melt viscosity distribution map based on the mica fluorine content of the batch quality coefficient; when the mica reaction rate data is less than 0.8 and the viscosity standard deviation data is greater than 50 Pa·s, use the historical defect database to mark production defects and obtain mica production line marking data.

[0069] Based on the statistical defect probability of mica production line marking data, when the defect rate of a single production line in the mica production line marking data is greater than 0.2, a defect distribution map of mica material is constructed.

[0070] In this embodiment of the invention, two key data points are extracted from the generated mica melt viscosity distribution map (the map uses the axial position of the kiln as the horizontal axis and the viscosity value of each point as the vertical axis):

[0071] 1) Mica reaction rate data: Calculate the rate of change of viscosity along the kiln axis (production flow direction), that is, the average slope of viscosity change between adjacent points (for example, if the viscosity at point A is 1200 Pa·s and the viscosity at point B (1 meter downstream) is 1100 Pa·s, then this rate is -100 Pa·s / m).

[0072] 2) Viscosity standard deviation data: Calculate the magnitude of the fluctuation (dispersion) of the viscosity value at all locations within the entire kiln or a specific section (such as each temperature zone) relative to its average value, and obtain a statistical value (unit: Pa·s). Next, obtain the historical defect database (this database stores the actual defect types and locations recorded in past production batches under different fluorine contents and different viscosity characteristics).

[0073] Based on the fluorine content level implied by the batch quality factor of the current batch (e.g., a quality factor Q=0.85 corresponds to a fluorine content of approximately 4.2%), historical records with similar fluorine content are selected from the historical database. Cross-correlation processing is then performed.

[0074] Compare and analyze the viscosity profile characteristics of the current batch (especially the newly extracted reaction rate and viscosity standard deviation) with the selected historical data.

[0075] Define clear judgment rules: If the reaction rate data (average change slope) of the current batch is less than 0.8 Pa·s / m (meaning that the viscosity change is too gradual and the reaction may be insufficient) and the viscosity standard deviation data is greater than 50 Pa·s (meaning that the viscosity fluctuates drastically in space and the process is unstable), then based on the frequently occurring defect types (such as "bubble aggregation" and "grain coarsening") with similar viscosity characteristics in the matched historical data, mark these potential production defects at the corresponding positions on the current viscosity distribution map, and generate mica production line marking data containing defect type and location (data structure: location coordinates + defect type label).

[0076] Finally, based on this marking data, the proportion of the number of locations marked as defects in the entire production line or key monitoring section is calculated to obtain the defect rate of a single production line. If this defect rate is greater than 0.2 (i.e., 20% of the locations are marked as problematic), a mica material defect distribution map is triggered (this map will integrate key information such as location, viscosity, marked defect type, and lattice distortion from previous steps).

[0077] In one implementation of this invention, it is assumed that the viscosity distribution map of the current batch of mica melt shows that 60 points (one point every 0.5 meters) were measured along a 30-meter kiln. The calculation yields:

[0078] The reaction rate data (average slope) is 0.65 Pa·s / m (less than the threshold of 0.8).

[0079] Viscosity standard deviation data = 55 Pa·s (greater than the threshold of 50 Pa·s)

[0080] The current batch has a quality coefficient Q=0.86, suggesting a fluorine content of approximately 4.3%. Historical database searches revealed that previous batches with a fluorine content of 4.2%-4.4% that simultaneously met the criteria of "rate <0.8 & standard deviation >50" frequently exhibited "micro-cracks" in the middle section (10-20 meters) of the kiln.

[0081] Therefore, the system marks data points within the 10-20 meter range of the current viscosity distribution map as "microcrack risk," generating production line marking data. Of the 60 points throughout the kiln, 15 points (concentrated in the 10-20 meter range) are marked, resulting in a defect rate of 15 / 60 = 0.25 (greater than the threshold of 0.2). Consequently, a detailed mica material defect distribution map is constructed and output, clearly indicating the 10-20 meter range as a "high-risk microcrack zone," and overlaying the viscosity anomalies and lattice distortion data for this region.

[0082] Step S3: Determine the cold temperature zone based on the mica material defect distribution map. If the density difference of the cold temperature zone is greater than the preset density difference threshold, perform axial temperature compensation to obtain the temperature compensation area. Calculate the pinhole probability based on the mica material defect distribution map. If the pinhole defect probability is greater than the preset defect probability threshold, perform fluorine compensation to obtain the fluorine compensation area.

[0083] Preferably, step S3 includes the following steps:

[0084] The deviation of the longitudinal mica nucleus density is calculated based on the mica material defect distribution map. If the nucleus density deviation is greater than 15% of the preset density difference threshold, temperature compensation is performed using the axial temperature compensation formula to obtain the temperature compensation area.

[0085] The quality coefficient of the current batch is extracted based on the defect distribution map of mica material. If the probability of pinhole defects in the quality coefficient of the current batch is greater than the preset defect probability threshold of 30%, a new formula is set based on the new fluorine content formula setting formula to obtain the fluorine compensation area.

[0086] Preferably, the axial temperature compensation formula and the new fluorine content formulation setting formula include: ;

[0087] in, For axial temperature compensation, Let be the start and end times of the integration time interval. For density deviation function, The difference in mica crystal nuclei density;

[0088] ;

[0089] in, Data set for the new fluoride content formulation. This represents the quality coefficient for the current batch.

[0090] In this embodiment of the invention, based on the mica material defect distribution map (which contains information on different axial positions of the kiln, including lattice distortion, defect markers, and key crystal nucleus density data), the actual mica crystal nucleus density (e.g., the number of crystal nuclei per meter) at each axial position (or small area) is calculated.

[0091] Using the average nucleus density of the entire kiln as a benchmark, the relative percentage deviation between the actual nucleus density at each location and this average value is calculated (i.e., (local density - average density) / average density × 100%). A preset density difference threshold (15%) is set. If the absolute value of the calculated nucleus density deviation at a certain location (or continuous area) is greater than 15% (i.e., there are significantly too many or too few nuclei at that location), it is determined that there is a problem with uneven temperature distribution in that area. For these areas exceeding the standard, the axial temperature compensation formula (the formula is...) is used. Use this to calculate the required temperature adjustment. This refers to the nucleus density deviation value calculated at that location (e.g., -20%). It is a function that determines the compensation strength based on the magnitude of the density deviation (the specific form is determined by the process, for example...). =k (where k is a coefficient) t2 represents the time interval during which the material in this area remains in this section of the kiln.

[0092] Integrating this function over the residence time interval yields the final temperature compensation. (Unit: degrees Celsius). This allows for precise definition of the temperature compensation zone requiring temperature adjustment (e.g., a range marked as X meters to Y meters within a kiln that needs heating or cooling). The quality coefficient of the current batch can be directly extracted from the batch information associated with the same defect distribution map. (This is a comprehensive quality score, for example, ranging from 0.8 to 1.0).

[0093] Based on the defect type data marked on the defect distribution map, the proportion of pinhole defects in the entire batch is calculated to obtain the pinhole defect probability of the current batch. A preset defect probability threshold (30%) is set. If the calculated pinhole defect probability is greater than 30%, the fluorine content is determined to be the main cause.

[0094] The formula for setting the new fluorine content formulation is as follows (the formula is...) This is used to calculate the adjustment amount for the fluoride content. Here, This refers to the extracted quality coefficient of the current batch (e.g., 0.82), calculated using a formula. This refers to the amount (usually a percentage) that needs to be increased from the existing fluorine content in the formula. This determines the fluorine compensation zone where the raw material formula needs adjustment (typically referring to the entire batch of raw materials where the fluorine content needs to be increased). .

[0095] In one implementation of this invention, the density deviation function The residence time of the material in the kiln section (e.g., 5 minutes).

[0096] In one implementation of this invention, it is assumed that the following is obtained from the analysis of the defect distribution map:

[0097] The nucleus density in a certain area of ​​the kiln (located between 10 and 12 meters) is 85 nuclei / meter, while the average nucleus density for the entire kiln is 100 nuclei / meter. This is a deviation in nucleus density. =(85-100) / 100×100%=-15%. Absolute value| |=15%, equal to the threshold of 15% (usually, a value greater than or equal to the threshold triggers the event; we assume it triggers here). Assume the material residence time in this area is t2-t1=5 minutes. Defined as =0.1 (That is, every 1% negative deviation requires a compensation of -0.1℃ per minute).

[0098] Temperature compensation Therefore, the temperature compensation zone was determined to be the 10-meter to 12-meter section of the kiln, requiring a temperature reduction of 7.5℃.

[0099] The current batch quality coefficient K_batch¹ = 0.82. Defect distribution statistics show that 25 out of 60 monitoring points in the entire kiln are marked as "pinhole defects". The probability of pinhole defects is approximately 25 / 60 ≈ 41.7% (greater than the threshold of 30%).

[0100] Formula for setting fluoride content in formulations: 0.2 × |0.82 - 1| = 0.2 × 0.18 = +0.036%.

[0101] Therefore, the fluorine compensation zone refers to the batch of raw material formulation that requires an increase of 0.036% in fluorine content (e.g., from the original 4.500% to 4.536%).

[0102] Step S4: Obtain the actual mica crystal growth image; overlay the temperature compensation region and fluorine compensation region according to the current timestamp, and perform similarity matching with the actual mica crystal growth image to display a full-process visualization of mica materials and generate a full-process report of mica materials.

[0103] Preferably, step S4 includes:

[0104] Step S41: Obtain actual mica crystal growth images;

[0105] Step S42: Overlay the temperature compensation region and the fluorine compensation region according to the current timestamp to obtain the predicted thermal map of mica crystal nucleus density;

[0106] Step S43: Perform similarity matching between the predicted thermal map of mica crystal nucleus density and the actual mica crystal growth image. If the spatial similarity is greater than 0.9, display the full-process visualization graphics of mica materials and construct a full-process report of mica materials.

[0107] In this embodiment of the invention, a high-resolution industrial camera installed in the kiln observation window or growth chamber captures a digital image (usually a grayscale or RGB pixel matrix with a resolution of 1920x1080) of the mica crystal growth process at the current moment (accurately recorded timestamp, such as 2023-07-25T14:30:25.120Z) in real time. This image is the "actual mica crystal growth image", which intuitively reflects the true state of crystal morphology and crystal nucleus distribution at that moment.

[0108] Extract the "temperature compensation zone" (e.g., the kiln axial position range [12.5m, 14.5m] requires cooling) and "fluorine compensation zone" (e.g., the fluorine content of the entire batch needs to be increased by +0.036%) calculated from previous steps (such as S3 or S5). The key operation is:

[0109] 1) Spatial mapping: The physical coordinates (kiln meters) of the temperature compensation area are converted into pixel coordinate areas on the image (e.g., [500px, 580px]) according to a preset correspondence (e.g., 1 meter = 40 pixels).

[0110] 2) Effect modeling: based on fluorine compensation amount ( Using known models of the effect of fluorine content on the nucleus formation rate (e.g., increased fluorine promotes nucleation), the possible spatial variation of nucleus density under this compensation (especially in the temperature-compensated region) is predicted.

[0111] 3) Heatmap generation: Combining the location of the mapped temperature compensation region and the prediction of the fluorine compensation effect, a "mica crystal nucleus density prediction heatmap" is generated on the image coordinate system.

[0112] The mica nucleus density prediction heatmap is essentially a two-dimensional matrix (the same size as the image). The value of each pixel in the matrix represents the predicted nucleus density level at that location (e.g., a range of 0-1, with higher values ​​indicating denser nuclei). It is usually visualized using a color gradient (e.g., blue-yellow-red), with red areas indicating high predicted density.

[0113] The generated predicted heatmap (prediction matrix) is compared with the actual growth image (real pixel matrix) obtained in step S41. Specifically:

[0114] 1) Image preprocessing: This may convert the actual image into a binary image or gradient image that highlights the features of the crystal nucleus;

[0115] 2) Similarity Calculation: The similarity between the predicted heatmap matrix and the actual image processed matrix is ​​calculated spatially (i.e., by pixel location). For example, the correlation coefficient of pixel values ​​or the proportion of overlapping area in the overlapping region (especially the temperature compensation region) of the two images is calculated to obtain a quantified "spatial similarity" score (range 0-1). Judgment Rule: If the calculated spatial similarity score is greater than a preset high threshold (0.9), it indicates that the predicted crystal nucleus distribution (based on the compensation scheme) highly matches the actual observation, the compensation scheme is effective, and the process state is consistent with expectations.

[0116] The system integrates currently captured actual images, overlaid predicted heat maps, temperature / fluorine compensation zone markers, batch parameters (quality coefficient, fluorine content, etc.), and historical feature data to generate a "mica material full-process visualization graphic" containing key data and visualization elements for the operator to see. It also automatically outputs a structured "mica material full-process report" which includes timestamps, compensation parameters, similarity values, key quality indicators, etc.

[0117] In one implementation of this invention, an actual crystal growth image (resolution 1920x1080) is captured at timestamp 2023-07-25T14:30:25.120Z.

[0118] Temperature compensation region: Physical location [10.0m, 12.0m] -> mapped to the horizontal pixel range of the image [400px, 480px] (assuming 1m = 40px). Fluorine compensation region: Fluorine content increases by +0.036% (predicted to promote crystal nucleation). Predicted thermogram: Within the pixel range [400, 480], based on the fluorine compensation effect model, it is predicted that the crystal nucleus density in this region will be 20% higher than the surrounding area, generating a thermogram (e.g., displayed as a yellow to red transition in the [400, 480] range).

[0119] The actual image was processed to identify the location of the crystal nuclei and generate a density distribution map. The overlap ratio between the predicted heatmap (predicted high density in the [400,480] region) and the actual crystal nucleus density map in the [400,480] region was calculated: 85% of the predicted high-density region actually showed high-density crystal nuclei in the actual image, and the spatial similarity was calculated to be 0.92 (greater than the threshold of 0.9). Result: Matching was successful. The system displays a visualization: the background is the actual growth image, with a red prediction box (temperature compensation area) overlaid in the [400,480] pixel range, and the predicted density distribution (which basically overlaps with the actual high-density crystal nucleus area) is represented by semi-transparent heatmap color blocks. Full process report record: timestamp 14:30:25.120Z, temperature compensation range [10.0m,12.0m] (pixels [400,480]), fluorine compensation +0.036%, similarity 0.92, current batch Q value 0.83.

[0120] Preferably, step S43 includes:

[0121] Step S431: Perform similarity matching between the predicted mica nucleus density heat map and the actual mica crystal growth image. If the spatial similarity is greater than 0.9, extract the pixels from the heat map to obtain the mica nucleus pixels. Extract the isosurface based on the isovalues ​​of the mica nucleus pixels to obtain the mica heat map vector data.

[0122] Step S432: Mark the same isosurfaces based on the mica thermal map vector data to obtain a visualization graphic of the mica material;

[0123] Step S433: Perform affine transformations on the visualized graphics of mica materials and trace the entire production line process to obtain a full-process report on mica materials.

[0124] In this embodiment of the invention, when the spatial similarity between the predicted heatmap and the actual crystal growth image is determined to be greater than 0.9 (high match), the following operations are performed: Pixel data is extracted from the predicted heatmap. The predicted heatmap is essentially a two-dimensional matrix with the same size as the image (e.g., 1920x1080), where the value of each pixel represents the predicted nucleus density level at that location (e.g., 0.0 to 1.0). All pixels with values ​​higher than a specific threshold (e.g., 0.7) are selected; these points are considered to be predicted high nucleus density regions and are called "mica nucleus pixels." Next, isosurface extraction is performed on these discrete "mica nucleus pixels": image processing algorithms (such as Marching Squares or its variants) are used to find continuous contour lines (contour lines) formed by all points with equal predicted density values. Connecting these contour lines outlines the predicted boundaries of high-density, medium-density, and low-density crystal nuclei. Storing these boundary data (polygons or curves composed of point coordinate sequences) in a structured vector format (such as SVG path data or a list of coordinate points) results in "mica heat map vector data".

[0125] These vector data are used to annotate the visualization: the extracted isosurfaces (i.e., the outlines of different predicted density regions) are overlaid on the original image of the actual mica crystal growth. Typically, different density levels are distinguished by lines of different colors or semi-transparent blocks (e.g., areas surrounded by red outlines represent predicted high-density areas, and blue represents low-density areas), thus generating a "mica material visualization" that visually compares the predicted nucleus distribution areas with the actual growth image.

[0126] To enable end-to-end traceability, the system performs an affine transformation on the visualization: based on the known mapping relationship between the kiln coordinate system and the image pixel coordinate system (such as scaling, translation, and rotation parameters), the pixel coordinates in the image (e.g., the coordinates of contour points in a high-density area) are precisely converted back to the corresponding physical kiln location coordinates (in meters). Then, based on these physical location coordinates, the entire production process is traced back: the system automatically associates and extracts relevant data generated at that location in all previous steps (S1, S2, S3…), such as the original temperature and pressure data at that location, calculated lattice distortion values, viscosity values, whether it was marked as a defect, compensation decision information, raw material batch information, etc.

[0127] By integrating all this traceability data and current visualizations, a structured "Mica Material Full-Process Report" is generated. This report not only includes the final graphics but also details the key process parameters, calculated indicators, decision points, and results affecting crystal growth in the region, organized by physical location or time series, providing complete production history traceability.

[0128] In one implementation of this invention, a similarity of 0.92 > 0.9 triggers subsequent operations. In the predicted heatmap, pixel (420, 300) has a value of 0.85, (430, 310) has a value of 0.82, ... (all are high-density points). A density threshold of 0.7 is set, and all pixels with values ​​>= 0.7 are extracted (e.g., a total of 5000 points). Isosurface extraction: The algorithm finds a closed contour line A (vector data: point sequence [(400, 280), (405, 285), ..., (450, 310), ..., (400, 280)]) that encloses all high-density points (value ≈ 0.8) with pixel coordinates approximately in the range of (400-450, 280-320).

[0129] On the original actual growth image, outline A is drawn with red lines to circle the predicted high nucleus density region. A visualization is generated: the background is an actual crystal photograph, overlaid with the red outline of the predicted high-density region.

[0130] Affine transformation: Given the mapping relationship X(meter) = 0.025 u (pixels), Y (meters) = 0.025 v (pixels). The point (420, 300) on contour line A is transformed into a physical location (10.5 meters, 7.5 meters). Production line traceability: The system locates the kiln at 10.5 meters (belonging to temperature zone 3): Backtracking S1: Temperature gradient at this location = 0.92℃ / cm, pressure spectrum integral = 0.38kPa, lattice distortion = 0.22%. Backtracking S2 / S3: Melt viscosity at this location = 1150Pa·s, not marked as a defect. Backtracking compensation decision: This area belongs to the temperature compensation zone (requires a 2.5℃ temperature reduction), fluorine compensation +0.036%. Report generation: The full-process report includes: Visualized graphics (actual images with predicted contours). Key traceability data (location 10.5m): S1 features: T_grad=0.92, P_f=0.38, ε=0.22% S2 / S3 status: Viscosity=1150Pa·s, NoDefect S3 compensation: ΔT=-2.5℃, ΔF=+0.036% Global information such as timestamp, batch ID, quality coefficient (Q=0.83), similarity (0.92).

[0131] Therefore, the embodiments should be considered as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0132] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A digital visualization control method for a synthetic mica material production line, characterized in that, Includes the following steps: Step S1: Obtain industrial data of mica materials and extract data feature vectors to obtain batch quality coefficients, temperature-pressure fitting data and lattice distortion data; Step S1 includes: Acquire industrial data for mica materials, including raw material feature vectors, thermal tensor data, and intrinsic crystal growth properties; the thermal tensor data includes the axial temperature gradients of thermocouples in six temperature zones and the pressure pulsation spectrum of pressure transmitters. The batch quality coefficient is obtained by encoding the feature vector of raw materials with fluorine content as a benchmark. Wavelet fusion is performed on the axial temperature gradient and pressure pulsation spectrum of the thermal tensor data to output temperature-pressure fitting data. By analyzing the biaxial interference of crystal growth eigenvalues, lattice distortion data can be obtained. Step S2: Using the temperature-pressure fitting data along the kiln direction as the abscissa and the lattice distortion data as the axial coordinate, and combining the batch quality coefficient, output the mica material defect distribution map; Step S2 includes the following steps: Step S21: Construct a spatial mica evolution coordinate system by unfolding the temperature-pressure fitting data along the kiln direction as the abscissa and using the lattice distortion data as the axial coordinate; Step S22: Locate the crystal phase region of the spatial mica evolution coordinate system, identify the suspended mica crystal nuclei in the crystal phase region, and generate mica crystal nuclei identification data; mark the mica crystal nuclei identification data according to the fluorine content, and thus output the mica melt viscosity distribution map; Step S23: Based on the batch quality coefficient, find the production line defects in the mica melt viscosity distribution map to obtain the mica material defect distribution map; Step S23 includes: Based on the viscosity distribution map of mica melt, the reaction rate and viscosity standard deviation were extracted to obtain mica reaction rate data and viscosity standard deviation data. Obtain a historical defect database; perform cross-correlation processing on the mica melt viscosity distribution map based on the mica fluorine content of the batch quality coefficient; when the mica reaction rate data is less than 0.8 and the viscosity standard deviation data is greater than 50 Pa·s, use the historical defect database to mark production defects and obtain mica production line marking data. Based on the mica production line marking data, the defect probability is statistically analyzed. When the defect rate of a single production line in the mica production line marking data is greater than 0.2, a mica material defect distribution map is constructed. Step S3: Based on the mica material defect distribution map, the cold temperature zone is determined. If the density difference of the cold temperature zone is greater than the preset density difference threshold, axial temperature compensation is performed to obtain the temperature compensation area. Based on the mica material defect distribution map, the pinhole probability is statistically analyzed. If the pinhole defect probability is greater than the preset defect probability threshold, fluorine compensation is performed to obtain the fluorine compensation area. Step S4: Obtain the actual mica crystal growth image; overlay the temperature compensation region and fluorine compensation region according to the current timestamp, and perform similarity matching with the actual mica crystal growth image to display a full-process visualization of mica materials and generate a full-process report of mica materials. Step S5: Generate control instructions for the mica material production line based on the mica material full-process report, and perform full-process control on the mica material production line according to the control instructions.

2. The digital visualization control method for a synthetic mica material production line as described in claim 1, characterized in that, The biaxial interference of wavelet fusion and analysis of crystal growth eigenvalues ​​based on the axial temperature gradient and pressure pulsation spectrum of thermal tensor data includes: Six temperature zone acquisition points were set along the longitudinal axis of the kiln, and envelope extraction was performed on the six temperature zone acquisition points to obtain the axial temperature gradient; the pressure spectrum energy of the kiln was integrated by signal amplitude to obtain the pressure pulsation spectrum; The axial temperature gradient and pressure pulsation spectrum are fused using wavelet fusing and sorted according to temperature-pressure to obtain temperature-pressure fitting data; The thickness of the mica crystal was obtained; the extraordinary and ordinary refractive indices were extracted from the intrinsic properties of crystal growth, and the birefringence compensation data were calculated using the biaxial interference analytical formula, which is as follows: ； Where Δδ represents the birefringence compensation amount. It is a very high refractive index. d is the ordinary refractive index, and d is the thickness of the mica crystal. The birefringence of mica; The optical path is simulated using birefringence compensation data, and the lattice distortion data is obtained by compensating for the difference based on the simulated optical path.

3. The digital visualization control method for a synthetic mica material production line as described in claim 1, characterized in that, Step S3 includes: The deviation of the longitudinal mica nucleus density is calculated based on the mica material defect distribution map. If the nucleus density deviation is greater than 15% of the preset density difference threshold, temperature compensation is performed using the axial temperature compensation formula to obtain the temperature compensation area. The quality coefficient of the current batch is extracted based on the defect distribution map of mica material. If the probability of pinhole defects in the quality coefficient of the current batch is greater than the preset defect probability threshold of 30%, a new formula is set based on the new fluorine content formula setting formula to obtain the fluorine compensation area.

4. The digital visualization control method for a synthetic mica material production line as described in claim 1, characterized in that, The axial temperature compensation formula and the formula for setting the new fluorine content formula include: ; in, For axial temperature compensation, , Let be the start and end times of the integration time interval. For density deviation function, The difference in mica crystal nuclei density; ； in, Data set for the new fluoride content formulation. This represents the quality coefficient for the current batch.

5. The digital visualization control method for a synthetic mica material production line as described in claim 1, characterized in that, Step S4 includes: Step S41: Obtain actual mica crystal growth images; Step S42: Overlay the temperature compensation region and the fluorine compensation region according to the current timestamp to obtain the predicted thermal map of mica crystal nucleus density; Step S43: Perform similarity matching between the predicted thermal map of mica crystal nucleus density and the actual mica crystal growth image. If the spatial similarity is greater than 0.9, display the full-process visualization graphics of mica materials and construct a full-process report of mica materials.

6. The digital visualization control method for a synthetic mica material production line as described in claim 5, characterized in that, Step S43 includes: Step S431: Perform similarity matching between the predicted mica nucleus density heat map and the actual mica crystal growth image. If the spatial similarity is greater than 0.9, extract the pixels from the heat map to obtain the mica nucleus pixels. Extract the isosurface based on the isovalues ​​of the mica nucleus pixels to obtain the mica heat map vector data. Step S432: Mark the same isosurfaces based on the mica thermal map vector data to obtain a visualization graphic of the mica material; Step S433: Perform affine transformations on the visualized graphics of mica materials and trace the entire production line process to obtain a full-process report on mica materials.

7. A digital visualization control system for a synthetic mica material production line, characterized in that, The method for implementing the digital visualization control method for a synthetic mica material production line as described in claim 1 includes: The data acquisition and feature construction module is used to acquire industrial data of mica materials and extract data feature vectors to obtain batch quality coefficients, temperature-pressure fitting data and lattice distortion data. The defect modeling and probability analysis module is used to output a defect distribution map of mica material by unfolding temperature-pressure fitting data along the kiln direction as the horizontal axis and lattice distortion data as the axial axis, and combining the batch quality coefficient. The defect compensation strategy generation module is used to determine the cold temperature zone based on the defect distribution map of mica material. If the density difference of the cold temperature zone is greater than the preset density difference threshold, axial temperature compensation is performed to obtain the temperature compensation area. The module also calculates the pinhole probability based on the defect distribution map of mica material. If the pinhole defect probability is greater than the preset defect probability threshold, fluorine compensation is performed to obtain the fluorine compensation area. The visualization and report generation module is used to acquire actual mica crystal growth images; temperature compensation regions and fluorine compensation regions are superimposed according to the current timestamp, and similarity matching is performed with the actual mica crystal growth images to display a full-process visualization of mica materials and generate a full-process report of mica materials. The control instruction module is used to generate control instructions for the mica material production line based on the full-process report of mica materials, and to perform full-process control of the mica material production line according to the control instructions.

Images