A process monitoring method and system for glass sheet processing

Abstract

The present application relates to the technical field of automation control, and especially relates to a process monitoring method and system for glass plate processing. The method comprises the following steps: dividing a grinding disc into several regions, collecting temperature, linear velocity and pressure data of each region at each time; constructing a temperature prediction function; obtaining several groups of initial temperature rise coefficients of each region; constructing a temperature rise coefficient decay function based on the roughness factor of each region at each time and the several groups of initial temperature rise coefficients, and obtaining each group of temperature rise coefficients of each region at each time; performing weighted summation on each group of temperature rise coefficients of each region at each time according to the weight of each group of temperature rise coefficients, to obtain a final group of temperature rise coefficients; substituting the final group of temperature rise coefficients into the temperature prediction function to predict the temperature at the next time; and independently adjusting the linear velocity and pressure of the region according to the predicted temperature to realize accurate temperature control. The present application realizes accurate temperature control of each region.

Description

Technical Field

[0001] This invention relates to the field of automation control technology, and in particular to a process monitoring method and system for glass plate processing. Background Technology

[0002] Grinding is a crucial step in the manufacturing of precision optical components such as mobile phone screen glass, aiming to obtain a highly smooth and flat surface. This process typically involves attaching the glass to be processed onto a high-speed rotating grinding disc, where it rubs against a fixed abrasive grain below.

[0003] However, temperature control during the grinding process is a significant challenge. Due to differences in linear velocity across different areas of the grinding disc (the linear velocity at the edges is much higher than in the center), uneven frictional heat generation occurs, easily leading to localized high temperatures. Excessive temperatures not only cause fatal defects such as thermal cracking and deformation in the glass, severely impacting product yield, but also accelerate abrasive wear. When excessive temperature is detected, the overall rotational speed or pressure of the grinding disc is reduced, causing a decrease in the linear velocity in the central grinding area and further reducing grinding efficiency.

[0004] Therefore, traditional temperature control methods, which uniformly control the entire grinding disc, cannot solve the problem of local overheating caused by uneven linear velocity distribution. It is difficult to achieve a balance between ensuring grinding quality (avoiding thermal cracks) and production efficiency. Furthermore, the grinding process is a dynamic process, and the surface roughness of the abrasive gradually changes with the accumulation of processing time. This change directly affects the efficiency of frictional heat generation. Existing temperature control models cannot adapt to the characteristics of the surface roughness of the abrasive changing over time to predict the temperature, resulting in reduced accuracy of temperature prediction and thus affecting the control effect. Summary of the Invention

[0005] To address the technical problems that traditional temperature control methods cannot solve, such as localized overheating caused by uneven linear velocity distribution, the inability to achieve a balance between grinding quality and production efficiency, and the inability to adapt to changes in the surface roughness of abrasives over time, this invention provides a process monitoring method and system for glass plate processing.

[0006] In a first aspect, the present invention provides a process monitoring method for glass plate processing, employing the following technical solution:

[0007] A process monitoring method for glass plate processing includes the following steps:

[0008] The grinding disk is divided into several regions, and temperature, linear velocity, and pressure data of each region at each time point are collected. A temperature prediction function is constructed based on the linear velocity, pressure, and heat generation and dissipation effects caused by the roughness of the abrasive in each region.

[0009] Obtain several sets of initial temperature rise coefficients for each region; based on the cumulative grinding work of each region at each time, obtain the roughness factor of each region at each time; based on the roughness factor and several sets of initial temperature rise coefficients, construct a temperature rise coefficient decay function to obtain each set of temperature rise coefficients for each region at each time.

[0010] Based on the prediction accuracy of each set of temperature rise coefficients for each region at each time point to the actual temperature, the weight of each set of temperature rise coefficients for each region at each time point is obtained; the weighted sum of each set of temperature rise coefficients is performed according to the weights to obtain the final set of temperature rise coefficients for each region at each time point.

[0011] The final set of temperature rise coefficients is substituted into the temperature prediction function to predict the temperature at the next moment. Based on the comparison between the predicted temperature at the next moment and the preset temperature threshold, the linear velocity and pressure of the region are adjusted independently to achieve precise temperature control for each region.

[0012] The innovation of this invention lies in dividing the grinding disc into several independent regions and implementing independent temperature prediction and parameter adjustment for each region. This avoids the problem of reduced efficiency in the central region of the grinding disc when the entire grinding disc is uniformly controlled. This ensures that the grinding efficiency in the central region is maintained while the temperature in the edge region of the grinding disc does not exceed the limit, thereby improving product quality and significantly shortening the processing cycle. Furthermore, by quantifying the abrasive roughness through accumulated grinding work and incorporating it into the dynamic update of the temperature rise coefficient, the temperature prediction model can consider the impact of abrasive roughness on temperature during the grinding process, increasing the accuracy of temperature prediction. Furthermore, based on the prediction accuracy of each set of temperature rise coefficients for the actual temperature, weights are assigned to each set of temperature rise coefficients, and then the weighted summation of each set of temperature rise coefficients is used to obtain the final set of temperature rise coefficients, ensuring the accuracy of the obtained temperature rise coefficients and making temperature prediction more accurate.

[0013] Preferably, the step of constructing a temperature prediction function based on the heat generation and heat dissipation effects caused by the linear velocity, pressure, and roughness of the abrasive in the region includes:

[0014] Preset time step ;

[0015]

[0016] In the formula, Represents the i-th region in the... Predicted temperature at each moment; Represents the i-th region in the... The temperature at that moment; Represents the i-th region in the th... The linear velocity temperature rise coefficient at each moment; The i-th region represents the i-th region in the th... linear velocity at each moment; Represents the i-th region in the th... Pressure-temperature rise coefficient at any given moment; The i-th region represents the i-th region in the th... The pressure at any moment; This represents the preset heat dissipation coefficient.

[0017] It facilitates the prediction of future temperatures based on temperature prediction functions, thereby enabling temperature control and preventing thermal cracks in the abrasive due to abnormal temperatures.

[0018] Preferably, obtaining the roughness factor of each region at each time step based on the cumulative grinding work of each region at each time step includes:

[0019] The time t of the i-th region and the times before it are recorded as the historical time of the i-th region at time t. In the formula, This represents the cumulative grinding work done by the i-th region at time t. This represents the number of historical moments in the i-th region at time t. This represents the linear velocity of the i-th region at time t at the b-th historical moment; This represents the pressure of the i-th region at time t at the b-th historical moment;

[0020] In the formula, This represents the roughness factor of the i-th region at time t.

[0021] By quantifying the roughness of the abrasive through accumulated grinding work, it is easier to incorporate it into the dynamic update of the temperature rise coefficient. This allows the temperature prediction model to consider the impact of the roughness of the abrasive on the temperature during the grinding process, thus increasing the accuracy of temperature prediction.

[0022] Preferably, the step of constructing a temperature rise coefficient decay function based on the roughness factor and several initial sets of temperature rise coefficients, and obtaining each set of temperature rise coefficients for each region at each time step, includes:

[0023] ; ;

[0024] In the formula, Represents the i-th region in the th... The linear velocity temperature rise coefficient in the j-th group of temperature rise coefficients at time 1; The linear velocity temperature rise coefficient represents the temperature rise coefficient of the j-th group of temperature rise coefficients in the i-th region at the first time. This represents the roughness factor of the i-th region at time 1. Represents the i-th region in the... Roughness factor at each moment; Represents the i-th region in the... The pressure temperature rise coefficient in the j-th group of temperature rise coefficients at time 1; The pressure temperature rise coefficient represents the temperature rise coefficient of the j-th group in the i-th region at time 1.

[0025] Preferably, obtaining the weight of each group of temperature rise coefficients for each region at each time step includes:

[0026] Substituting the temperature rise coefficient of each group of regions at time 1, the temperature, linear velocity, pressure of regions at time 1, and the coolant temperature of the grinding disc at time 1 into the temperature prediction function, we obtain the temperature prediction result for region i at time 1. Predicted temperature at each time step under each set of temperature rise coefficients;

[0027] , Represents the i-th region in the... The weight of the j-th group of temperature rise coefficients at time 1; The weight of the j-th group of temperature rise coefficients for the i-th region at time 1; Represents the i-th region in the... The actual temperature at that moment; Represents the i-th region in the... The predicted temperature at the j-th temperature rise coefficient at time j; exp() represents an exponential function with the natural constant as the base.

[0028] Preferably, the step of weighted summation of each group of temperature rise coefficients according to the weights to obtain the final group temperature rise coefficient for each region at each time step includes:

[0029] ; ;

[0030] In the formula, Represents the i-th region in the th... The linear velocity temperature rise coefficient at each moment; Represents the i-th region in the... The linear velocity temperature rise coefficient in the j-th group of temperature rise coefficients at time 1; Represents the i-th region in the th... The weight of the j-th group of temperature rise coefficients at time 1; Represents the i-th region in the... Pressure-temperature rise coefficient at any given moment; Represents the i-th region in the th... The pressure temperature rise coefficient in the j-th group of temperature rise coefficients at time 1;

[0031] The as well as For the i-th region in the i-th region The final group temperature rise coefficient at each moment.

[0032] This improves the accuracy of the temperature rise coefficient.

[0033] Preferably, the step of substituting the final set of temperature rise coefficients into the temperature prediction function to predict the temperature at the next moment includes:

[0034] The i-th region in the... The final group temperature rise coefficient at time i, and the temperature rise coefficient of the i-th region at time i. Temperature, linear velocity, and pressure at time 1; grinding disc at time 2 Substituting the coolant temperature at time i into the temperature prediction formula, we obtain the temperature of the i-th region at time i. Predicted temperature at a given time.

[0035] This improved the accuracy of temperature prediction.

[0036] Preferably, the step of independently adjusting the linear velocity and pressure of the region based on the comparison result of the predicted temperature at the next moment and the preset temperature threshold, to achieve precise temperature control for each region, includes:

[0037] Preset temperature threshold If the i-th region is in the th... The predicted temperature at any given time is less than the temperature threshold. When, the linear velocity and pressure of the i-th region are not adjusted; if the i-th region is in the... The predicted temperature at any given time is greater than the temperature threshold. When, obtain the i-th region in the i-th region. The system calculates the predicted pressure and linear velocity values ​​at time i, based on the i-th region at time j. The predicted values ​​of linear velocity and pressure at time i are used to adjust the linear velocity and pressure of the i-th region to the predicted values.

[0038] Preferably, the step of obtaining the i-th region is in the first... The predicted pressure and linear velocity values ​​at each time point include:

[0039] , Represents the i-th region in the th... Predicted pressure values ​​at a given time point; Represents the i-th region in the th... The pressure at that moment; Represents the i-th region in the th... Predicted temperature at a given time; This represents the preset temperature threshold. Represents the pressure proportional adjustment coefficient;

[0040] , Represents the i-th region in the th... Predicted linear velocity values ​​at each time point; Represents the i-th region in the th... Linear velocity at a given moment; Represents the i-th region in the th... Predicted temperature at a given time.

[0041] Secondly, the present invention provides a process monitoring system for glass plate processing, which adopts the following technical solution:

[0042] A process monitoring system for glass plate processing includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the aforementioned process monitoring method for glass plate processing is implemented.

[0043] By adopting the above technical solution, a process monitoring method for glass plate processing is generated into a computer program and stored in a memory for loading and execution by a processor. This allows for the creation of a terminal device based on the memory and processor, facilitating its use.

[0044] The present invention has the following technical effects: The purpose of this invention is to divide the grinding disc into several regions and perform individual temperature prediction for each region, avoiding the problem of reduced efficiency in the central area of ​​the grinding disc when the entire grinding disc is uniformly controlled. This significantly shortens the processing cycle while improving product quality. Furthermore, by quantifying the abrasive roughness through accumulated grinding work and incorporating it into the dynamic update of the temperature rise coefficient, the temperature prediction model considers the influence of abrasive roughness on temperature during the grinding process, increasing the accuracy of temperature prediction. Finally, based on the prediction accuracy of each group of temperature rise coefficients for the actual temperature, weights are assigned to each group of temperature rise coefficients, and then the weighted summation of each group of temperature rise coefficients is used to obtain the final group of temperature rise coefficients, ensuring the accuracy of the obtained temperature rise coefficients and making temperature prediction more accurate. Attached Figure Description

[0045] Figure 1 This is a flowchart of a process monitoring method for glass plate processing according to an embodiment of the present invention. Detailed Implementation

[0046] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments.

[0047] This invention discloses a process monitoring method for glass plate processing, referring to... Figure 1 This includes steps S1-S4:

[0048] S1: Divide the grinding disc into several regions and collect the temperature, linear velocity, pressure of each region of the grinding disc at each moment, as well as the coolant temperature of the grinding disc at each moment.

[0049] It should be noted that during the grinding process of mobile phone screen glass, the screen glass is attached to the grinding disc and rotates together with it. The grinding disc is circular, and its high-speed rotation generates friction with the abrasive material fixed below, making the glass smoother. Since the linear velocity is higher at the edges farther from the center of the grinding disc, this friction generates heat, potentially causing the glass to reach higher temperatures and leading to quality issues such as thermal cracking. Similarly, higher pressure on the grinding disc also increases the glass temperature. Therefore, when the temperature on the grinding disc becomes too high, the linear velocity and pressure of the grinding disc need to be adjusted to control the temperature. However, this adjustment affects the linear velocity of the entire grinding disc, slowing down the linear velocity in the central grinding area and reducing grinding efficiency. Therefore, this invention divides the grinding disc into several annular regions, equipping each annular region with an independent control system to precisely adjust the linear velocity and pressure of each region, thereby achieving a balance between temperature control and efficiency.

[0050] In the real-time example of the present invention, the center point and radius of the grinding disk are obtained, and the radius of the grinding disk is divided into three equal parts to obtain three concentric circles. Based on these three concentric circles, the grinding disk is divided into two annular regions and the smallest concentric circle region. The two annular regions and the smallest concentric circle region are used as the various regions of the grinding disk.

[0051] The preset acquisition time is 1 second / time. Temperature sensors, laser velocimeters and pressure sensors are installed on each area of ​​the grinding disc. Temperature sensors are installed on the coolant pipes near the grinding disc. During the grinding process of the grinding disc on the glass, the temperature, linear velocity and pressure of each area at each time are collected, as well as the coolant temperature of the grinding disc at each time.

[0052] S2: Construct a temperature prediction function based on the heat generation and heat dissipation effects caused by the linear velocity, pressure, and roughness of the abrasive in the region.

[0053] It should be noted that when the linear velocity and pressure in a certain area of ​​the grinding disc are higher, frictional heat generation will be intensified, thereby accelerating the temperature rise in that area and determining its heat generation effect. At the same time, the temperature difference between that area and the coolant temperature determines its heat dissipation effect. Therefore, by analyzing the influence of parameters such as the linear velocity and pressure of each area of ​​the grinding disc on the temperature at the current moment, and by analyzing the heat dissipation effect of each area, the temperature of each area of ​​the grinding disc at the next moment can be predicted. This allows for the construction of a temperature prediction function to achieve temperature control and prevent excessively high temperatures from causing quality problems such as thermal cracking in the glass.

[0054] It should be further explained that in actual work, the surface roughness of the abrasive may decrease over time during the grinding process, which directly affects the magnitude of friction and the generation of frictional heat. The greater the roughness, the greater the friction and the more frictional heat is generated, resulting in different rates of temperature rise. Therefore, it is also necessary to consider the influence of the roughness of the abrasive on temperature changes at different times during the grinding process, and obtain the pressure temperature rise coefficient and linear velocity temperature rise coefficient at different times, so as to improve the adaptability and accuracy of temperature prediction.

[0055] In the real-time example of the present invention, a preset time step is used. In other embodiments, the implementer may preset the time according to the specific implementation method. The value;

[0056] Obtain the predicted temperature (temperature prediction function) for each region at each time step:

[0057]

[0058] In the formula, Represents the i-th region in the th... Predicted temperature at each moment; Represents the i-th region in the th... The temperature at that moment; Represents the i-th region in the th... The linear velocity temperature rise coefficient at each moment; The i-th region represents the i-th region in the th... linear velocity at each moment; Represents the i-th region in the th... Pressure-temperature rise coefficient at any given moment; The i-th region represents the i-th region in the th... The pressure at any moment; Representing a preset heat dissipation coefficient, in this embodiment of the invention, the preset... ; This represents the coolant temperature of the grinding disc at time t.

[0059] It reflects the heat generated per unit time due to friction caused by linear velocity; It reflects the heat generated by friction due to pressure per unit time; The larger the value, the greater the temperature rise at the next moment; as well as This reflects the effect of abrasive roughness on frictional heat generation at each moment;

[0060] This represents the heat dissipation temperature per unit time. The higher the value, the stronger the heat dissipation per unit time.

[0061] S3: Obtain several initial temperature rise coefficients for each region; based on the cumulative grinding work of each region at each time step, obtain the roughness factor of each region at each time step; based on the roughness factor and several initial temperature rise coefficients, construct a temperature rise coefficient decay function to obtain each group of temperature rise coefficients for each region at each time step; based on the prediction accuracy of each group of temperature rise coefficients for each region at each time step to the actual temperature, obtain the weight of each group of temperature rise coefficients for each region at each time step; perform a weighted summation of each group of temperature rise coefficients according to the weights to obtain the final group of temperature rise coefficients for each region at each time step.

[0062] It should be noted that the roughness of the abrasive changes over time. Therefore, the temperature rise coefficient needs to be updated based on the roughness of the grinding disc at different times. As the work accumulates during the grinding process, the mechanical and thermal shocks on the abrasive become more intense, causing its surface roughness to gradually decrease, gradually becoming smooth from the initial rough state. Therefore, this invention obtains the cumulative grinding work of each region at each time. If the cumulative grinding work is larger, it means that the roughness factor of each region at each time is smaller under continuous work, that is, the smoother the abrasive is. If the cumulative grinding work is smaller, it means that no work is done. At this time, the roughness factor of each region at each time is larger, that is, the rougher the abrasive is.

[0063] In this embodiment of the invention, time t of the i-th region and the times preceding it are recorded as the historical time of the i-th region at time t; the cumulative grinding work of each region at each time is obtained:

[0064] ;

[0065] In the formula, This represents the cumulative grinding work done by the i-th region at time t. This represents the number of historical moments in the i-th region at time t. This represents the linear velocity of the i-th region at time t at the b-th historical moment; This represents the pressure of the i-th region at time t at the b-th historical moment; The larger the value, the greater the cumulative grinding work of the i-th region at time t, and the smaller the abrasive roughness of the i-th region at time t.

[0066] In this embodiment of the invention, the roughness factor of the i-th region at time t is obtained:

[0067] ;

[0068] In the formula, This represents the roughness factor of the i-th region at time t; This represents the cumulative grinding work done by the i-th region at time t. The larger the value, the coarser the abrasive; the smaller the value, the smoother the abrasive.

[0069] It should be noted that when the present invention makes real-time temperature prediction during the grinding process, it is necessary to preliminarily estimate several sets of temperature rise coefficients (a set of temperature rise coefficients includes linear velocity temperature rise coefficient and pressure temperature rise coefficient) for each region at the initial moment based on the parameters of each region at the initial moment and the temperature prediction function. This estimation facilitates subsequent iterative updates, so that the temperature rise coefficient can be continuously optimized and adjusted in each iteration, thereby improving the accuracy of temperature prediction.

[0070] In this embodiment of the invention, the specific method for obtaining several sets of temperature rise coefficients for the i-th region at the first time step is as follows:

[0071] The temperature, linear velocity, and pressure of the i-th region at time 1, the coolant temperature of the grinding disc at time 1, and the temperature of the i-th region at time 2 are substituted into the temperature prediction formula, and the least squares method is used to fit them to obtain the linear velocity temperature rise coefficient and the pressure temperature rise coefficient of the i-th region, which are recorded as a set of temperature rise coefficients for the i-th region. Similarly, based on the data at time 2 and time 3 of the i-th region, a set of temperature rise coefficients for the i-th region is obtained, until N sets of temperature rise coefficients are obtained. The initial number of temperature rise coefficient sets N is preset to 5. In other embodiments, the implementer can preset the value of N according to the specific implementation method.

[0072] The Gaussian prior distribution of the linear velocity temperature rise coefficient of the i-th region is obtained as follows: , as well as Let represent the mean and variance of the linear velocity temperature rise coefficient among all groups of temperature rise coefficients in the i-th region, respectively; and obtain the Gaussian prior distribution of the pressure temperature rise coefficient in the i-th region as follows: , as well as These represent the mean and variance of the pressure temperature rise coefficient among all groups of temperature rise coefficients in the i-th region, respectively.

[0073] In the Gaussian prior distribution of linear velocity and pressure-temperature rise coefficient in the i-th region, a set of data is randomly selected as a set of temperature rise coefficients for the i-th region at time 1. A total of H sets of temperature rise coefficients are extracted to obtain several sets of temperature rise coefficients for the i-th region at time 1. The weight of each set of temperature rise coefficients for the i-th region at time 1 is preset to 1. The several sets of temperature rise coefficients for the i-th region at time 1 are also called several sets of initial temperature rise coefficients for the i-th region.

[0074] It should be further explained that the above steps obtain several sets of temperature rise coefficients for the i-th region at time 1. Since the roughness factor of the abrasive decreases over time, the value of the temperature rise coefficient also decreases over time. Therefore, the values ​​of the several sets of temperature rise coefficients for the i-th region at time 1 are first corrected based on the roughness factor to construct a temperature rise coefficient attenuation model, thus obtaining the values ​​of the i-th region at time 1+ The temperature rise coefficient for each time step; then, according to the particle filtering algorithm, the present invention applies the temperature rise coefficient of the i-th region at the (1+)-th time step. The prediction effect of each group of temperature rise coefficients at time t is evaluated, and the prediction effect of the i-th region at time t is obtained. The weight of each group of temperature rise coefficients at time i is determined; finally, the weighted sum of each group of temperature rise coefficients is calculated based on the weights to obtain the weight of the temperature rise coefficients for the i-th region at time i. The final temperature rise coefficient at each moment.

[0075] Get the i-th region in the 1+th region The specific method for calculating the final group temperature rise coefficient at each moment is as follows:

[0076] Construct a temperature rise coefficient decay model: Based on each set of temperature rise coefficients for the i-th region at time 1, obtain the temperature rise coefficients for the i-th region at time 1+. Temperature rise coefficient for each group at each moment:

[0077] ;

[0078] ;

[0079] In the formula, Represents the i-th region in the th... The linear velocity temperature rise coefficient in the j-th group of temperature rise coefficients at time 1; The linear velocity temperature rise coefficient represents the temperature rise coefficient of the j-th group of temperature rise coefficients in the i-th region at the first time. This represents the roughness factor of the i-th region at time 1. Represents the i-th region in the th... Roughness factor at each moment; Represents the i-th region in the th... The pressure temperature rise coefficient in the j-th group of temperature rise coefficients at time 1; The pressure temperature rise coefficient represents the temperature rise coefficient in the j-th group of temperature rise coefficients for the i-th region at time 1. The smaller the value, the smaller the roughness of the abrasive. Therefore, it is necessary to reduce the value of the j-th group of temperature rise coefficients for the i-th region at the first time step, thereby obtaining the value of the j-th group of temperature rise coefficients for the i-th region at the first time step. The temperature rise coefficient of the j-th group at time t.

[0080] Substitute the temperature rise coefficient of each group of regions at time 1, the temperature, linear velocity, pressure of regions at time 1, and the coolant temperature of the grinding disc at time 1 into the temperature prediction function to obtain the temperature of regions at time 1. Predicted temperature at each time step under each set of temperature rise coefficients;

[0081] Get the i-th region in the i-th region The weight of each temperature rise coefficient at each time point:

[0082] ;

[0083] In the formula, Represents the i-th region in the th... The weight of the j-th group of temperature rise coefficients at time 1; The weight of the j-th group of temperature rise coefficients for the i-th region at time 1; Represents the i-th region in the th... The actual temperature at that moment; Represents the i-th region in the th... The predicted temperature at the j-th temperature rise coefficient at time j; exp() represents an exponential function with the natural constant as the base; The smaller the value, the more likely the i-th region is in the i-th position. The j-th temperature rise coefficient at time t has a better prediction effect, therefore the j-th temperature rise coefficient has a larger weight; it should be noted that for the i-th region at time t The weights of the temperature rise coefficients of all groups at each time point are linearly normalized.

[0084] Get the i-th region in the i-th region The final group temperature rise coefficient at each moment:

[0085] ;

[0086] ;

[0087] In the formula, Represents the i-th region in the th... The linear velocity temperature rise coefficient at each moment; Represents the i-th region in the th... The linear velocity temperature rise coefficient in the j-th group of temperature rise coefficients at time 1; Represents the i-th region in the... The weight of the j-th group of temperature rise coefficients at time 1; Represents the i-th region in the... Pressure-temperature rise coefficient at any given moment; Represents the i-th region in the... The pressure temperature rise coefficient is the temperature rise coefficient in the j-th group at time j; it should be noted that... as well as For the i-th region in the i-th region The final group temperature rise coefficient at each moment.

[0088] It should be noted that the above steps yielded the result of the i-th region in the i-th region. The weight of each temperature rise coefficient at time i and the weight of the i-th region at time j. For each set of temperature rise coefficients at time i, according to the particle filtering algorithm, this invention reduces or replaces the values ​​based on the weight of each set of temperature rise coefficients, and uses this as the value for the i-th region at time i. The updated temperature rise coefficients for each time step are then substituted into the temperature rise coefficient decay model to obtain the temperature rise coefficient decay model for the i-th region at time step 1. Analyze the temperature rise coefficient of each group at each time point to obtain the temperature rise coefficient of the i-th region at the i-th time point. The final set of temperature rise coefficients at each time point can utilize the dynamic changes in the temperature rise coefficients and improve the accuracy of the temperature rise coefficients in each iteration, thereby providing more accurate temperature predictions.

[0089] In this embodiment of the invention, the i-th region is obtained in the first... The method for calculating the final group temperature rise coefficient at each moment is as follows:

[0090] The i-th region in the... The set of temperature rise coefficients with the smallest weight at time i is replaced by the set of temperature rise coefficients with the largest weight, thus obtaining the temperature rise coefficients of the i-th region at time i. Update the temperature rise coefficient for each group at each time step; update the temperature rise coefficient for the i-th region at the time step. Substituting each updated temperature rise coefficient at time step i into the temperature rise coefficient decay model, we obtain the temperature rise coefficient decay model for the i-th region at time step i. Temperature rise coefficient for each group at each moment;

[0091] According to the i-th region in the... The method for obtaining the weight of each temperature rise coefficient at time t, and obtaining the weight of the ith region at time t. The weight of each temperature rise coefficient at each time point;

[0092] According to the i-th region in the... The weight of each temperature rise coefficient at time i is applied to the i-th region at time j. The temperature rise coefficients of each group at time t are weighted and summed to obtain the temperature rise coefficient of the i-th region at time t. The final group temperature rise coefficient at each moment;

[0093] By analogy, the final group temperature rise coefficient is obtained for each iteration.

[0094] It should be noted that, since the set of temperature rise coefficients with the smallest weight is replaced with the set of temperature rise coefficients with the largest weight in each iteration, this operation causes the multiple sets of temperature rise coefficients in subsequent iterations to be too similar. Therefore, in order to avoid the degradation of temperature rise coefficients during iteration, if the repetition of several sets of temperature rise coefficients in any round of iteration is too high, it is necessary to reconstruct the distribution of temperature rise coefficients.

[0095] In this embodiment of the invention, if the i-th region is in the... The number of groups with repeated temperature rise coefficients at any given time point is less than [a certain value]. When, N represents the i-th region in the i-th region at the i-th time node. The number of temperature rise coefficient groups at time i, where the i-th region is at time j. Reconstruct the Gaussian prior distribution of the linear velocity temperature rise coefficient and the new Gaussian prior distribution of the pressure temperature rise number for the i-th region based on all the temperature rise coefficients at time i. Then, randomly select several sets of temperature rise coefficients as the data for the i-th region at time i. The temperature rise coefficient of several groups at a given time.

[0096] S4: Substitute the final set of temperature rise coefficients into the temperature prediction function to predict the temperature at the next moment; based on the comparison between the predicted temperature at the next moment and the preset temperature threshold, independently adjust the linear velocity and pressure of the region to achieve precise temperature control for each region.

[0097] It should be noted that after obtaining the final group temperature rise coefficient of each region at the current moment, the parameters of each region at the current moment and the final group temperature rise coefficient need to be substituted into the temperature prediction formula to obtain the predicted temperature of each region after the current moment. If the predicted temperature exceeds the temperature threshold, the linear velocity and pressure of each region at the current moment should be adjusted to avoid thermal cracking of the abrasive due to temperature rise.

[0098] In this embodiment of the invention, the i-th region is in the... The final group temperature rise coefficient at time i, and the temperature rise coefficient of the i-th region at time i. Temperature, linear velocity, and pressure at time 1; grinding disc at time 2 Substituting the coolant temperature at time i into the temperature prediction formula, we obtain the temperature of the i-th region at time i. Predicted temperature at a given time;

[0099] Preset temperature threshold In this embodiment of the invention, the implementer can preset a temperature threshold according to the specific implementation method. The value;

[0100] If the i-th region is in the... The predicted temperature at any given time is less than the temperature threshold. At that time, in the At any given moment, the linear velocity and pressure of the i-th region are not adjusted.

[0101] If the i-th region is in the... The predicted temperature at any given time is greater than the temperature threshold. When, obtain the i-th region in the i-th region. Predicted stress values ​​at each time point:

[0102] ;

[0103] In the formula, Represents the i-th region in the... Predicted pressure values ​​at a given time point; Represents the i-th region in the... The pressure at that moment; Represents the i-th region in the... Predicted temperature at a given time; This represents the preset temperature threshold. Represents the pressure proportional adjustment coefficient; The larger the value, the more likely the i-th region is in the i-th region. The higher the predicted temperature at any given time, the more necessary it is to reduce the pressure to effectively prevent the temperature from rising further. In this embodiment of the invention, a preset pressure proportional adjustment coefficient is used. In order to smoothly control the effect of temperature changes on pressure and avoid overreaction.

[0104] Get the i-th region in the i-th region Predicted linear velocity values ​​at each time point:

[0105] ;

[0106] In the formula, Represents the i-th region in the... Predicted linear velocity values ​​at each time point; Represents the i-th region in the... Linear velocity at a given moment; Represents the i-th region in the... Predicted temperature at a given time; This represents the preset temperature threshold. The larger the value, the more likely the i-th region is in the i-th region. The higher the predicted temperature at a given moment, the more necessary it is to reduce the linear velocity to effectively prevent the temperature from continuing to rise.

[0107] The system is based on the i-th region in the first... The predicted linear velocity and pressure at time t, for the t... At time i, the linear velocity and pressure of the i-th region are adjusted to the predicted values.

[0108] The above are all preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Therefore, all equivalent changes made in accordance with the structure, shape and principle of the present invention should be covered within the scope of protection of the present invention.

Claims

1. A process monitoring method for glass plate processing, characterized in that, include: The grinding disc was divided into several regions, and temperature, linear velocity, and pressure data for each region were collected at each time point. A temperature prediction function is constructed based on the heat generation and heat dissipation effects caused by the linear velocity, pressure, and roughness of the abrasive in the region. Obtain several sets of initial temperature rise coefficients for each region; Based on the cumulative grinding work of each region at each time, the roughness factor of each region at each time is obtained. Based on the roughness factor and several sets of initial temperature rise coefficients, a temperature rise coefficient decay function is constructed to obtain each set of temperature rise coefficients of each region at each time. Based on the prediction accuracy of each set of temperature rise coefficients for each region at each time point to the actual temperature, obtain the weight of each set of temperature rise coefficients for each region at each time point. The temperature rise coefficients of each group are weighted and summed according to the weights to obtain the final group temperature rise coefficients of each region at each time. The final set of temperature rise coefficients is substituted into the temperature prediction function to predict the temperature at the next moment. Based on the comparison between the predicted temperature at the next moment and the preset temperature threshold, the linear velocity and pressure of the region are adjusted independently to achieve precise temperature control for each region.

2. The process monitoring method for glass plate processing according to claim 1, characterized in that, The construction of a temperature prediction function based on the heat generation and heat dissipation effects caused by the linear velocity, pressure, and roughness of the abrasive in the region includes: Preset time step ; In the formula, Represents the i-th region in the th... Predicted temperature at each moment; Represents the i-th region in the th... The temperature at that moment; Represents the i-th region in the th... The linear velocity temperature rise coefficient at each moment; The i-th region represents the i-th region in the th... linear velocity at each moment; Represents the i-th region in the th... Pressure-temperature rise coefficient at any given moment; The i-th region represents the i-th region in the th... The pressure at any moment; This represents the preset heat dissipation coefficient.

3. The process monitoring method for glass plate processing according to claim 1, characterized in that, The step of obtaining the roughness factor of each region at each time step based on the cumulative grinding work of each region at each time step includes: The time t of the i-th region and the times before it are recorded as the historical time of the i-th region at time t. In the formula, This represents the cumulative grinding work done by the i-th region at time t. This represents the number of historical moments in the i-th region at time t. This represents the linear velocity of the i-th region at time t at the b-th historical moment; This represents the pressure of the i-th region at time t at the b-th historical moment; In the formula, This represents the roughness factor of the i-th region at time t.

4. The process monitoring method for glass plate processing according to claim 1, characterized in that, Based on the roughness factor and several initial sets of temperature rise coefficients, a temperature rise coefficient decay function is constructed to obtain each set of temperature rise coefficients for each region at each time step, including: ； ； In the formula, Represents the i-th region in the th... The linear velocity temperature rise coefficient in the j-th group of temperature rise coefficients at time 1; The linear velocity temperature rise coefficient represents the temperature rise coefficient of the j-th group of temperature rise coefficients in the i-th region at the first time. This represents the roughness factor of the i-th region at time 1. Represents the i-th region in the th... Roughness factor at each moment; Represents the i-th region in the th... The pressure temperature rise coefficient in the j-th group of temperature rise coefficients at time 1; The pressure temperature rise coefficient represents the temperature rise coefficient of the j-th group in the i-th region at time 1.

5. A process monitoring method for glass plate processing according to claim 1 or 2, characterized in that, The process of obtaining the weights of each set of temperature rise coefficients for each region at each time step includes: Substituting the temperature rise coefficient of each group of regions at time 1, the temperature, linear velocity, pressure of regions at time 1, and the coolant temperature of the grinding disc at time 1 into the temperature prediction function, we obtain the temperature prediction result for region i at time 1. Predicted temperature at each time step under each set of temperature rise coefficients; , Represents the i-th region in the th... The weight of the j-th group of temperature rise coefficients at time 1; The weight of the j-th group of temperature rise coefficients for the i-th region at time 1; Represents the i-th region in the th... The actual temperature at that moment; Represents the i-th region in the th... The predicted temperature at the j-th temperature rise coefficient at time j; exp() represents an exponential function with the natural constant as the base.

6. The process monitoring method for glass plate processing according to claim 1, characterized in that, The step of weighted summation of each group of temperature rise coefficients according to the weights to obtain the final group of temperature rise coefficients for each region at each time step includes: ; , Represents the i-th region in the th... The linear velocity temperature rise coefficient at each moment; Represents the i-th region in the th... The linear velocity temperature rise coefficient in the j-th group of temperature rise coefficients at time 1; Represents the i-th region in the th... The weight of the j-th group of temperature rise coefficients at time 1; Represents the i-th region in the th... Pressure-temperature rise coefficient at any given moment; Represents the i-th region in the th... The pressure temperature rise coefficient in the j-th group of temperature rise coefficients at time 1; The as well as For the i-th region in the i-th region The final group temperature rise coefficient at each moment.

7. The process monitoring method for glass plate processing according to claim 1, characterized in that, The step of substituting the final set of temperature rise coefficients into the temperature prediction function to predict the temperature at the next moment includes: The i-th region in the... The final group temperature rise coefficient at time i, and the temperature rise coefficient of the i-th region at time i. Temperature, linear velocity, and pressure at time 1; grinding disc at time 2 Substituting the coolant temperature at time i into the temperature prediction formula, we obtain the temperature of the i-th region at time i. Predicted temperature at a given time.

8. The process monitoring method for glass plate processing according to claim 1, characterized in that, The step of independently adjusting the linear velocity and pressure of each region based on the comparison between the predicted temperature at the next moment and a preset temperature threshold, to achieve precise temperature control for each region, includes: Preset temperature threshold If the i-th region is in the th... The predicted temperature at any given time is less than the temperature threshold. When, the linear velocity and pressure of the i-th region are not adjusted; if the i-th region is in the... The predicted temperature at any given time is greater than the temperature threshold. When, obtain the i-th region in the i-th region. The system calculates the predicted pressure and linear velocity values ​​at time i, based on the i-th region at time j. The predicted values ​​of linear velocity and pressure at time i are used to adjust the linear velocity and pressure of the i-th region to the predicted values.

9. A process monitoring method for glass plate processing according to claim 8, characterized in that, The acquisition of the i-th region in the first... The predicted pressure and linear velocity values ​​at each time point include: , Represents the i-th region in the th... Predicted pressure values ​​at a given time point; Represents the i-th region in the th... The pressure at that moment; Represents the i-th region in the th... Predicted temperature at a given time; This represents the preset temperature threshold. Represents the pressure proportional adjustment coefficient; , Represents the i-th region in the th... Predicted linear velocity values ​​at each time point; Represents the i-th region in the th... Linear velocity at a given moment; Represents the i-th region in the th... Predicted temperature at a given time.

10. A process monitoring system for glass plate processing, characterized in that, include: A processor and a memory, the memory storing computer program instructions that, when executed by the processor, implement a process monitoring method for glass plate processing according to any one of claims 1-9.

Images