Calibration method and calibration system of heating base and chemical vapor deposition equipment
By combining predictive models and adjusters, efficient and accurate calibration of the heating base level is achieved, solving the problems of low adjustment efficiency and poor repeatability of the heating base in the existing technology, and improving the uniformity of film thickness and equipment utilization.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- MAXSCEND SEMICONDUCTOR LAKEVIEW CO LTD
- Filing Date
- 2025-12-23
- Publication Date
- 2026-04-17
AI Technical Summary
In existing technologies, the leveling of the heating base relies on the experience of engineers, which is inefficient and has poor repeatability, resulting in poor film thickness uniformity and affecting process stability and product yield.
By combining a predictive model with an adjuster, the target adjustment amount is determined by acquiring the current film thickness data and the target film thickness data. The adjuster is controlled to calibrate the level of the heating base in one go. The machine learning model is used to accurately predict the adjustment amount and perform reverse verification, reducing the interference of human factors.
It improves the adjustment efficiency and accuracy of the heating base, shortens maintenance time, enhances process stability and product yield, and reduces reliance on engineers' experience.
Smart Images
Figure CN121874756A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of semiconductor manufacturing process technology, and specifically to a calibration method, calibration system, and chemical vapor deposition equipment for a heating base. Background Technology
[0002] In semiconductor chip manufacturing, chemical vapor deposition (CVD) is a key process for forming various thin films. After long-term operation of CVD equipment, the heating base may experience wear and deformation, affecting the uniformity of the thin film thickness on the wafer surface. Therefore, regular preventive maintenance (PM) of the heating base is required.
[0003] However, the reinstalled heating base inevitably has micron-level mechanical positional deviations, causing changes in its levelness and consequently leading to a deterioration in the film thickness grown after restarting. Currently, manual mechanical adjustment is typically used to correct the levelness of the heating base. However, this adjustment process relies on the engineer's experience and feel, requiring repeated adjustments to meet requirements. Furthermore, process testing and film thickness measurement are necessary after each adjustment, resulting in low adjustment efficiency. Summary of the Invention
[0004] This invention provides a calibration method, calibration system, and chemical vapor deposition equipment for a heated base to solve the problem of low adjustment efficiency.
[0005] In a first aspect, the present invention provides a calibration method for a heating base, applied to a controller in a calibration system for a heating base. The calibration system for the heating base includes a controller and an adjuster for adjusting the levelness of the heating base. The method includes: after maintaining the heating base, acquiring current film thickness data deposited on the wafer surface; determining target thickness deviation data based on the current film thickness data and target film thickness data of the wafer; determining a target adjustment amount for the adjuster based on the target thickness deviation data and a prediction model, wherein the prediction model is used to characterize the mapping relationship between the adjustment amount of the adjuster and the thickness deviation data; and controlling the adjuster to calibrate the levelness of the heating base according to the target adjustment amount.
[0006] The heating base calibration method provided in this embodiment, after acquiring the current film thickness data deposited on the wafer surface, determines the target thickness deviation data based on the current film thickness data and the target film thickness data of the wafer. Then, based on the target thickness deviation data and the prediction model, it determines the target adjustment amount of the adjuster and controls the adjuster to calibrate the levelness of the heating base according to the target adjustment amount. This embodiment predicts the target adjustment amount corresponding to the target thickness deviation data through a prediction model. Only one adjustment is needed to bring the deposited film thickness data close to the target, avoiding multiple process test iterations, greatly shortening the rework time after PM, improving debugging efficiency and equipment utilization. Moreover, determining the target adjustment amount through the prediction model can reduce human interference, ensure consistent adjustment results each time, and improve process stability and product yield.
[0007] In one optional implementation, the prediction model is a bidirectional mapping machine learning model. The target adjustment amount of the adjuster is determined based on the target thickness deviation data and the prediction model, including: inputting the target thickness deviation data into the prediction model and determining the initial adjustment amount of the adjuster based on the output of the prediction model; inputting the initial adjustment amount into the prediction model and determining the predicted thickness deviation data based on the output of the prediction model; determining the predicted film thickness data based on the predicted thickness deviation data and the current film thickness data; and if the predicted film thickness data and the target film thickness data are consistent, then the initial adjustment amount is determined as the target adjustment amount.
[0008] In this embodiment, the regression model constructed through machine learning can achieve accurate prediction of process response. Moreover, this embodiment does not directly determine the adjustment amount obtained by the prediction model based on the target thickness deviation data as the target adjustment amount. Instead, the adjustment amount is input into the prediction model for reverse verification. Only when the predicted film thickness data and the target film thickness data are consistent is the initial adjustment amount output by the prediction model determined as the target adjustment amount, which can further improve the adjustment accuracy.
[0009] In an optional embodiment, the calibration method for the heating base further includes: if the predicted film thickness data and the target film thickness data are inconsistent, updating the initial adjustment amount according to a preset adjustment amount until the predicted film thickness data obtained based on the updated initial adjustment amount is consistent with the target film thickness data; and determining the updated initial adjustment amount as the target adjustment amount.
[0010] In an alternative implementation, after determining the updated initial adjustment amount as the target adjustment amount, the calibration method for the heating base further includes: updating the model parameters in the prediction model based on the target adjustment amount and the target thickness deviation data.
[0011] In one alternative embodiment, the calibration system for the heating base further includes a display screen, and the calibration method for the heating base further includes displaying initial adjustment amounts and predicted film thickness data on the display screen.
[0012] In one alternative implementation, both the current film thickness data and the target film thickness data are characterized by a thickness distribution heatmap.
[0013] In one optional implementation, after calibrating the levelness of the heating base, the calibration method for the heating base further includes: acquiring actual film thickness data deposited on the wafer surface; if the actual film thickness data is inconsistent with the target film thickness data, then using the actual film thickness data as the current film thickness data, and returning to the step of determining the target thickness deviation data based on the current film thickness data and the target film thickness data of the wafer.
[0014] Secondly, the present invention provides a calibration system for a heating base, the calibration system comprising an adjuster and a controller for adjusting the levelness of the heating base; the controller is used to acquire current film thickness data deposited on the wafer surface after maintaining the heating base; the controller is also used to determine target thickness deviation data based on the current film thickness data and the target film thickness data of the wafer; the controller is also used to determine a target adjustment amount of the adjuster based on the target thickness deviation data and a prediction model, wherein the prediction model is used to characterize the mapping relationship between the adjustment amount of the adjuster and the thickness deviation data; the controller is also used to control the adjuster to calibrate the levelness of the heating base according to the target adjustment amount.
[0015] In one alternative implementation, the adjuster includes a leveling screw equipped with a displacement sensor and an adjustment amount display.
[0016] Thirdly, the present invention provides a chemical vapor deposition apparatus, including a calibration system for a heating base as described in the second aspect above or any corresponding embodiment thereof.
[0017] Fourthly, the present invention provides an electronic device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the calibration method of the heating base described in the first aspect or any corresponding embodiment thereof.
[0018] Fifthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the calibration method for the heating base described in the first aspect or any corresponding embodiment thereof.
[0019] In a sixth aspect, the present invention provides a computer program product, including computer instructions for causing a computer to execute the calibration method for a heating base according to the first aspect or any corresponding embodiment described above. Attached Figure Description
[0020] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0021] Figure 1 This is a schematic diagram of the shape of the heating base according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the adjustment points of the heating base according to an embodiment of the present invention; Figure 3 This is a schematic diagram of a heating base adjustment structure according to an embodiment of the present invention; Figure 4 This is a schematic diagram of a calibration system for a heating base according to an embodiment of the present invention; Figure 5 This is a schematic flowchart of a calibration method for a heating base according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the heating base after preventive maintenance according to an embodiment of the present invention; Figure 7 This is a schematic diagram of the heating base after adjustment according to an embodiment of the present invention; Figure 8 This is a schematic flowchart of another calibration method for a heating base according to an embodiment of the present invention; Figure 9 This is a schematic diagram of the display interface of a display screen according to an embodiment of the present invention; Figure 10 This is a schematic flowchart of another calibration method for a heating base according to an embodiment of the present invention; Figure 11 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention.
[0022] Reference numerals: 11, heating base; 12, support screw; 13, leveling screw; 21, controller; 31, adjuster. Detailed Implementation
[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0024] Chemical vapor deposition (CVD) processes utilize gaseous or vapor-state precursors to undergo chemical reactions on the surface of a substrate (wafer), depositing functional films (such as insulating layers, conductive layers, etc.). CVD equipment includes a chamber and a heating base located within the chamber. The heating base is used to support the semiconductor wafer and to heat the semiconductor wafer to the required process temperature. The shape of the heating base 11 can be as follows: Figure 1 As shown, it is circular, and its leveling is one of the core parameters to ensure the thickness uniformity of the thin film on the wafer surface.
[0025] Currently, after completing the periodic preventive maintenance (PM) of the CVD equipment, the reinstalled heating base inevitably has a micron-level mechanical positional deviation, which causes the levelness of the heating base to change compared with the optimal state (Baseline, BSL) before PM, and consequently leads to the degradation of the film thickness grown on the wafer surface after restarting.
[0026] To solve this problem, such as Figure 2 and Figure 3 As shown, the heating base 11 is equipped with support screws 12 and multiple leveling screws 13. After PM (partial pressure monitoring) of the heating base, the equipment engineer manually adjusts the leveling screws 13 on the heating base, and then performs multiple iterative cycles of process testing – film thickness measurement – readjustment to restore the levelness of the heating base to its optimal state. However, the above manual mechanical adjustment method has the following problems: (1) Poor accuracy, no real-time data feedback during the adjustment process, relying entirely on the engineer's experience and feel.
[0027] (2) Low efficiency. After each adjustment, a process test and film thickness measurement that lasts for several hours must be carried out, which greatly prolongs the tool down time after PM and reduces equipment utilization.
[0028] (3) Poor repeatability, it is difficult to accurately adjust to the target value through a few iterations, the adjustment process has uncertainty, which affects the stability of the process and the product yield.
[0029] In view of this, the present invention provides a calibration method, calibration system and chemical vapor deposition equipment for a heating base. After PM, the target adjustment amount for achieving the target value of the film thickness generated on the wafer surface is determined by a prediction model. Then, the levelness of the heating base is adjusted based on the target adjustment amount. Only one adjustment is needed to achieve the required film thickness, thereby improving the adjustment efficiency and accuracy.
[0030] To facilitate understanding, a brief description of the calibration system for the heating base provided by this invention will be given first.
[0031] like Figure 4 As shown, the calibration system for the heating base includes a controller 21 and an adjuster 31. The controller 21 can be an electronic device such as a computer, or a control unit within an electronic device. The adjuster 31 is located at the edge of the heating base 11 and is used to adjust the levelness of the heating base 11. The adjuster 31 includes leveling screws or other devices that can adjust the vertical position of the heating base 11. There are multiple adjusters 31. Figure 4 Taking the number of adjusters 31 as an example of 2, but not limited to this, for example, the number of adjusters 31 can be 3 or 4, etc.
[0032] For example, the adjuster 31 may include a leveling screw equipped with a displacement sensor and an adjustment amount display. The displacement sensor and the adjustment amount display are connected to the controller 21. The displacement sensor can measure the rotation angle and / or linear displacement of the leveling screw in real time. The adjustment amount display is used to display the rotation angle and / or linear displacement of the leveling screw. The adjustment accuracy of the leveling screw can reach ±0.02mm.
[0033] In some embodiments, the calibration system for the heating base also includes a display screen that provides a human-machine interface, allowing users to more intuitively understand the thickness distribution of the film and the adjustment amount of the adjuster.
[0034] The calibration method for the heating base provided by the present invention will now be described with reference to the accompanying drawings. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a controller such as a set of computer-executable instructions, and although a logical order is shown in the flowcharts, in some cases the steps shown or described may be executed in a different order than that shown here.
[0035] This invention provides a calibration method for a heating base, which can be used in the aforementioned controller. Figure 5 This is a flowchart of a calibration method for a heating base according to an embodiment of the present invention, such as... Figure 5 As shown, the process includes the following steps: Step S501: After maintaining the heating base, obtain the current film thickness data deposited on the wafer surface.
[0036] The current film thickness data refers to the distribution data of the film thickness deposited on the wafer surface after maintaining the heated substrate at various test points. The current film thickness data can be a set of data on the test points and their corresponding thicknesses, or it can be characterized by a thickness distribution heatmap (Map). The thickness distribution heatmap (Map) can characterize the uniformity of film thickness, and ideally, it is a standard Map with a concentric circle shape.
[0037] Specifically, the wafer is placed on the heated base after PM in the CVD equipment, and a film layer is grown on the wafer surface. Then, an optical ellipsometer, a reflectance spectrometer, or other film thickness acquisition device is used to measure the thickness of the film layer at each measurement point, so that the controller can obtain the current film thickness data.
[0038] Step S502: Determine the target thickness deviation data based on the current film thickness data and the target film thickness data of the wafer.
[0039] The target film thickness data refers to the thickness distribution data of the film deposited on the wafer surface at various test points when the heating substrate is in optimal condition (BSL). It is also the film thickness data when the film thickness uniformity is less than or equal to the preset uniformity (e.g., film thickness standard deviation is less than 2%). The target film thickness data can be characterized by a thickness distribution thermogram. The target film thickness data is obtained through measurement and pre-configured in the controller.
[0040] Specifically, after obtaining the current film thickness data, the difference between the target film thickness data and the current film thickness data is determined as the target thickness deviation data.
[0041] Step S503: Determine the target adjustment amount of the adjuster based on the target thickness deviation data and the prediction model.
[0042] The prediction model is used to characterize the mapping relationship between the adjustment amount of the adjuster and the thickness deviation data. The prediction model can be a machine learning model or a mathematical model, and the prediction model is pre-configured in the controller.
[0043] The target adjustment amount refers to the adjustment amount required to transform the current film thickness data into the target film thickness data. The adjustment amount refers to the linear vertical displacement or rotation angle of the adjuster. When there are multiple adjusters, the adjustment amount... This includes the sub-adjustment amount corresponding to each of the multiple adjusters. For example, if the number of adjusters is 2, then the adjustment amount... , This indicates the sub-adjustment amount corresponding to the first adjuster. This indicates the sub-adjustment amount corresponding to the second adjuster.
[0044] It should be understood that each upgrade or rotation of an adjuster will cause a change in the local height of the heating base; that is, the movement of multiple adjusters will change the levelness deviation of the heating base. Changes in the levelness of the heating base will alter the thickness distribution of the film deposited on the wafer surface.
[0045] Specifically, after obtaining the target thickness deviation data, the adjustment amount corresponding to the target thickness deviation data can be obtained based on the mapping relationship, and the adjustment amount corresponding to the target thickness deviation data can be determined as the target adjustment amount.
[0046] Step S504: Control the adjuster to calibrate the level of the heating base according to the target adjustment amount.
[0047] Specifically, the adjuster is moved according to the target adjustment amount to adjust the level of the heating base to the target level, thereby making the wafer deposition film thickness data the target film thickness data. For example, as Figure 6 As shown, the levelness of the heating base deviated after PM. After adjusting the position of the adjuster according to the target adjustment amount, the state of the heating base can be as follows. Figure 7 As shown.
[0048] The heating base calibration method provided in this embodiment, after acquiring the current film thickness data deposited on the wafer surface, determines the target thickness deviation data based on the current film thickness data and the target film thickness data of the wafer. Then, based on the target thickness deviation data and the prediction model, it determines the target adjustment amount of the adjuster and controls the adjuster to calibrate the levelness of the heating base according to the target adjustment amount. This embodiment predicts the target adjustment amount corresponding to the target thickness deviation data through a prediction model. Only one adjustment is needed to bring the deposited film thickness data close to the target, avoiding multiple process test iterations, greatly shortening the rework time after PM, improving debugging efficiency and equipment utilization. Moreover, determining the target adjustment amount through the prediction model can reduce human interference, ensure consistent adjustment results each time, and improve process stability and product yield.
[0049] The present invention also provides another calibration method for the heating base, which can be used in the aforementioned controller. Figure 8 This is a flowchart of another calibration method for a heating base according to an embodiment of the present invention, such as... Figure 8 As shown, the process includes the following steps: Step S801: After maintaining the heating base, obtain the current film thickness data deposited on the wafer surface.
[0050] Please see details Figure 5 Step S501 of the illustrated embodiment will not be described again here.
[0051] Step S802: Determine the target thickness deviation data based on the current film thickness data and the target film thickness data of the wafer.
[0052] Please see details Figure 5 Step S502 of the illustrated embodiment will not be described again here.
[0053] Step S803: Determine the target adjustment amount of the adjuster based on the target thickness deviation data and the prediction model.
[0054] The prediction model is a bidirectional mapping machine learning model. When the thickness deviation data is used as the input of the prediction model, the output of the prediction model is the predicted adjustment amount; when the adjustment amount is used as the input of the prediction model, the output of the prediction model is the predicted thickness deviation data.
[0055] The predictive model is based on a large amount of historical adjustment data (adjustment amount) Trained with thickness deviation data, the prediction model can learn the nonlinear mechanical-process response relationship unique to CVD equipment, achieving accurate prediction from adjustment amount to thickness deviation data, and vice versa.
[0056] For example, step S803 above may include: Step S8031: Input the target thickness deviation data into the prediction model, and determine the initial adjustment amount of the adjuster based on the output of the prediction model.
[0057] The initial adjustment amount is the adjustment amount corresponding to the target thickness deviation data obtained based on the prediction model.
[0058] Specifically, the target thickness deviation data is input into the prediction model, and the output of the prediction model is used as the initial adjustment amount.
[0059] Step S8032: Input the initial adjustment amount into the prediction model, and determine the predicted thickness deviation data based on the output of the prediction model.
[0060] Among them, the predicted thickness deviation data is the thickness deviation data corresponding to the initial adjustment amount, which is obtained based on the prediction model.
[0061] Specifically, after obtaining the initial adjustment amount, the initial adjustment amount is input into the prediction model, and the output of the prediction model is determined as the predicted thickness deviation data.
[0062] Step S8033: Determine the predicted film thickness data based on the predicted thickness deviation data and the current film thickness data.
[0063] Specifically, the sum of the current film thickness data and the predicted thickness deviation data is determined as the predicted film thickness data, which can be characterized by a thickness distribution heatmap.
[0064] The initial adjustment amount is the predicted value of the prediction model. This predicted value may have biases. Inputting the initial adjustment amount into the prediction model to determine the predicted film thickness data can verify the accuracy of the initial adjustment amount in reverse, avoid blind trial and error, and reduce the number of adjustments.
[0065] Step S8034: If the predicted film thickness data and the target film thickness data are consistent, then the initial adjustment amount is determined as the target adjustment amount.
[0066] Specifically, if the difference between the predicted film thickness data and the target film thickness data is less than or equal to a preset difference (e.g., 0.06 mm), it can be determined that the predicted film thickness data and the target film thickness data are consistent; if the difference between the predicted film thickness data and the target film thickness data is greater than the preset difference, it can be determined that the predicted film thickness data and the target film thickness data are inconsistent.
[0067] If the standard deviation of the predicted film thickness data and the standard deviation of the target film thickness data are less than or equal to the preset deviation (e.g., 0.5%), then the predicted film thickness data and the target film thickness data are consistent; if the standard deviation of the predicted film thickness data and the standard deviation of the target film thickness data are greater than the preset deviation (e.g., 0.5%), then the predicted film thickness data and the target film thickness data are inconsistent.
[0068] For example, if the predicted film thickness data and the target film thickness data are inconsistent, the initial adjustment amount is updated according to the preset adjustment amount until the predicted film thickness data obtained based on the updated initial adjustment amount is consistent with the target film thickness data; the updated initial adjustment amount is determined as the target adjustment amount.
[0069] The preset adjustment amount is a fixed value (e.g., 0.02 mm) representing the iteration step size. Specifically, if there is a discrepancy, the initial adjustment amount is updated to the sum or difference between the preset adjustment amount and the initial adjustment amount. Then, the updated initial adjustment amount is input into the prediction model to redetermine the predicted thickness deviation data. Based on the predicted thickness deviation data, the predicted film thickness data is redetermined. If the new predicted film thickness data matches the target film thickness data, the updated initial adjustment amount is determined as the target adjustment amount. If the new predicted film thickness data does not match the target film thickness data, the updated initial adjustment amount is used as the initial adjustment amount. The above process is repeated until the predicted film thickness data obtained based on the updated initial adjustment amount matches the target film thickness data.
[0070] After determining the updated initial adjustment amount as the target adjustment amount, the calibration method for the heating base further includes updating the model parameters in the prediction model based on the target adjustment amount and the target thickness deviation data. Specifically, the target adjustment amount and the target thickness deviation data are used as new samples to update the model parameters (weight parameters) in the prediction model, thereby improving the prediction accuracy of the prediction model.
[0071] Step S804: Control the adjuster to calibrate the level of the heating base according to the target adjustment amount.
[0072] Please see details Figure 5 Step S504 of the illustrated embodiment will not be described again here.
[0073] In this embodiment, the regression model constructed through machine learning can achieve accurate prediction of process response. Moreover, this embodiment does not directly determine the adjustment amount obtained by the prediction model based on the target thickness deviation data as the target adjustment amount. Instead, the adjustment amount is input into the prediction model for reverse verification. Only when the predicted film thickness data and the target film thickness data are consistent is the initial adjustment amount output by the prediction model determined as the target adjustment amount, which can further improve the adjustment accuracy.
[0074] In some embodiments, the calibration system for the heating base further includes a display screen, and the calibration method for the heating base further includes displaying initial adjustment amounts and predicted film thickness data on the display screen.
[0075] Specifically, such as Figure 9 As shown, information such as the initial adjustment amount, predicted film thickness data, and current film thickness data can be displayed on the screen.
[0076] In some embodiments, after calibrating the levelness of the heating base, the calibration method for the heating base may further include the following steps: Step a1: Obtain the actual film thickness data deposited on the wafer surface.
[0077] The actual film thickness data refers to the distribution data of the film thickness at various test points after the heating base is adjusted and deposited on the wafer surface. The actual film thickness data can also be characterized by a thickness distribution thermogram.
[0078] Specifically, the wafer is placed on an adjusted heating base of a CVD machine, and a film layer is grown on the wafer surface. Then, an optical ellipsometer, a reflectance spectrometer, or other film thickness acquisition device is used to measure the thickness of the film layer at various measurement points, so that the controller can obtain the actual film thickness data.
[0079] Step a2: If the actual film thickness data is inconsistent with the target film thickness data, the actual film thickness data is used as the current film thickness data, and the process returns to the step of determining the target thickness deviation data based on the current film thickness data and the target film thickness data of the wafer.
[0080] Specifically, if the actual film thickness data is inconsistent with the target film thickness data, the actual film thickness data is used as the current film thickness data, and the above steps S502 to S504 and step a1 are repeated until the actual film thickness data is consistent with the target film thickness data.
[0081] The calibration method for the heating base provided by this invention will be described in detail below, taking an example where the number of adjusters is two and the film thickness data is characterized by a thickness distribution heat map (Map). The adjuster is a digital display adjuster, which is a leveling screw equipped with a displacement sensor and an adjustment amount display.
[0082] like Figure 10 As shown, the calibration method for the heating base includes the following steps: Step 1: Perform the first process test after PM to measure the current film thickness distribution Map_current.
[0083] Step 2: Determine the thickness deviation distribution between the current Map (Map_current) and the target Map (Map_target). , .
[0084] Step 3: Based on A preliminary screw adjustment plan is obtained through a predictive model, and then generated on the user interface. .
[0085] Step 4: The prediction model is adjusted according to the plan. The predicted adjusted film thickness distribution Map_predict is calculated.
[0086] Step 5: Visualize the prediction map (Map_predict) on the interface and compare it with the target map. If the difference between the prediction map and the target map meets the conditions set by the engineer (preset conditions), then the digital display adjuster will be operated according to the plan to perform precise adjustment. If not, return to step 3 to modify the adjustment plan and re-predict until satisfactory, or the engineer can manually modify the adjustment plan and re-execute step 4.
[0087] Step 6: Perform a verification process test to measure the actual map; if the actual map meets the requirements (consistent with the target map, or the thickness uniformity is less than the preset uniformity), then the process ends, usually one adjustment is enough to approach the target; if the actual map does not meet the requirements (there is a slight deviation), then return to step 2 for a final round of fine-tuning.
[0088] This invention has the following advantages: (1) High calibration accuracy: By combining a high-precision digital display adjuster (±0.02mm) with a prediction model, micron-level precise adjustment is achieved, which significantly improves the uniformity of film thickness.
[0089] (2) Significantly improve adjustment efficiency: avoid multiple process testing iterations, usually one adjustment can approach the target map, greatly shorten the downtime after PM and improve equipment utilization.
[0090] (3) High repeatability of operation: Based on the data-driven prediction model, human factors are reduced, ensuring consistent adjustment results each time, and improving process stability and product yield.
[0091] (4) Reduce reliance on engineers’ experience: Through visual interfaces and predictive simulations, the adjustment process is standardized and made intelligent, reducing the difficulty of operation and training costs.
[0092] (5) Wide applicability: It can be flexibly applied to various CVD equipment platforms (such as PECVD, MOCVD, etc.), and has good promotional value and industry applicability.
[0093] This embodiment also provides a calibration system for a heating base. The calibration system includes an adjuster and a controller for adjusting the levelness of the heating base. The controller is used to acquire the current film thickness data deposited on the wafer surface after maintaining the heating base. The controller is also used to determine target thickness deviation data based on the current film thickness data and the target film thickness data of the wafer. The controller is also used to determine the target adjustment amount of the adjuster based on the target thickness deviation data and a prediction model, wherein the prediction model is used to characterize the mapping relationship between the adjustment amount of the adjuster and the thickness deviation data. The controller is also used to control the adjuster to calibrate the levelness of the heating base according to the target adjustment amount.
[0094] Optionally, the adjuster includes a leveling screw equipped with a displacement sensor and an adjustment amount display. In this embodiment, a digital, real-time feedback adjuster is used to replace experience-based mechanical adjustment. The controller can understand the current adjustment amount of the leveling screw in real time, avoiding the current adjustment amount from exceeding or failing to reach the target adjustment amount.
[0095] The controller provided in this embodiment of the invention can execute the calibration method of the heating base provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the various modules and units described above are the same as in the corresponding embodiments described above, and will not be repeated here.
[0096] Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.
[0097] The following is a detailed reference. Figure 11 The diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, a graphics processing unit, etc.) 1101, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1102 or a program loaded from memory 1108 into random access memory (RAM) 1103. The RAM 1103 also stores various programs and data required for the operation of the electronic device. The processor 1101, ROM 1102, and RAM 1103 are interconnected via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.
[0098] Typically, the following devices can be connected to I / O interface 1105: input devices 1106 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 1107 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 1108 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1109. Communication device 1109 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 11 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.
[0099] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 1109, or installed from a memory 1108, or installed from a ROM 1102. When the computer program is executed by the processor 1101, it performs the functions defined in the calibration method for the heating base of the embodiments of the present invention.
[0100] Figure 11 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.
[0101] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that the computer, processor, microprocessor controller, or programmable hardware includes storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the calibration method for the heating base shown in the above embodiments is implemented.
[0102] A portion of this invention can be applied to computer program products, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installation program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.
[0103] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.
Claims
1. A calibration method for a heating base, characterized in that, A controller is used in a calibration system for a heating base, the calibration system including the controller and an adjuster for adjusting the levelness of the heating base, the method comprising: After maintaining the heating base, acquire the current film thickness data deposited on the wafer surface; Based on the current film thickness data and the target film thickness data of the wafer, the target thickness deviation data is determined; Based on the target thickness deviation data and the prediction model, the target adjustment amount of the adjuster is determined, wherein the prediction model is used to characterize the mapping relationship between the adjustment amount of the adjuster and the thickness deviation data; The adjuster is controlled to calibrate the levelness of the heating base according to the target adjustment amount.
2. The calibration method for the heating base according to claim 1, characterized in that, The prediction model is a bidirectional mapping machine learning model. Determining the target adjustment amount of the adjuster based on the target thickness deviation data and the prediction model includes: The target thickness deviation data is input into the prediction model, and the initial adjustment amount of the adjuster is determined based on the output of the prediction model. The initial adjustment amount is input into the prediction model, and the predicted thickness deviation data is determined based on the output of the prediction model. The predicted film thickness data is determined based on the predicted thickness deviation data and the current film thickness data; If the predicted film thickness data and the target film thickness data are consistent, then the initial adjustment amount is determined as the target adjustment amount.
3. The calibration method for the heating base according to claim 2, characterized in that, The calibration method for the heating base also includes: If the predicted film thickness data and the target film thickness data are inconsistent, the initial adjustment amount is updated according to the preset adjustment amount until the predicted film thickness data obtained based on the updated initial adjustment amount is consistent with the target film thickness data. The updated initial adjustment amount is determined as the target adjustment amount.
4. The calibration method for the heating base according to claim 3, characterized in that, After determining the updated initial adjustment amount as the target adjustment amount, the calibration method for the heating base further includes: The model parameters in the prediction model are updated based on the target adjustment amount and the target thickness deviation data.
5. The calibration method for the heating base according to any one of claims 2 to 4, characterized in that, The calibration system for the heating base also includes a display screen, and the calibration method for the heating base further includes: The initial adjustment amount and the predicted film thickness data are displayed on the screen.
6. The calibration method for the heating base according to any one of claims 1 to 4, characterized in that, Both the current film thickness data and the target film thickness data are characterized by thickness distribution heatmaps.
7. The calibration method for the heating base according to any one of claims 1 to 4, characterized in that, After calibrating the levelness of the heating base, the calibration method for the heating base further includes: Obtain the actual film thickness data deposited on the wafer surface; If the actual film thickness data is inconsistent with the target film thickness data, the actual film thickness data is used as the current film thickness data, and the process returns to the step of determining the target thickness deviation data based on the current film thickness data and the target film thickness data of the wafer.
8. A calibration system for a heating base, characterized in that, The calibration system for the heating base includes an adjuster and a controller for adjusting the levelness of the heating base; The controller is used to acquire the current film thickness data deposited on the wafer surface after maintaining the heating base; The controller is further configured to determine target thickness deviation data based on the current film thickness data and the target film thickness data of the wafer; The controller is further configured to determine the target adjustment amount of the adjuster based on the target thickness deviation data and the prediction model, wherein the prediction model is used to characterize the mapping relationship between the adjustment amount of the adjuster and the thickness deviation data; The controller is also used to control the adjuster to calibrate the levelness of the heating base according to the target adjustment amount.
9. The calibration system for the heating base according to claim 8, characterized in that, The adjuster includes a leveling screw equipped with a displacement sensor and an adjustment amount display.
10. A chemical vapor deposition apparatus, characterized in that, The calibration system includes the heating base as described in claim 8 or 9.