A quartz crucible melting machine melting intelligent control system

Abstract

The present application relates to the technical field of quartz crucible manufacturing, and specifically discloses a quartz crucible melting machine melting intelligent control system, which comprises a precision correction module, a preheating and temperature rising module, a melting and heat soaking module and a clarification constant temperature module. The precision correction module cross- verifies the predicted temperature based on the arc length and power through a dual-color temperature measuring instrument, so as to realize online calibration of the temperature measuring equipment; the preheating and temperature rising module monitors the quartz sand surface temperature rising rate and dynamically controls it; the melting and heat soaking module adopts the polar coordinate grid method to arrange points, judges the heating uniformity of the melt, and identifies local hot spots, local cold spots or overall mode problems, so as to provide clear basis for intervention; the clarification constant temperature module monitors the temperature curve in real time, identifies the fluctuation mode and traces the causes. The present application realizes intelligent temperature control of the whole process, improves the temperature measuring precision, the melt uniformity and the finished product quality, and is suitable for the quartz crucible melting production environment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of quartz crucible manufacturing, and relates to a quartz crucible melting machine intelligent control system. BACKGROUND

[0002] As a key basic material in the fields of semiconductors, photovoltaics, etc., the quality of quartz crucibles directly affects the performance and yield of downstream products. The melting process of quartz crucibles is the most core and precise link in the entire production process, and especially the temperature control in the melting stage has a decisive influence on the purity, uniformity and structural integrity of the final product.

[0003] At present, there are still obvious deficiencies in the temperature control during the melting process of quartz crucibles: first, the temperature measurement means is single, and it is mostly dependent on single-point or single-waveband temperature measurement equipment, which is easily disturbed by factors such as observation window pollution, target shielding and distance change, resulting in large temperature measurement error, and lacking effective cross-validation mechanism, it is difficult to guarantee the reliability of the data.

[0004] Secondly, the existing control system often focuses on temperature regulation in a certain stage, lacks the ability of dynamic tracking and intelligent regulation and control from preheating, melting to clarification, and is difficult to realize accurate judgment and real-time intervention on the uniformity of melt heating and temperature stability, which is easy to cause local thermal stress cracks, uneven melt, bubble residue and other defects, affecting the quality of finished products and production consistency.

[0005] Therefore, it is urgent to develop a quartz crucible melting machine intelligent control system capable of realizing multi-source temperature measurement data cross-validation, full-process dynamic temperature control, intelligent diagnosis and intervention, so as to improve the stability of the melting process and the quality of finished products. SUMMARY

[0006] In view of the above problems, the present application provides a quartz crucible melting machine intelligent control system, which realizes the function of temperature regulation and control of quartz crucible melting.

[0007] The technical scheme adopted by the present application to solve its technical problems is: the present application provides a quartz crucible melting machine intelligent control system, comprising: a precision correction module, used for verifying the reliability of the temperature measurement data and calibrating the dual-color pyrometer before melting by comparing the heating temperature detected by the dual-color pyrometer in the test heating process with the heating temperature predicted based on the arc length and power.

[0008] A preheating and temperature rising module is used for monitoring the temperature rising rate of the quartz sand surface in the preheating stage in real time, and making corresponding regulation and control according to the difference between the temperature rising rate and the expected temperature rising rate.

[0009] The melting and soaking module is used for selecting multiple temperature measuring points on the melt surface in the melting stage by using the polar coordinate grid method, judging the uniformity of the melt heating according to the temperature difference between the temperature measuring points, and identifying the problem type and intervening when the heating is uneven, wherein the problem type includes local hot spots, local cold spots and overall mode problems.

[0010] The clarification constant temperature module is used for monitoring the melt temperature in real time and generating a temperature curve in the clarification stage, judging whether the temperature fluctuation exceeds the allowed range according to the temperature curve, and tracing the suspected causes according to the mode of the temperature fluctuation when the limit is exceeded, wherein the temperature fluctuation mode includes regular oscillation, irregular jump, one-way drift and step jump.

[0011] Compared with the prior art, the quartz crucible melting machine melting intelligent control system has the following beneficial effects: 1. The present application realizes online calibration of the temperature measuring device by cross verification of the dual-color temperature measuring instrument and the predicted temperature based on the arc length and power, effectively reduces the environmental interference, and improves the accuracy and consistency of the temperature data.

[0012] 2. The present application covers the preheating, melting and clarification stages of the melting process, respectively through the functions of temperature rise rate monitoring, polar coordinate grid uniformity judgment and temperature fluctuation mode identification, realizes the whole process intelligent temperature control from initial heating to final forming.

[0013] 3. The present application adopts the polar coordinate grid point distribution method, synchronously analyzes the ring temperature difference and the radial temperature gradient, comprehensively captures the temperature distribution abnormality, enhances the melt heating uniformity judgment ability, accurately identifies the local hot spot, the local cold spot or the overall mode problem, and provides clear basis for intervention. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creating laborious work.

[0015] Figure 1 It is the system module connection diagram of the present application.

[0016] Figure 2 It is the principle diagram of the arc centrifugal method of the present application.

[0017] Figure 3 It is the melt surface temperature measuring point layout schematic diagram of the present application.

[0018] Figure legend: 1. Observation window; 2. Temperature measuring port; 3. Quartz crucible; 4. Graphite mold; 5. Heating assembly; 6. Electrode; 7. Cracible lifting and rotating mechanism. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be apparently and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0020] Please refer to Figure 1 As shown in the figure, the present application provides a quartz crucible smelting machine smelting intelligent control system, which comprises a precision correction module, a preheating and temperature rising module, a smelting and heat preservation module and a clarification constant temperature module.

[0021] The preheating and temperature rising module is connected with the precision correction module and the smelting and heat preservation module respectively, and the clarification constant temperature module is connected with the smelting and heat preservation module.

[0022] The precision correction module is used to verify the reliability of the temperature measurement data and calibrate the double-color pyrometer by comparing the heating temperature detected by the double-color pyrometer in the trial heating process with the heating temperature predicted based on the arc length and power before smelting.

[0023] Further, the specific working process of the precision correction module is as follows: a plurality of temperature measurement ports are arranged around the furnace body and a double-color pyrometer is arranged, so as to form a temperature measurement network.

[0024] A trial temperature point is selected at the junction of the inner side wall and the bottom of the graphite mold.

[0025] Trial heating is performed before smelting, and the heating temperature of the trial temperature point detected by each double-color pyrometer in the trial heating process is obtained.

[0026] The arc image during the trial heating is collected through the observation window, the arc length is obtained through image processing technology, the arc length is input into the arc length-heating temperature correlation model, and the heating temperature predicted based on the arc length is obtained.

[0027] The arc power during the trial heating is called from the console and input into the arc power-heating temperature correlation model, and the heating temperature predicted based on the arc power is obtained.

[0028] The heating temperatures predicted based on the arc length and the arc power are weighted and fused to obtain a comprehensive predicted heating temperature.

[0029] According to the preset corresponding relationship between the thickness of the graphite mold and the temperature attenuation amount, the temperature attenuation amount is determined in combination with the current thickness of the graphite mold.

[0030] The comprehensive predicted heating temperature is subtracted by the temperature attenuation amount, and the predicted heating temperature of the trial temperature point is calculated.

[0031] The heating temperature of each dual-color temperature measuring instrument is compared with the predicted heating temperature of the test temperature point to obtain the temperature measurement deviation of each dual-color temperature measuring instrument.

[0032] If the temperature measurement deviation is less than a set threshold value, it is determined that the temperature measurement data of the corresponding dual-color temperature measuring instrument is reliable, otherwise it is determined to be unreliable.

[0033] The dual-color temperature measuring instrument determined to be unreliable is calibrated.

[0034] It should be noted that, as shown in Figure 2 In the present application, an arc centrifugal method is used to smelt a quartz crucible.

[0035] It should be noted that the present application selects a temperature measurement method of a dual-color temperature measuring instrument, which calculates temperature by measuring the ratio of radiation energy of two similar wavelengths, effectively reducing the interference of factors such as observation window pollution, local target shielding, and measurement distance changes, and is more suitable for the complex industrial environment of quartz crucible smelting than single-band thermal imaging instruments.

[0036] It should be noted that if the arc is unstable and jumps during the test heating process, the average value of the arc length is taken as the final arc length.

[0037] It should be noted that the specific method for obtaining the corresponding relationship between the thickness of the graphite mold and the temperature decay amount is as follows: by performing a standard heating experiment on a graphite mold of different thickness, the temperature on the heat source side and the temperature of the test temperature point on the inside of the mold are measured synchronously, the difference between the two is calculated to obtain the actual temperature decay amount, and then the corresponding relationship between the thickness of the graphite mold and the temperature decay amount is fitted, which is a curve or a mathematical model.

[0038] It should be noted that the weight of the weighted fusion can be preset according to the experience in the field, or can be obtained through a limited number of test data, for example, first collect the actual heating temperature historical data under different combinations of arc length and arc power, then calculate the correlation coefficients of arc length, arc power and heating temperature respectively, use regression analysis to determine the contribution of the two to the prediction of heating temperature, and finally normalize the contribution to convert it into a weight coefficient, and the sum of the two weights is 1.

[0039] For example, in one specific embodiment, the following steps can be performed to determine the weight in a data-driven manner: collect no less than 50 groups of historical test heating data, each group of data containing arc length, arc power and calibrated reference temperature.

[0040] The correlation coefficients of the arc length, the arc power and the reference temperature are calculated respectively, assuming that the length correlation coefficient is 0.85 and the power correlation coefficient is 0.70, through multiple linear regression analysis, the standardized regression coefficients of the length and the power are 0.6 and 0.4 respectively, and after normalization, the weight can be preset as: the arc length weight is 0.6 and the arc power weight is 0.4. The weight can be recalibrated once every 100 crucibles produced according to the electrode loss or process change.

[0041] It should be noted that the temperature measurement deviation threshold is set by analyzing historical calibration data or conducting special tests, specifically: collect a large amount of temperature measurement deviation data of the dual-color temperature measuring instrument in the trial heating process, combine the maximum allowed temperature measurement error required by the process, and determine the upper limit of the threshold value by statistical methods such as calculating the confidence interval to ensure that the threshold value can effectively distinguish between normal measurement error and abnormal deviation.

[0042] Specifically, the threshold value is a dynamic value based on statistical analysis and process requirements. For example, more than 200 times of temperature measurement deviation data in the trial heating process can be collected, and the mean and standard deviation can be calculated. Assuming that the deviation data conforms to the normal distribution, the mean is 0°C and the standard deviation is 5°C. According to the process requirements, the maximum allowed temperature measurement error is ±15°C. Then take ±15°C as the fixed threshold. More preferably, the 3σ principle can be used to set the threshold value to the mean ± 3 times the standard deviation, i.e. ±15°C. When the stability of the equipment improves, it can be tightened to ±2σ (i.e. ±10°C) to pursue higher precision.

[0043] It should be noted that the basis for cross-validation of the heating temperature predicted based on the arc length and power on the detection value of the dual-color temperature measuring instrument is that there is a clear mechanism between the arc physical parameters and the heating temperature, which can provide a temperature estimation benchmark independent of optical measurement. Its role is to identify whether the dual-color temperature measuring instrument has deviation or failure through multi-source data comparison, so as to realize online verification and accurate calibration of the temperature measuring instrument, and ensure the reliability and consistency of the temperature monitoring data in the melting process.

[0044] In this embodiment, the present application realizes online calibration of the temperature measuring equipment by cross-validation of the dual-color temperature measuring instrument and the predicted temperature based on the arc length and power, effectively reduces environmental interference, and improves the accuracy and consistency of temperature data.

[0045] Further, the establishment process of the arc length-heating temperature correlation model is: retrieving the arc images collected in multiple historical melting periods and the synchronous recorded melt temperature data from the database.

[0046] The arc image is subjected to image processing to extract the arc length.

[0047] The extracted arc length is taken as an input variable, and the melt temperature recorded at the corresponding time is taken as an output variable.

[0048] A regression analysis method is used to fit the input variable and the output variable, to establish a mapping relationship from the arc length to the heating temperature, and to construct an arc length-heating temperature correlation model.

[0049] It should be noted that the melt temperature is measured by a calibrated dual-color temperature meter.

[0050] Further, the establishment process of the arc power-heating temperature correlation model is: retrieving the arc current and voltage data collected in multiple historical melting periods and the synchronously recorded melt temperature data from the database.

[0051] The arc power is calculated according to the current and voltage, and the obtained power data is preprocessed.

[0052] The preprocessed arc power is taken as an input variable, and the melt temperature recorded at the corresponding time is taken as an output variable.

[0053] A regression analysis method is used to fit the input variable and the output variable, to establish a mapping relationship from the arc power to the heating temperature, and to construct an arc power-heating temperature correlation model.

[0054] It should be noted that the preprocessing of the electric power data includes filtering and normalization processing to eliminate noise interference and unify the data dimension.

[0055] The preheating temperature module is used to monitor the temperature rising rate of the quartz sand surface in real time during the preheating stage, and to adjust accordingly according to the difference between the temperature rising rate and the expected temperature rising rate.

[0056] Further, the specific working process of the preheating temperature module is: in the preheating stage, selecting several detection points on the edge line formed by the contact between the horizontal surface layer of the quartz sand and the inner side wall of the graphite mold.

[0057] The temperature at each detection point is collected in real time, and the average value is calculated as the surface temperature of the quartz sand.

[0058] The temperature rising rate of the surface temperature is monitored, and compared with the set expected temperature rising rate to obtain the temperature rising rate deviation.

[0059] If the temperature rising rate deviation at the current time exceeds the preset allowable range, and the deviation at the next time still exceeds the range, it is determined that the temperature rising rate needs to be adjusted.

[0060] According to the temperature rising rate deviation, the adjustment direction and adjustment amount of the temperature rising rate are determined and adaptive adjustment is performed.

[0061] It should be noted that the expected heating rate is set based on the material properties of quartz sand, target melting process requirements and historical production data, and is specifically determined by analyzing the temperature change rate in the preheating stage of the ideal process curve and combining expert experience values to ensure uniform heating of the quartz sand and avoid thermal stress cracks.

[0062] For example, for quartz sand with a purity of 99.99% or above and a particle size distribution of 180-250 μm, the ideal preheating curve requires a smooth transition to the melting point. Historical data from 100 successful production batches can be analyzed to statistically determine that the heating rate in the preheating stage (e.g., from room temperature to 1200°C) is mainly concentrated in the interval of 4.5°C / min to 5.5°C / min. In combination with the experience of material experts, the heating rate should not exceed 6°C / min to prevent thermal stress cracks. Therefore, the expected heating rate can be set to 5.0°C / min. If coarser or finer quartz sand raw materials are used, the value can be adjusted to 4.8°C / min or 5.2°C / min accordingly.

[0063] It should be noted that the allowed range of heating rate deviation is obtained by statistical analysis of the fluctuation range of heating rate in the preheating stage during normal production, and a confidence interval calculation method is used, taking into account process fault tolerance requirements and equipment control accuracy to set reasonable upper and lower limits of the deviation.

[0064] The specific setting method is as follows: select 100 normal production batches, extract the heating rate data every minute in the preheating stage, and calculate the standard deviation (σ) of the overall data. Assuming that σ = 0.3°C / min is calculated. Considering the inherent small fluctuations of the system, the allowed range can be set to the expected value ± 2σ, i.e., ± 0.6°C / min. This means that when the real-time heating rate continuously exceeds the range of 4.4°C / min to 5.6°C / min, the system will trigger regulation. This range can be adjusted according to the temperature control performance of different furnaces, and the performance of the furnace can be tightened to ± 0.4°C / min.

[0065] It should be noted that the preheating stage heating rate is regulated to ensure uniform and stable heating of the quartz sand layer, prevent local thermal stress cracks caused by rapid heating, or low energy efficiency and uneven material heating caused by slow heating, and thus provide a stable and controllable preheating basis for the subsequent melting stage, avoid the adverse effects of temperature sudden changes on the quality of the melt, and thus ensure the finished product quality and production consistency of the quartz crucible.

[0066] In this embodiment, the present application avoids energy waste and material thermal stress damage through adaptive regulation of the preheating stage heating rate, ensures smooth melting process, and ultimately improves the finished product quality and consistency between production batches of the quartz crucible.

[0067] Further, the specific process of determining the adjustment direction and adjustment amount of the temperature increase rate is: judging the adjustment direction according to the sign of the temperature increase rate deviation.

[0068] If the deviation is positive, it indicates that the current temperature increase rate is greater than the expected temperature increase rate, and the adjustment direction of the temperature increase rate is to decrease.

[0069] If the deviation is negative, it indicates that the current temperature increase rate is less than the expected temperature increase rate, and the adjustment direction of the temperature increase rate is to increase.

[0070] The absolute value of the temperature increase rate deviation is taken as the adjustment amount of the temperature increase rate.

[0071] The melting and heating module is used to select a plurality of temperature measurement points on the melt surface in the melting stage by using the polar coordinate grid method, to judge the uniformity of the melt heating according to the temperature difference between the temperature measurement points, and to identify the problem type and intervene when the heating is uneven, wherein the problem type includes local hot spots, local cold spots and overall mode problems.

[0072] Further, the specific working process of judging the uniformity of the melt heating in the melting and heating module is: referring to FIG. Figure 3 The center point of the melt surface is taken as the origin, concentric circles are set according to a fixed radius step, and rays are drawn from the origin according to a fixed angle step, and temperature measurement points are arranged at the intersection of the concentric circles and the rays.

[0073] The temperatures of the center point of the melt surface and each temperature measurement point are collected in real time.

[0074] The maximum temperature difference between each temperature measurement point on the same circle is calculated as the relative temperature difference on the ring of the circle.

[0075] The temperature variation between the temperature measurement points at different radii on the same ray is calculated to construct a radial temperature gradient sequence of the ray.

[0076] If the following conditions are met at the same time, it is determined that the melt is heated uniformly: (1) the relative temperature difference on the ring of all circles is less than the set relative temperature difference threshold on the ring.

[0077] (2) the matching degree of the radial temperature gradient sequence of all rays with the reference radial temperature gradient sequence is greater than the set matching degree threshold.

[0078] Otherwise, it is determined that the heating is uneven.

[0079] It should be noted that the relative temperature difference threshold on the ring is determined based on the material thermal uniformity process requirements and historical normal production data statistics, and by analyzing the maximum temperature difference distribution of each circle under a large number of uniformly heated conditions, the upper limit of the confidence interval is taken as the threshold, which ensures that the uniformity and abnormality of the ring temperature distribution can be effectively distinguished.

[0080] For example, to set the threshold, a large number of production data (such as 50 batches) under the condition of uniform heating can be collected, and the maximum temperature difference between all temperature measurement points on each ring is calculated. Assuming that for a certain ring with a radius of R, the 95% quantile of these maximum temperature differences is 8°C. To ensure process robustness, a margin of about 25% can be added, and the relative temperature difference threshold for this ring is set to 10°C. For rings with different radii, the threshold can be different, for example, the threshold for the inner ring (small radius) can be set to 8°C, the threshold for the middle ring can be set to 10°C, and the threshold for the outer ring (large radius) can be set to 12°C, to match its inherent thermal field distribution characteristics.

[0081] It should be noted that the reference radial temperature gradient sequence is generated by collecting multiple radial temperature gradient data under the condition of uniform heating in historical melting processes, and is generated after smoothing and mean calculation, representing the reasonable variation of radial temperature under ideal heating conditions.

[0082] For example, from 30 high-quality production batches under uniform heating, 5 key points (e.g. radius proportions 0, 0.25, 0.5, 0.75, 1.0) from the center to the edge of each ray are selected. Calculate the average temperature difference of each point relative to the center point in all batches to obtain an original gradient sequence, for example [0, -3, -7, -12, -15] (°C). Then use the moving average method for smoothing to finally obtain a smooth reference radial temperature gradient sequence, for example [0, -2.5, -5.8, -10.5, -14] (°C). This sequence represents the ideal radial temperature distribution under the specific equipment and process.

[0083] It should be noted that the similarity index between the real-time radial temperature gradient sequence and the reference sequence is calculated to quantify the matching degree, and the specific value of the matching degree is the Pearson correlation coefficient or the cosine similarity, and the higher the similarity, the greater the matching degree.

[0084] Taking the Pearson correlation coefficient as an example, its value range is [-1, 1]. Under the condition of uniform heating, the correlation coefficient of the real-time gradient and the reference gradient is usually very high. By statistical analysis of historical data, it can be found that the coefficient is greater than 0.92 under normal conditions. Therefore, the matching degree threshold can be set to 0.90. When the calculated correlation coefficient is less than 0.90, it is determined that the radial temperature distribution in this radial direction is abnormal. If the cosine similarity is used, its value range is [0, 1], and it is usually greater than 0.98 under normal conditions, and the threshold can be set to 0.975 accordingly.

[0085] It should be noted that by synchronously analyzing the circumferential temperature difference and the radial gradient through the polar coordinate grid, the abnormality of the melt surface temperature distribution in the angle and radius directions can be comprehensively captured, the accuracy and reliability of the uniformity judgment can be improved, and clear basis can be provided for subsequent precise intervention, thereby improving the melting quality consistency.

[0086] In the embodiment, the application adopts the polar coordinate grid point arrangement mode, synchronously analyzes the circumferential temperature difference and the radial temperature gradient, comprehensively captures the temperature distribution abnormality, enhances the melt heating uniformity judgment ability, accurately identifies the local hot spot, the local cold spot or the overall mode problem, and provides clear basis for intervention.

[0087] Further, the specific working process of identifying the problem type when the heating is uneven in the melting and soaking module is as follows: the average value of the temperatures of the temperature measuring points on the same ring is calculated to obtain the average temperature of the ring.

[0088] The average temperatures of the rings are compared with the temperature of the center point on the melt surface to obtain the temperature difference.

[0089] If the temperature difference of all the rings exceeds the respective preset allowable range, it is determined that it is an overall mode problem, otherwise the following steps are performed: the temperature measuring points on the same ring are numbered in a set order, a coordinate system is established with the number as the horizontal coordinate and the temperature as the vertical coordinate, and a scatter plot of the temperature distribution of each ring is drawn.

[0090] The fluctuation band of the data points in the scatter plot is obtained by regression and fitting method, if a data point deviates from the fluctuation band and its temperature is higher than the upper limit of the fluctuation band, the point is recorded as a local hot spot, and if its temperature is lower than the lower limit of the fluctuation band, it is recorded as a local cold spot.

[0091] The number, position and deviation of the local hot spots and the local cold spots on all the rings are counted.

[0092] It should be noted that the allowable range of the temperature difference of each ring is obtained by counting the difference range between the average temperature of each ring and the center point temperature in the melting stage in the historical normal production process, using the confidence interval calculation method, and considering the material heat uniformity process requirement and the system measurement error, the reasonable upper and lower limits of the allowable range of each ring are set.

[0093] The specific setting process is as follows: for each ring, the temperature difference with the center point under normal production state is counted. For example, for the first ring (the innermost ring), the temperature difference data is distributed between-4°C and +4°C; the second ring is distributed between-7°C and +6°C; and the third ring is distributed between-11°C and +9°C. The 95% confidence interval is taken and appropriately rounded to set the allowable range of each ring. For example, the first ring is ±5°C, the second ring is-6°C to +7°C (or take the symmetric value ±7°C), and the third ring is-10°C to +10°C. This differentiated setting is more consistent with the actual heat field distribution.

[0094] It should be noted that, for the identified local hot spots, measures are taken to reduce the corresponding regional energy input; for local cold spots, the energy supply of the corresponding region is increased; if it belongs to the overall mode problem, the heating system is globally calibrated and the process parameters are optimized.

[0095] The clarified constant temperature module is used to monitor the melt temperature in real time during the clarification stage and generate a temperature curve, according to which it is judged whether the temperature fluctuation is beyond the allowed range, and when it is beyond the limit, the suspected cause is traced according to the mode of temperature fluctuation, wherein the mode of temperature fluctuation includes regular oscillation, irregular jump, one-way drift and step jump.

[0096] Further, the specific working process of the clarified constant temperature module is: monitoring the melt temperature in real time during the clarification stage, and drawing the temperature curve changing with time.

[0097] The linear regression line of the temperature curve is taken as the reference line.

[0098] Identify each extreme point on the temperature curve, calculate the fluctuation of each extreme point relative to the reference line, mark the extreme points with fluctuation greater than the set threshold as fluctuation points, and record the time span corresponding to each fluctuation point as the fluctuation duration.

[0099] If the total number of fluctuation points and the cumulative duration of fluctuation are both within the allowed range, it is determined that the temperature fluctuation is not beyond the limit, otherwise it is determined that the temperature fluctuation is beyond the limit, and the following steps are performed: according to the morphological characteristics of the temperature curve, the specific mode of temperature fluctuation is determined, combined with the pre-established association set of each fluctuation mode and potential cause, the suspected cause of the current temperature fluctuation is matched and fed back.

[0100] It should be noted that the allowed range of the total number of fluctuation points and the cumulative duration of fluctuation is obtained by statistical analysis of the fluctuation characteristics of the temperature curve in the historical normal clarification process, the distribution range of the number of fluctuation points and the duration of fluctuation is calculated respectively, and reasonable threshold is set based on the confidence interval method combined with the process stability requirement.

[0101] For example, its setting is as follows: analyze the temperature curves (60 minutes in length) of 50 normal batches during the clarification stage. The total number of fluctuation points (fluctuation greater than ±3°C) of each curve is counted, and the 95% percentile is 3; the percentage of the total duration of fluctuation to the total duration is counted, and the 95% percentile is 4.5%. According to this, the allowed range can be set as: the total number of fluctuation points is not more than 3, and the cumulative duration of fluctuation is not more than 5% of the total duration. For example, for a 60-minute clarification stage, the cumulative fluctuation duration should not exceed 3 minutes. This threshold can be adjusted according to the product grade requirement, and high-specification products can be tightened to 2 points and 3% duration.

[0102] It should be noted that the correlation set is established based on a large number of historical abnormal data analysis and process knowledge induction, the temperature curve characteristics in different fluctuation modes are extracted, and the causal correlation mining is carried out in combination with device state, process parameters and external interference and other multi-source information, so as to form a mapping relationship library between each mode and potential causes.

[0103] In the embodiment, the present application identifies fluctuation modes such as regular oscillation and irregular jump through temperature curve analysis in the clarification stage, and traces the causes in combination with historical data and process knowledge, so as to realize rapid diagnosis and feedback and avoid quality abnormalities.

[0104] Further, the specific mode of determining temperature fluctuation is that: the example temperature curves corresponding to each temperature fluctuation mode in the pre-stored database are extracted, and the temperature fluctuation mode includes regular oscillation, irregular jump, one-way drift and step jump.

[0105] The temperature curve obtained by real-time monitoring in the clarification stage is compared with each example temperature curve in shape similarity.

[0106] The temperature fluctuation mode corresponding to the example curve with the highest similarity is determined as the finally identified fluctuation mode.

[0107] It should be noted that each temperature fluctuation mode usually shows distinct visual characteristics: regular oscillation is shown as that the temperature curve fluctuates around the set value in an approximate sinusoidal periodic manner, and the amplitude and period are usually stable; irregular jump is shown as that the temperature data suddenly rises or falls, forming a short peak or valley, and then quickly recovers, which is changeable and has no repeated rules; one-way drift refers to that the temperature measurement value continuously deviates from the set value, showing a monotone rising or falling trend; and step jump refers to that the temperature suddenly drops or jumps, and reaches a new steady state, forming an obvious step response.

[0108] In the embodiment, the present application covers the preheating, melting and clarification stages of the melting process, and realizes intelligent temperature control from initial heating to final forming through functions such as temperature rise rate monitoring, polar coordinate grid uniformity judgment and temperature fluctuation mode identification.

[0109] The above formulas are all dimensionless numerical calculations, the formula is obtained by collecting a large amount of data to simulate the latest real situation, and the preset parameters in the formula are set by the person skilled in the art according to the actual situation.

[0110] The above embodiments can be realized by software, hardware, firmware or any combination thereof, in whole or in part. When realized by software, the above embodiments can be realized in the form of a computer program product in whole or in part.

[0111] Those skilled in the art can understand that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0112] In addition, each functional module in each embodiment of the present application can be integrated in one processing module, or each module can exist physically alone, or two or more modules can be integrated in one module.

[0113] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0114] Finally, the above is only the preferred embodiment of the present application, and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A quartz crucible melting machine melting intelligent control system, characterized in that, The application relates to a precision correction module for verifying the reliability of temperature measurement data and calibrating a dual-color temperature detector by comparing the heating temperature detected by the dual-color temperature detector during trial heating with the heating temperature predicted based on the arc length and power before melting. The specific working process of the precision correction module is as follows: a plurality of temperature measuring openings are arranged around the furnace body, and a dual-color temperature detector is arranged, so as to form a temperature measurement network; a test temperature point is selected at the junction between the inner side wall and the bottom of the graphite mold; trial heating is performed before melting, and the heating temperature of each test temperature point detected by the dual-color temperature detector during the trial heating is obtained; an arc image during the trial heating is collected through an observation window, the arc length is obtained through image processing technology, the arc length is input into an arc length-heating temperature correlation model, and the heating temperature predicted based on the arc length is obtained; the arc power during the trial heating is called from a control console and input into an arc power-heating temperature correlation model, and the heating temperature predicted based on the arc power is obtained; the heating temperatures predicted based on the arc length and the arc power are weighted and fused to obtain a comprehensive predicted heating temperature; according to a preset corresponding relationship between the thickness of the graphite mold and the temperature attenuation amount, the temperature attenuation amount is determined in combination with the current thickness of the graphite mold; the comprehensive predicted heating temperature is subtracted by the temperature attenuation amount, and the predicted heating temperature of the test temperature point is calculated; the heating temperatures of the test temperature points detected by the dual-color temperature detectors are compared with the predicted heating temperature of the test temperature point, and the temperature measurement deviation of each dual-color temperature detector is obtained; if the temperature measurement deviation is less than a set threshold, it is determined that the temperature measurement data of the corresponding dual-color temperature detector is reliable, otherwise it is determined to be unreliable; the dual-color temperature detector determined to be unreliable is calibrated. A preheating and temperature rising module is used for monitoring the temperature rising rate of the quartz sand surface in the preheating stage in real time, and the temperature rising rate is adjusted according to the difference between the temperature rising rate and the expected temperature rising rate. A melting and heat soaking module is used for selecting a plurality of temperature measuring points on the surface of the melt by using a polar coordinate grid method in the melting stage, judging the heating uniformity of the melt according to the temperature difference between the temperature measuring points, and identifying the problem type and intervening when the heating is uneven, wherein the problem type includes local hot spots, local cold spots and overall mode problems. A clarification and constant temperature module is used for monitoring the melt temperature in real time and generating a temperature curve in the clarification stage, judging whether the temperature fluctuation exceeds the allowed range according to the temperature curve, and tracing the suspected causes according to the mode of the temperature fluctuation when the limit is exceeded, wherein the temperature fluctuation mode includes regular oscillation, irregular jump, one-way drift and stepwise jump. The establishment process of the arc length-heating temperature correlation model is as follows:

2. The quartz crucible melting machine melting intelligent control system according to claim 1, characterized in that: A plurality of historical arc images and synchronous melt temperature data collected in a plurality of historical melting periods are called from a database; The arc images are processed by image processing, and the arc length is extracted; The extracted arc length is used as an input variable, and the melt temperature recorded at the corresponding moment is used as an output variable; A regression analysis method is used to fit the input variable and the output variable, a mapping relationship from the arc length to the heating temperature is established, and an arc length-heating temperature correlation model is constructed. The establishment process of the arc power-heating temperature correlation model is as follows:

3. The quartz crucible melting machine melting intelligent control system according to claim 1, characterized in that: ​ Retrieve arc current and voltage data and synchronous recorded melt temperature data collected in a plurality of historical melting cycles from a database; Calculate arc power according to the current and voltage, and pre-process the obtained power data; Take the pre-processed arc power as input variable and the recorded melt temperature at the corresponding time as output variable; Use regression analysis method to fit the input variable and output variable, establish the mapping relationship from arc power to heating temperature, and construct the arc power-heating temperature correlation model.

4. The quartz crucible melting machine melting intelligent control system according to claim 1, characterized in that: The specific working process of the preheating and temperature rising module is as follows: In the preheating stage, select several detection points on the edge line formed by the contact between the horizontal surface layer of quartz sand and the inner side wall of graphite mold; Real-time collect the temperature of each detection point, and calculate the average value as the surface temperature of quartz sand; Monitor the temperature rising rate of the surface temperature, and compare it with the set expected temperature rising rate to obtain the temperature rising rate deviation; If the temperature rising rate deviation at the current time exceeds the preset allowable range, and the deviation at the next time still exceeds the range, it is determined that the temperature rising rate needs to be adjusted; According to the temperature rising rate deviation, determine the adjustment direction and adjustment amount of the temperature rising rate and perform adaptive control.

5. The quartz crucible melting machine melting intelligent control system according to claim 4, characterized in that: The specific process of determining the adjustment direction and adjustment amount of the temperature rising rate is as follows: Determine the adjustment direction according to the sign of the temperature rising rate deviation; If the deviation is positive, it indicates that the current temperature rising rate is greater than the expected temperature rising rate, and the adjustment direction of the temperature rising rate is to decrease; If the deviation is negative, it indicates that the current temperature rising rate is less than the expected temperature rising rate, and the adjustment direction of the temperature rising rate is to increase; Take the absolute value of the temperature rising rate deviation as the adjustment amount of the temperature rising rate.

6. The quartz crucible melting machine melting intelligent control system according to claim 1, characterized in that: The specific working process of judging the heating uniformity of the melt in the melting and soaking module is as follows: Take the center point of the melt surface as the origin, set concentric circles with fixed radius steps, and draw rays from the origin with fixed angle steps, and arrange temperature measurement points at the intersection of the concentric circles and the rays; Real-time collect the temperature of the center point of the melt surface and each temperature measurement point; Calculate the maximum temperature difference between each temperature measurement point on the same circle as the relative temperature difference of the circle; Calculate the temperature variation between temperature measurement points at different radii on the same ray to construct the radial temperature gradient sequence of the ray; If the following conditions are met at the same time, it is determined that the melt is uniformly heated: (1) The relative temperature difference of all circles is less than the set relative temperature difference threshold; (2) The matching degree of the radial temperature gradient sequence of all rays and the reference radial temperature gradient sequence is greater than the set matching degree threshold; Otherwise, it is determined that the heating is not uniform.

7. The quartz crucible melting machine melting intelligent control system according to claim 6, characterized in that: The specific working process of identifying the problem type when the heating is not uniform in the melting and soaking module is as follows: Calculate the average value of the temperature of each temperature measurement point on the same circle to obtain the average temperature of the circle; Compare the average temperature of each circle with the temperature of the center point of the melt surface to obtain the temperature difference; If the temperature difference of all circles exceeds its respective preset allowable range, it is determined as a whole mode problem, otherwise, the following steps are performed: Number the temperature measurement points on the same circle in a set order to establish a coordinate system with the number as the horizontal coordinate and the temperature as the vertical coordinate, and draw a scatter plot of the temperature distribution of each circle; The fluctuation band of the data points in the scatter plot is obtained by regression and fitting method, if a data point deviates from the fluctuation band and its temperature is higher than the upper limit of the fluctuation band, the point is recorded as a local hot spot, if its temperature is lower than the lower limit of the fluctuation band, it is recorded as a local cold spot; The number, position and offset of the local hot spots and the local cold spots on all the annuli are counted.

8. The quartz crucible melting machine melting intelligent control system according to claim 1, characterized in that: The specific working process of the clarified constant temperature module is as follows: The melt temperature is monitored in real time during the clarification stage, and the temperature curve changing with time is drawn; The linear regression line of the temperature curve is obtained as the reference line; Each extreme point on the temperature curve is identified, the fluctuation of each extreme point relative to the reference line is calculated, the extreme point with fluctuation greater than the set threshold is marked as a fluctuation point, and the time span corresponding to each fluctuation point is recorded as the fluctuation duration; If the total number of fluctuation points and the fluctuation cumulative duration do not exceed the set allowable range, it is determined that the temperature fluctuation does not exceed the limit, otherwise it is determined that the limit is exceeded, and the following steps are executed: According to the morphological characteristics of the temperature curve, the specific mode of temperature fluctuation is determined, the suspected cause of the current temperature fluctuation is matched by combining the pre-established association set of each fluctuation mode and potential cause, and feedback is performed.

9. The quartz crucible melting machine intelligent control system according to claim 8, characterized in that: The specific mode of temperature fluctuation is determined as follows: The example temperature curves corresponding to each temperature fluctuation mode in the database are extracted, the temperature fluctuation modes include regular oscillation, irregular jump, one-way drift and step jump; The temperature curve monitored in real time during the clarification stage is compared with each example temperature curve in shape similarity; The temperature fluctuation mode corresponding to the example curve with the highest similarity is determined as the finally identified fluctuation mode.

Images