Method for monitoring wafer polishing and electronic equipment

Abstract

The invention provides a method for monitoring wafer polishing and electronic equipment, and relates to the field of wafer polishing detection. The method comprises the following steps: acquiring a pressure observation value of polishing equipment at a current moment and a pressure observation value of the polishing equipment at a previous moment when a wafer is in a formal polishing process; predicting a first pressure prediction value at the current moment according to the pressure observation value at the previous moment, and updating the first pressure prediction value at the current moment according to the pressure observation value at the current moment to obtain a second pressure prediction value at the current moment; the target pressure prediction value at the current moment is calculated based on the second pressure prediction value at the current moment and the target pressure prediction value at the previous moment; and based on the observed value of the current moment and the target pressure predicted value of the current moment, the pressure deviation of the current moment is determined, and if the pressure deviation exceeds the dynamic interval, the polishing equipment is controlled to stop running. According to the method, the pressure change condition can be captured, early warning is performed in time, measures are taken, and the stability of the wafer polishing process is improved.

Description

Technical Field

[0001] The present application relates to the field of wafer polishing detection, and in particular to a method and electronic equipment for monitoring wafer polishing. Background Art

[0002] In the semiconductor manufacturing process, the wafer polishing process is one of the key steps to ensure the flatness and quality of the wafer surface. Traditional polishing processes usually rely on the control of fixed parameters, such as the rotation speed of the polishing disk, the flow rate of the polishing liquid, and the applied pressure. However, this fixed parameter control method is difficult to adapt to the dynamic changes that may occur during the polishing process, such as wafer surface characteristics, uniformity of the polishing liquid, and equipment wear. These factors may cause pressure fluctuations during the polishing process, which in turn affects the surface quality and processing accuracy of the wafer.

[0003] In addition, polishing monitoring systems in related technologies are mostly based on manual experience or simple sensor data monitoring, lacking the ability to perform real-time dynamic analysis and prediction of pressure changes. This makes it difficult to detect abnormal conditions in time during the polishing process, thereby increasing the risk of wafer damage and reducing production efficiency and yield. Summary of the invention

[0004] Based on this, it is necessary to provide a method and electronic equipment for monitoring wafer polishing to address the above technical problems. The method can capture pressure changes, issue warnings in time and take measures to improve the stability of the wafer polishing process.

[0005] In a first aspect, the present application provides a method for monitoring wafer polishing, the method being applied to a wafer polishing system, the system comprising a pressure sensor, the pressure sensor being mounted on a polishing device, and being used to obtain a pressure value applied by the polishing device to the wafer, the method being executed by a controller, and the method comprising: Get the pressure observation value z of the polishing equipment at the current moment when the wafer is in the formal polishing process k And the pressure observation value z at the previous moment k-1 ; According to the pressure observation value z at the last moment k-1 Predict the first pressure prediction value at the current moment, and according to the pressure observation value z at the current moment k The first pressure prediction value at the current moment is updated to obtain the second pressure prediction value at the current moment; Obtaining a target pressure prediction value at a current moment, where the target pressure prediction value at a current moment is calculated based on the second pressure prediction value at a current moment and the target pressure prediction value at a previous moment; Based on the observation value z at the current time kThe target pressure prediction value at the current moment is used to determine the pressure deviation at the current moment. If the pressure deviation exceeds the dynamic range, the polishing equipment is controlled to stop running; the dynamic range can be dynamically adjusted based on the pressure deviation within a unit time period.

[0006] In one embodiment, obtaining the target pressure prediction value at the current moment based on the second pressure prediction value at the current moment and the target pressure prediction value at the previous moment includes: Using the moving weighted average algorithm, the target pressure prediction value at the current moment is obtained based on the second pressure prediction value at the current moment associated with the first coefficient and the target pressure prediction value at the previous moment associated with the second coefficient; wherein the first coefficient is a dynamically adjustable coefficient, and the larger the first coefficient, the larger the pressure observation value z at the current moment. k The greater the impact on the target pressure prediction value at the current moment, the second coefficient is adjusted following the adjustment of the first coefficient.

[0007] In one embodiment, a moving weighted average algorithm is used to obtain the target pressure prediction value at the current moment, and the moving weighted average calculation formula is: , Among them, EWMA k is the target pressure prediction value at the current moment, EWMA k-1 is the target pressure prediction value at the previous moment, is the second pressure prediction value at the current moment, is the first coefficient, is the second coefficient.

[0008] In one embodiment, dynamically adjusting the first coefficient includes: The pressure observation value z at the current moment k Input the pre-trained Gaussian regression model to get the prediction variance , according to the prediction variance Dynamically update the first coefficient; wherein the calculation formula for updating the first coefficient is: , is the first coefficient after update, To set the pressure, is the first coefficient before updating.

[0009] In one embodiment, according to the pressure observation value z at the current moment k The first pressure prediction value at the current moment is updated to obtain the second pressure prediction value at the current moment, including: Obtain the process noise covariance Q and the observation noise covariance R, and determine the error covariance at the current moment according to the observation noise covariance R and the error covariance at the previous moment; Substitute the error covariance and observation noise covariance R at the current moment into the gain equation to obtain the Kalman gain; According to the Kalman gain, the pressure observation value z at the current moment k And the first pressure prediction value at the current moment are substituted into the update equation to obtain the second pressure prediction value at the current moment.

[0010] In one embodiment, the polishing device includes upper and lower polishing plates; determining that the wafer is in a formal polishing process includes: Obtaining an upper polishing plate speed interval and a lower polishing plate speed interval, wherein the upper and lower polishing plate speed intervals are determined based on the upper polishing plate speed and the lower polishing plate speed in a historical formal polishing process; The latest n1 data of the current wafer polishing process are obtained. If the upper polishing plate speeds in the latest n1 data are all within the upper polishing plate speed range and the lower polishing plate speeds are all within the lower polishing plate speed range, it is determined that the wafer is in the formal polishing process.

[0011] In one embodiment, the method further comprises: Obtain the latest pressure observation value sequence within a preset time period, and perform a sliding window operation on the pressure observation value sequence; Determine the first-order difference value diff of each pressure observation value in the window. If the window size is m, the first-order difference value set P in the window diff =[diff1, diff2, ... diff m-1 ]; If there are L consecutive first-order difference values ​​in the window that exceed the differential dynamic threshold, the polishing device is controlled to stop running; wherein the differential dynamic threshold is determined based on the mean and standard deviation of multiple first-order difference values ​​collected in the window.

[0012] In one embodiment, dynamically adjusting the dynamic interval based on the pressure deviation within a unit time period includes: Acquire multiple pressure observation values ​​in a sliding window within a unit time period, and obtain each pressure offset in the sliding window based on each pressure observation value in the sliding window and a corresponding target pressure prediction value; The offset mean and the offset standard deviation of the sliding window are calculated based on each pressure offset in the sliding window, and the dynamic range is adjusted based on the offset mean and the offset standard deviation of the sliding window.

[0013] In a second aspect, the present application further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and wherein the method for monitoring wafer polishing in the first aspect is implemented when the processor executes the computer program.

[0014] In the third aspect, the present application also provides a wafer polishing system, which includes the electronic device of the second aspect mentioned above, and in addition, the wafer polishing system also includes: an upper polishing plate for polishing one side of the wafer; a lower polishing plate for polishing the other side of the wafer; a supporting device for fixing the wafer, the supporting device applies a supporting force to the wafer so that the wafer contacts the upper and lower polishing plates; a polishing liquid pipeline for applying polishing liquid to the wafer and / or the upper and lower polishing plates; a rotation speed sensor for monitoring the instantaneous rotation speed of the upper and lower polishing plates; and a pressure sensor for monitoring the instantaneous pressure applied by the upper and lower polishing plates.

[0015] The above-mentioned method for monitoring the wafer method obtains the pressure observation value z of the polishing device at the current moment when confirming that the wafer is in the formal polishing process. k and the pressure observation value z at the previous moment k-1 ; Based on z k-1 Predict the first pressure prediction value at the current moment, and use z k Update it to obtain the second pressure prediction value; combine the second pressure prediction value at the current moment and the target pressure prediction value at the previous moment to calculate the target pressure prediction value at the current moment; according to the observation value z at the current moment k The pressure offset is determined by the target pressure prediction value. If the offset exceeds the dynamic range, the polishing equipment is controlled to stop running. The dynamic range is dynamically adjusted based on the pressure offset data within a unit time period to adapt to the pressure changes in the actual polishing process. Through real-time monitoring and dynamic adjustment, this method can effectively capture abnormal pressure changes, identify potential abnormal trends before wafer polishing breaks, and take timely warnings and measures, thereby improving the stability of the wafer polishing process. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic diagram of a wafer polishing system in one embodiment; Figure 2 A flowchart of a method for monitoring wafer polishing in one embodiment; Figure 3 A flowchart of obtaining a second pressure prediction value at the current moment in one embodiment; Figure 4 A flowchart for determining that a wafer is in a formal polishing process in one embodiment; Figure 5 A flowchart for monitoring wafer polishing in one embodiment; Figure 6 A flowchart of dynamically adjusting the dynamic interval based on the pressure deviation within a unit time period in one embodiment; Figure 7 is a structural diagram of an electronic device in one embodiment; Figure 8Schematic diagram of a wafer polishing system in another embodiment. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0018] In one embodiment, Figure 1 As shown, a method for monitoring wafer polishing is provided, which is applied to a wafer polishing system 100, the system comprising a pressure sensor 10, the pressure sensor 10 being mounted on a polishing device 20, and being used to obtain a pressure value applied by the polishing device 20 to the wafer, the method being executed by a controller 30, the polishing device 20 comprising an upper polishing plate 21 and a lower polishing plate 22. Figure 2 As shown, the following steps are included: Step 201: Obtain the pressure observation value z of the polishing device 20 at the current moment when the wafer is in the formal polishing process k And the pressure observation value z at the previous moment k-1 ; The formal polishing process can be determined by filtering out the pressure values ​​in the startup phase and the end phase. In the startup phase, the applied pressure value is not yet stable because the polishing device 20 has just been started; and in the end phase, the pressure value fluctuates due to the completion of polishing or equipment adjustment. Therefore, the formal polishing process refers to the stable phase after filtering out the startup phase and the end phase.

[0019] To determine whether it is in the formal polishing process, it is necessary to set the normal working range of the rotation speed of the upper polishing plate 21 and the lower polishing plate 22. The normal working range of the rotation speed of the upper polishing plate 21 and the lower polishing plate 22 can be based on the normal distribution of the historical formal polishing process data, and the 3σ criterion is used to determine the upper and lower limits of the fluctuation of the rotation speed of the upper polishing plate 21 and the lower polishing plate 22. Then the upper and lower limits of the fluctuation of the rotation speed of the upper polishing plate 21 and the lower polishing plate 22 are [ ]and[ ].

[0020] During real-time monitoring, the latest n data of the current processing process are read in real time, including the rotation speed value of the upper polishing plate 21 and the speed value of the lower polishing plate 22 Then, the real-time data is compared with the preset speed range. If, in the n data, each value of the speed of the upper polishing plate 21 and the speed of the lower polishing plate 22 is respectively within [ ]and[ ] interval, that is, for all i (1≤i≤n), there is belong[ ],and belong[ ], it can be determined that the current wafer is in the formal polishing processing state.

[0021] During the formal polishing process, the controller 30 obtains the pressure observation value z at the current moment. k , the pressure observation value z at the current moment k It can refer to the pressure value applied by the polishing device 20 to the wafer measured by the pressure sensor 10 at a specific time point k, that is, the pressure of the upper polishing plate 21 on the lower polishing plate 22. Get the pressure observation value z at the previous moment k-1 , that is, the pressure value measured at time point k-1.

[0022] It should be noted that the pressure of the upper polishing plate 21 on the lower polishing plate 22 and the pressure of the lower polishing plate 21 on the upper polishing plate 22 physically interact with each other. Usually, only the pressure value of one of the polishing plates needs to be measured to reflect the pressure value applied to the wafer. The pressure sensor 10 can be installed on one side of the upper polishing plate 21 or the lower polishing plate 22 to measure the pressure value applied to the wafer.

[0023] Step 202: Based on the pressure observation value z at the previous moment k-1 Predict the first pressure prediction value at the current moment, and according to the pressure observation value z at the current moment k The first pressure prediction value at the current moment is updated to obtain the second pressure prediction value at the current moment; According to the pressure observation value z at the last moment k-1 , the first pressure prediction value x at the current moment can be predicted by a preset mathematical model or algorithm (such as linear regression, moving average, etc.) k∣k-1 . Further, obtain the pressure observation value z at the current moment k , and use the current pressure observation value z k For the first pressure prediction value x k∣k-1 Correction is performed to obtain the second pressure prediction value x at the current moment k The correction process can be achieved by simple difference adjustment, for example, using the formula x k =x k∣k-1 +β(z k -x k∣k-1 ), where β can be an adjustment coefficient used to control the magnitude of the correction.

[0024] During the polishing process, the error of the pressure observation value mainly comes from the precision of the polishing equipment 20, the characteristics of the wafer and the environmental conditions. The insufficient precision of the polishing equipment 20 leads to the unevenness of the polishing plate and the unstable pressure distribution; the difference in wafer characteristics affects the force distribution; and the change of environmental conditions interferes with the reading of the pressure sensor 10.

[0025] Furthermore, the pressure observation value z at the current moment k Due to interference factors such as errors, the current pressure observation value z k There may be a significant deviation from the actual pressure value. Similarly, it will also cause the current pressure observation value z k will be consistent with the pressure observation value z at the previous moment k-1 Predicted first pressure prediction value x k∣k-1 There is a significant deviation. Therefore, it is necessary to k∣k-1 Correction is performed to obtain a more accurate current pressure prediction value x k .

[0026] It should be noted that the first pressure prediction value x k∣k-1 It can be based on the pressure observation value z at the previous moment k-1 The prediction cannot fully capture the latest actual pressure changes. By introducing the current pressure observation value z k , the first pressure prediction value x can be k∣k-1 Correction is made to make it closer to the actual pressure state. This updating process can effectively reduce the prediction error and improve the reliability of the prediction value.

[0027] If the previous moment is the initial moment of formal polishing, since there is not enough pressure data accumulated for prediction calculation, the first pressure observation value z1 can be used as the first prediction value x0 at the current moment, that is, x0=z1.

[0028] Step 203: obtaining a target pressure prediction value at the current moment, where the target pressure prediction value at the current moment is calculated based on the second pressure prediction value at the current moment and the target pressure prediction value at the previous moment; The second pressure prediction value at the current moment is a corrected pressure prediction value, which can reflect the comprehensive result of the latest observation data and the previous prediction; and the target pressure prediction value at the previous moment can provide reference information of the pressure change trend at the previous moment. The target pressure prediction value at the current moment is obtained by comprehensively considering the second pressure prediction value at the current moment and the target pressure prediction value at the previous moment through a preset calculation method, such as weighted average or other fusion strategies.

[0029] It should be noted that the second pressure prediction value mainly reflects the pressure state at the current moment, while the target pressure prediction value takes into account the trend and historical information of pressure changes by introducing the target pressure prediction value at the previous moment. Comprehensively considering the second pressure prediction value at the current moment and the target pressure prediction value at the previous moment can effectively reduce the misjudgment caused by single observation errors or short-term fluctuations, and improve the accuracy and reliability of the prediction. In addition, the calculation process of the target pressure prediction value can be regarded as a dynamic adjustment mechanism, which can update the prediction algorithm model in real time according to the changes in historical data and current observations, so as to better adapt to the dynamic changes in the polishing process. Therefore, calculating the target pressure prediction value at the current moment can improve the stability of the prediction and provide a more reliable basis for monitoring and controlling the polishing process.

[0030] Step 204: Based on the observed value z at the current moment k and the target pressure prediction value at the current moment, determine the pressure deviation at the current moment, if the pressure deviation exceeds the dynamic range, control the polishing device 20 to stop running; the dynamic range can be dynamically adjusted based on the pressure deviation within a unit time period.

[0031] The pressure deviation can reflect the difference between the actual observed pressure value and the predicted pressure value. If the pressure deviation exceeds the preset dynamic range, an alarm will be triggered and the polishing device 20 will be controlled to stop running to prevent potential abnormal conditions from causing damage to the wafer.

[0032] It should be noted that the dynamic interval can be dynamically adjusted according to the pressure offset data within a unit time period, and the statistical characteristics (such as the mean and standard deviation) of all pressure offsets within the unit time period can be calculated, and the upper and lower limits of the dynamic interval can be set based on this. For example, the dynamic interval can be set to the mean value of the pressure offset within the unit time period plus or minus a number of times the standard deviation of the pressure offset.

[0033] In this embodiment, when it is confirmed that the wafer is in the formal polishing process, the pressure observation value z of the polishing device 20 at the current moment is obtained. k and the pressure observation value z at the previous moment k-1 ; Based on z k-1 Predict the first pressure prediction value at the current moment, and use z k Update it to obtain the second pressure prediction value; combine the second pressure prediction value at the current moment and the target pressure prediction value at the previous moment to calculate the target pressure prediction value at the current moment; according to the observation value z at the current moment kThe pressure offset is determined by the target pressure prediction value. If the offset exceeds the dynamic range, the polishing device 20 is controlled to stop running. The dynamic range is dynamically adjusted based on the pressure offset data within a unit time period to adapt to the pressure changes in the actual polishing process. Through real-time monitoring and dynamic adjustment, the method can effectively capture abnormal conditions of pressure changes, identify potential abnormal trends before wafer polishing breaks, and take timely warnings and measures, thereby improving the stability of the wafer polishing process.

[0034] In one embodiment, obtaining the target pressure prediction value at the current moment based on the second pressure prediction value at the current moment and the target pressure prediction value at the previous moment includes: Using the moving weighted average algorithm, the target pressure prediction value at the current moment is obtained based on the second pressure prediction value at the current moment associated with the first coefficient and the target pressure prediction value at the previous moment associated with the second coefficient; wherein the first coefficient is a dynamically adjustable coefficient, and the larger the first coefficient, the larger the pressure observation value z at the current moment. k The greater the impact on the target pressure prediction value at the current moment, the second coefficient is adjusted following the adjustment of the first coefficient.

[0035] By assigning different weights (i.e., the first coefficient and the second coefficient) to the second pressure prediction value and the target pressure prediction value at the previous moment, the target pressure prediction value at the current moment is obtained by combining the latest observation data and the historical pressure change trend.

[0036] The first coefficient can be a dynamically adjustable parameter. The larger its value is, the higher the pressure observation value z at the current moment is. k The greater the impact on the target pressure prediction value, the greater the impact on the target pressure prediction value. Accordingly, the second coefficient will change according to the adjustment of the first coefficient to ensure that the sum of the two coefficients is 1.

[0037] In this embodiment, the dynamic adjustment of the first coefficient and the second coefficient can more flexibly balance the latest observation data and the historical data, thereby improving the accuracy and reliability of the target pressure prediction value.

[0038] In one embodiment, a moving weighted average algorithm is used to obtain the target pressure prediction value at the current moment, and the moving weighted average calculation formula is: , Among them, EWMA k is the target pressure prediction value at the current moment, EWMA k-1 is the target pressure prediction value at the previous moment, is the second pressure prediction value at the current moment, is the first coefficient, is the second coefficient.

[0039] Specifically, the moving weighted average algorithm (EWMA) is used to obtain the target pressure prediction value EWMA at the current moment. k , the calculation formula is .

[0040] Among them, the first coefficient The larger the value, the greater the pressure observed value x at the current moment. k Calculate the target pressure prediction value EWMA at the current moment k The greater the weight, the greater the second coefficient It is reduced accordingly to ensure that the target pressure prediction value can flexibly reflect the current observation data and the trend of historical pressure changes.

[0041] It should be noted that the moving weighted average algorithm can smoothly integrate the current observation data and historical data by weighted average, reduce the impact of short-term fluctuations on the prediction results, and maintain the ability to track long-term trends. The moving weighted average algorithm can effectively capture the trend of pressure changes and provide more stable prediction values ​​for subsequent monitoring and early warning.

[0042] In this embodiment, the method dynamically adjusts the first coefficient , which can flexibly balance the latest observation data and historical data, thereby improving the accuracy and reliability of the target pressure prediction value, and enhancing adaptability and stability.

[0043] In one embodiment, dynamically adjusting the first coefficient includes: The pressure observation value z at the current moment k Input the pre-trained Gaussian regression model to get the prediction variance , according to the prediction variance Dynamically update the first coefficient; wherein the calculation formula for updating the first coefficient is: , is the first coefficient after update, To set the pressure, is the first coefficient before updating.

[0044] During the wafer polishing process, equipment aging and wear are inevitable. These factors will cause the performance of the polishing equipment 20 to gradually decline, thereby affecting the stability and accuracy of the pressure observation value. Predicting the variance of the current data through the Gaussian regression process The Gaussian regression model can learn the relationship between input and output based on historical data and output the pressure prediction variance at the current moment. .

[0045] Based on the prediction variance , using the formula Dynamically update the first coefficient. When the prediction variance When it is larger, it means that the Gaussian regression model has a higher uncertainty about the current observation value, and the first coefficient after update will decrease and become more dependent on historical data; on the contrary, when the prediction variance When smaller, will increase, paying more attention to the current observation.

[0046] For example, assuming that the set pressure =100 units, current first coefficient = 0.5, the prediction variance of the Gaussian regression model output =25 units², then the first updated coefficient is =100+25100×0.5≈0.4.

[0047] It should be noted that the Gaussian regression model can obtain the prediction variance in the following way: Assume that there is a historical data set containing past pressure observations and their corresponding actual pressure values. The Gaussian regression model establishes a Gaussian process by learning the relationship between these data points. In the Gaussian process, each input point z k Corresponding to the mean and variance of an output.

[0048] In this embodiment, this dynamic adjustment mechanism effectively improves the adaptability to pressure changes and the prediction accuracy, and enhances the stability and reliability of the early warning.

[0049] In one embodiment, Figure 3 As shown, according to the pressure observation value z at the current moment k Updating the first pressure prediction value at the current moment to obtain the second pressure prediction value at the current moment includes the following steps: Step 301: Obtain the process noise covariance Q and the observation noise covariance R, and determine the error covariance at the current moment according to the process noise covariance Q and the error covariance at the previous moment; Specifically, the process noise covariance Q can describe the uncertainty of the internal state change, while the observation noise covariance R can reflect the degree of error in the measurement process. k =P k-1 +Q, the error covariance P of the previous moment k-1 Added to the process noise covariance Q, we get the error covariance P at the current moment k .

[0050] Step 302: Substitute the error covariance and the observation noise covariance R at the current moment into the gain equation to obtain the Kalman gain; The calculation formula of Kalman gain is: This formula can reflect the degree of trust in the observed data at the current moment. Among them, K k is the Kalman gain, P k is the error covariance at the current moment, and R is the observation noise covariance. The value of the Kalman gain is between 0 and 1. When the observation noise covariance R is large, the Kalman gain K k will decrease, indicating a lower degree of trust in the observed data; conversely, when the observed noise covariance R is small, the Kalman gain K k will increase, indicating a higher degree of confidence in the observed data.

[0051] For example, assuming that the error covariance P at the current moment is k =4 (unit²), observation noise covariance R=1 (unit²), then the Kalman gain is calculated as: K k =0.8. This means that at the current moment, the degree of trust in the observed data is high (because K k If the observation noise covariance R increases, for example, R=9, the Kalman gain will decrease. k ≈0.308. At this point, the trust in the observed data is low, and the observed data has little impact on the state update, which will rely more on the previous prediction value.

[0052] Step 303: Based on the Kalman gain and the pressure observation value z at the current moment k And the first pressure prediction value at the current moment are substituted into the update equation to obtain the second pressure prediction value at the current moment.

[0053] According to the Kalman gain K k , the pressure observation value z at the current moment k And the first pressure prediction value x at the current moment k∣k-1 , by updating the equation x k =x k∣k-1 +K k (z k -x k∣k-1 ) Calculate the second pressure prediction value x at the current moment k .

[0054] Among them, z k -x k∣k-1 Represents the deviation between actual observation and prediction. Kalman gain K k It can determine the weight of the deviation between the actual observation and the prediction in the update process. k is larger, indicating a higher degree of trust in the observed data, and the observed value has a greater impact on the second pressure prediction value; conversely, if the Kalman gain K kA smaller value indicates a lower degree of trust in the observed data and a smaller impact of the predicted value on the second pressure predicted value.

[0055] In this embodiment, the process noise covariance Q and the observation noise covariance R are obtained, and the error covariance at the previous moment is combined to determine the error covariance at the current moment, and then the Kalman gain is calculated. Finally, the Kalman gain and the pressure observation value z at the current moment are used to calculate the error covariance at the current moment. k The second pressure prediction value at the current moment is obtained by updating the equation based on the first pressure prediction value. This process not only takes into account the internal dynamic changes and the uncertainty of the observed data, but also dynamically adjusts the weights of the predicted value and the observed value through the Kalman gain, thereby optimizing the accuracy of the pressure prediction.

[0056] In one embodiment, the polishing device 20 includes an upper polishing plate 21 and a lower polishing plate 22. Figure 4 As shown, it is determined that the wafer is in the formal polishing process, including the following steps: Step 401: obtaining a rotation speed interval of the upper polishing plate 21 and a rotation speed interval of the lower polishing plate 22, wherein the rotation speed intervals of the upper and lower polishing plates are determined based on the rotation speeds of the upper polishing plate 21 and the lower polishing plate in the historical formal polishing process; By statistically analyzing the rotation speed data of the upper polishing disc 21 and the lower polishing disc during the historical formal polishing process, the mean and standard deviation of the rotation speed of the upper polishing disc 21 and the mean and standard deviation of the rotation speed of the lower polishing disc are calculated. Based on the mean and standard deviation of the rotation speed of the upper polishing disc 21 and the mean and standard deviation of the rotation speed of the lower polishing disc, combined with the process requirements and equipment characteristics, the normal fluctuation range of the rotation speed of the upper polishing disc 21 and the normal fluctuation range of the rotation speed of the lower polishing disc are set, that is, the rotation speed range of the upper polishing disc 21 and the rotation speed range of the lower polishing disc.

[0057] Exemplarily, the method of adding or subtracting three times the standard deviation of the mean may be used to determine the speed range of the upper polishing disk 21 and the speed range of the lower polishing disk, ensuring that during normal polishing, the speed value falls within the speed range most of the time.

[0058] Step 402: Obtain the latest n1 data of the current wafer polishing process. If the upper polishing plate 21 speed in the latest n1 data is within the upper polishing plate 21 speed range and the lower polishing plate speed is within the lower polishing plate speed range, determine that the wafer is in the formal polishing process.

[0059] The latest n1 data may include the rotation speed information of the upper polishing plate 21 and the rotation speed information of the lower polishing plate. Further, it is checked whether the rotation speeds of the upper polishing plate 21 in the n1 data are all within the preset rotation speed range of the upper polishing plate 21, and it is also checked whether the rotation speeds of the lower polishing plate are all within the preset rotation speed range of the lower polishing plate. If both conditions are met, that is, all the checked rotation speeds of the upper polishing plate 21 and the lower polishing plate are within their respective normal ranges, it can be determined that the current wafer is in the formal polishing process.

[0060] In this embodiment, this method uses the statistical characteristics of historical data to provide a benchmark for the current processing status, ensuring that the formal processing process is only identified when the rotation speed is within the normal process range, thereby improving the stability and reliability of the polishing process and providing an important basis for subsequent quality control and abnormal warning.

[0061] In one embodiment, Figure 5 As shown, the method further comprises the following steps: Step 501: obtaining the latest pressure observation value sequence within a preset time period, and performing a sliding window operation on the pressure observation value sequence; First, a preset time period is determined, such as the latest 10 seconds or 30 seconds, and then all pressure observations within the preset time period are obtained to form the latest pressure observation sequence.

[0062] Furthermore, a sliding window is defined, which can slide on the pressure observation sequence, each time sliding a certain step size (for example, 1 second), and extract the pressure observations within the window. In this way, a long sequence of pressure observations can be divided into multiple shorter subsequences, each of which represents the change of pressure within a specific time window. The sliding window operation helps to perform local analysis of pressure changes, thereby more effectively capturing the dynamic characteristics of pressure.

[0063] For example, assuming that the preset time period is 10 seconds, the pressure observation value sequence is [1,2,3,4,5,6,7,8,9,10], the sliding window size is 3, and the step size is 1. The sliding window operation will extract the following subsequences in sequence: first window: [1,2,3], second window: [2,3,4], third window: [3,4,5], fourth window: [4,5,6], fifth window: [5,6,7], sixth window: [6,7,8], seventh window: [7,8,9], eighth window: [8,9,10].

[0064] Step 502: Determine the first-order difference value diff of each pressure observation value in the window. If the window size is m, the first-order difference value set P in the window diff =[diff1, diff2, ... diff m−1]; Assume that the size of the sliding window is m, and the pressure observation sequence in the window is [z1,z2,…,z m ], then the first-order difference value set P diff is [diff1,diff2,…,diff m-1 ], where each difference value diff i Calculated from the difference between adjacent observations, i.e. diff i =z i+1 -z i For example, if the observation sequence in the window is [z1, z2, z3, z4], then the first-order difference value set is P diff =[z2-z1,z3-z2,z4-z3].

[0065] Step 503: If there are L consecutive first-order difference values ​​in the window that exceed the differential dynamic threshold, the polishing device 20 is controlled to stop running; wherein the differential dynamic threshold is determined based on the mean and standard deviation of multiple first-order difference values ​​collected in the window.

[0066] Calculate all first-order difference values ​​diff in the window i The mean μ diff and standard deviation σ diff , set adjustment coefficients based on business needs . Further, the differential dynamic threshold can be μ diff + σ diff .

[0067] If there are L consecutive first-order difference values ​​diff in the window i If the differential dynamic threshold is exceeded, it indicates that the pressure change is abnormally drastic and there is a sudden problem in the polishing process. At this time, the polishing device 20 needs to be controlled to stop running to prevent wafer damage or degradation of polishing quality.

[0068] In this embodiment, the method monitors the pressure change trend in real time and uses statistical methods to dynamically adjust the threshold, which can effectively identify abnormal pressure fluctuations and stop equipment operation in time, thereby ensuring the quality and stability of the wafer polishing process.

[0069] In one embodiment, Figure 6 As shown, dynamically adjusting the dynamic interval based on the pressure deviation within a unit time period includes the following steps: Step 601: acquiring a plurality of pressure observation values ​​in a sliding window within a unit time period, and obtaining each pressure offset in the sliding window based on each pressure observation value in the sliding window and a corresponding target pressure prediction value; A plurality of pressure observation values ​​in a sliding window within a unit time period are obtained, and for each pressure observation value in the sliding window within the unit time period, the difference between the pressure observation value and the corresponding target pressure prediction value is calculated, that is, each pressure offset in the sliding window is obtained.

[0070] For example, it is assumed that the pressure observation sequence in the sliding window within a unit time period is [z1, z2, …, z k ], the corresponding target pressure prediction value sequence is [EWMA1, EWMA2, …, EWMA k ], then each pressure offset is . Furthermore, the pressure offset set within the sliding window [ , ,…, ].

[0071] Step 602: Calculate the offset mean and offset standard deviation of the sliding window based on each pressure offset in the sliding window, and adjust the dynamic range based on the offset mean and offset standard deviation of the sliding window.

[0072] For the pressure offset value set within the sliding window [ , ,…, ] to perform statistical analysis and calculate the mean value μ and standard deviation σ of the offset. The mean value μ can reflect the average level of pressure offset in the window, while the standard deviation σ can indicate the degree of dispersion of these offset values.

[0073] According to the offset mean μ and the offset standard deviation σ, the upper and lower limits of the dynamic interval can be dynamically adjusted. For example, the adjustment coefficient η (for example, 3) can be set according to business needs, and the upper limit of the dynamic interval can be set to , the lower limit is set to .

[0074] In this embodiment, the method can reflect the deviation between the pressure observation value and the target prediction value in real time, capture the dynamic characteristics of the pressure change through statistical analysis, and flexibly adjust the dynamic range to adapt to the pressure fluctuation in the actual polishing process.

[0075] In one embodiment, the present application embodiment designs a dual warning mechanism. During the wafer polishing process, the dual warning mechanism jointly determines whether to issue a wafer explosion warning through two links: prediction warning and real-time monitoring warning.

[0076] For example, once the real-time monitoring value changes abnormally, even if the pressure deviation between the current target pressure prediction value and the current pressure observation value is small, an early warning will be issued immediately, directly triggering the polishing device 20 to shut down, ensuring that the polishing device 20 stops running under abnormal circumstances. Among them, the real-time monitoring early warning has a higher priority and directly responds to the current state of the equipment. The dual early warning mechanism can reduce the risk of errors when relying solely on the predicted value, and ensure timely response when sudden changes occur in the actual environment.

[0077] Based on the same concept, the present application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes a method for monitoring wafer polishing in the computer program.

[0078] In one embodiment, an electronic device is provided, including a memory and a processor. The electronic device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 7 As shown. The electronic device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the electronic device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for monitoring wafer polishing is implemented. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the housing of the electronic device, or an external keyboard, touchpad or mouse.

[0079] Based on the same concept, Figure 8 As shown, the present application also provides a wafer polishing system 800, which includes the above-mentioned electronic device 810. In addition, the wafer polishing system 800 also includes: The upper polishing plate 820 is used to polish one side of the wafer; the lower polishing plate 830 is used to polish the other side of the wafer; the supporting device 840 is used to fix the wafer, and the supporting device 840 applies a supporting force to the wafer so that the wafer contacts the upper polishing plate 820 and the lower polishing plate 830; the polishing liquid pipeline 850 is used to apply polishing liquid to the wafer and / or the upper polishing plate 820 and the lower polishing plate 830; the speed sensor 860 is used to monitor the instantaneous speed of the upper polishing plate 820 and the lower polishing plate 830; the pressure sensor 870 is used to monitor the instantaneous pressure applied by the upper polishing plate 820 and the lower polishing plate 830.

[0080] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0081] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for monitoring wafer polishing, characterized in that: The method is applied to a wafer polishing system, the system comprising a pressure sensor, the pressure sensor being mounted on a polishing device and being used to obtain a pressure value applied by the polishing device to the wafer, the method being executed by a controller, the method comprising: Get the pressure observation value z of the polishing equipment at the current moment when the wafer is in the formal polishing process k And the pressure observation value z at the previous moment k-1 ; According to the pressure observation value z at the previous moment k-1 Predict the first pressure prediction value at the current moment, and according to the pressure observation value z at the current moment k Updating the first pressure prediction value at the current moment to obtain a second pressure prediction value at the current moment; Obtaining a target pressure prediction value at a current moment, wherein the target pressure prediction value at the current moment is calculated based on the second pressure prediction value at the current moment and the target pressure prediction value at a previous moment; Based on the observed value z at the current moment k and the target pressure prediction value at the current moment, determine the pressure offset at the current moment, if the pressure offset exceeds the dynamic range, control the polishing device to stop running; the dynamic range can be dynamically adjusted based on the pressure offset within a unit time period.

2. The method for monitoring wafer polishing according to claim 1, characterized in that: Obtaining the target pressure prediction value at the current moment based on the second pressure prediction value at the current moment and the target pressure prediction value at the previous moment includes: Using a moving weighted average algorithm, the target pressure prediction value at the current moment is obtained based on the second pressure prediction value at the current moment associated with the first coefficient and the target pressure prediction value at the previous moment associated with the second coefficient; wherein the first coefficient is a dynamically adjustable coefficient, and the larger the first coefficient, the larger the pressure observation value z at the current moment. k The greater the impact on the target pressure prediction value at the current moment, the second coefficient is adjusted following the adjustment of the first coefficient.

3. The method for monitoring wafer polishing according to claim 2, characterized in that: The moving weighted average algorithm is used to obtain the target pressure prediction value at the current moment. The moving weighted average calculation formula is: ， Among them, EWMA k is the target pressure prediction value at the current moment, EWMA k-1 is the predicted value of the target pressure at the previous moment, is the second pressure prediction value at the current moment, is the first coefficient, is the second coefficient.

4. The method for monitoring wafer polishing according to claim 2, characterized in that: Dynamically adjusting the first coefficient includes: The pressure observation value z at the current moment k Input the pre-trained Gaussian regression model to get the prediction variance , according to the prediction variance Dynamically update the first coefficient; wherein the calculation formula for updating the first coefficient is: ， is the first coefficient after update, To set the pressure, is the first coefficient before updating.

5. The method for monitoring wafer polishing according to any one of claims 1 to 4, characterized in that: According to the current pressure observation value z k The first pressure prediction value at the current moment is updated to obtain a second pressure prediction value at the current moment, including: Obtaining a process noise covariance Q and an observation noise covariance R, and determining an error covariance at a current moment according to the process noise covariance Q and an error covariance at a previous moment; Substitute the error covariance and the observation noise covariance R at the current moment into the gain equation to obtain the Kalman gain; According to the Kalman gain, the pressure observation value z at the current moment k And the first pressure prediction value at the current moment is substituted into the update equation to obtain the second pressure prediction value at the current moment.

6. The method for monitoring wafer polishing according to claim 1, characterized in that: The polishing device comprises upper and lower polishing plates; Confirm that the wafer is in the formal polishing process, including: Obtaining an upper polishing plate speed interval and a lower polishing plate speed interval, wherein the upper and lower polishing plate speed intervals are determined based on the upper polishing plate speed and the lower polishing plate speed in a historical formal polishing process; The latest n1 data of the current wafer polishing process are obtained. If the upper polishing plate speeds in the latest n1 data are all within the upper polishing plate speed range and the lower polishing plate speeds are all within the lower polishing plate speed range, it is determined that the wafer is in the formal polishing process.

7. The method for monitoring wafer polishing according to claim 1, characterized in that: The method further comprises: Obtaining the latest pressure observation value sequence within a preset time period, and performing a sliding window operation on the pressure observation value sequence; Determine the first-order difference value diff of each pressure observation value in the window. If the window size is m, the first-order difference value set P in the window diff =[diff1, diff2, ... diff m-1 ]; If there are L consecutive first-order difference values ​​in the window that exceed the differential dynamic threshold, the polishing device is controlled to stop running; wherein the differential dynamic threshold is determined based on the mean and standard deviation of multiple first-order difference values ​​collected in the window.

8. The method for monitoring wafer polishing according to claim 1, characterized in that: Dynamically adjusting the dynamic interval based on the pressure deviation within a unit time period includes: Acquire multiple pressure observation values ​​in a sliding window within a unit time period, and obtain each pressure offset in the sliding window based on each pressure observation value in the sliding window and a corresponding target pressure prediction value; The mean offset and the standard offset of the sliding window are calculated based on each pressure offset in the sliding window, and the dynamic range is adjusted based on the mean offset and the standard offset of the sliding window.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for monitoring wafer polishing according to any one of claims 1 to 8 are implemented.

10. A wafer polishing system, characterized in that: The system includes the electronic device of claim 9, and the wafer polishing system further includes: An upper polishing plate, used for polishing one side of the wafer; a lower polishing plate, used for polishing the other side of the wafer; A supporting device, used to fix the wafer, the supporting device applies a supporting force to the wafer so that the wafer contacts the upper and lower polishing plates; A polishing liquid pipeline, used for applying polishing liquid to the wafer and / or the upper and lower polishing plates; Speed ​​sensor, used to monitor the instantaneous speed of the upper and lower polishing discs; Pressure sensor, used to monitor the instantaneous pressure applied by the upper and lower polishing plates.

Images