Control method of semiconductor wafer processing equipment, equipment and medium

Abstract

The invention discloses a control method of semiconductor wafer processing equipment, equipment and a medium, and relates to the technical field of semiconductor manufacturing. The method comprises the following steps: monitoring the axial runout of the rotating base in real time, and acquiring the clamping stress distribution of a clamping part through an optical fiber strain gauge; collecting surface temperature field data of the rotating base, establishing a thermal-mechanical coupling model of the rotating base and the clamping part in combination with the axial runout and the clamping stress distribution, and calculating to obtain a deformation quantity predicted value; according to the predicted value of the deformation quantity, calculating a rotating speed compensation value for a target rotating speed of a rotating base driving motor, and calculating a displacement correction quantity for a piezoelectric actuator of the clamping part; and controlling the rotating speed of the driving motor and the displacement of the piezoelectric actuator in real time according to the rotating speed compensation value and the displacement correction amount. According to the method, through the steps of real-time monitoring, thermal coupling model establishment, real-time compensation, correction and the like, the machining precision is improved, the stability is enhanced, and the clamping force distribution is optimized.

Description

Technical Field

[0001] The present application relates to the field of semiconductor manufacturing technology, and in particular to a control method, equipment, and medium for semiconductor wafer processing equipment. Background Art

[0002] In semiconductor wafer manufacturing, etching and cleaning in wet processes require extremely high precision in equipment motion control. Traditional equipment relies on fixed PID (Proportional-Integral-Derivative) control, but thermal deformation during high-speed rotation leads to uneven wafer clamping force, further causing micron-level position offset.

[0003] The prior art CN112735805A is a production process for inductor coils that uses a temperature compensation algorithm. However, it does not address the synergistic effects of thermomechanical coupling and dynamic wear, requiring frequent shutdowns for calibration, for example, every eight hours, resulting in production capacity loss. In addition, wear detection relies on manual microscopic observation and cannot respond in real time.

[0004] Through the above analysis, the problems and defects of the existing technology are as follows:

[0005] In conventional semiconductor wafer manufacturing, thermal deformation during high-speed rotation causes uneven wafer clamping force, which further leads to positional offset and poor control accuracy. Summary of the Invention

[0006] The embodiments of the present application provide a control method, equipment and medium for semiconductor wafer processing equipment, which can solve the problem in the prior art semiconductor wafer manufacturing that, during high-speed rotation, thermal deformation causes uneven wafer clamping force, further causing position offset and poor control accuracy.

[0007] In a first aspect, an embodiment of the present application provides a control method for semiconductor wafer processing equipment, the method comprising: based on the semiconductor wafer processing equipment including a rotating base and a clamping component, the axial runout of the rotating base is monitored in real time by a laser displacement sensor, and the clamping stress distribution of the clamping component is obtained by an optical fiber strain gauge; the surface temperature field data of the rotating base is collected, and a thermomechanical coupling model of the rotating base and the clamping component is established in combination with the axial runout and the clamping stress distribution, and a deformation variable prediction value is calculated; according to the deformation variable prediction value, a speed compensation value is calculated for the target speed of the rotating base drive motor, and a displacement correction value is calculated for the piezoelectric actuator of the clamping component; according to the speed compensation value and the displacement correction value, the speed of the drive motor and the displacement of the piezoelectric actuator are controlled in real time.

[0008] In one implementation of the present application, the surface temperature field data of the rotating base is collected, and combined with the axial runout and the clamping stress distribution, a thermal coupling model of the rotating base and the clamping component is established, and the deformation variable prediction value is calculated, specifically including: extracting the characteristic curve of temperature change with time through the surface temperature field data; introducing the material thermal expansion coefficient database, and constructing a three-dimensional transient model including contact thermal resistance based on the characteristic curve and the material thermal expansion coefficient database; defining the boundary condition of the three-dimensional transient model as a composite load of vacuum adsorption force and centrifugal force; and outputting the deformation variable prediction value of the rotating base at different speeds by iteratively solving the three-dimensional transient model.

[0009] In one implementation of the present application, the method also includes: obtaining topographic image data of the surface of the clamping component through a confocal microscope to determine whether there is a wear area; if there is a wear area, inputting the topographic image data into a pre-trained convolutional neural network, extracting the position coordinates and depth value of the wear area, and generating a wear feature vector; when the maximum radial wear depth in the wear feature vector is greater than the wear threshold, triggering an automatic replacement instruction, and updating the parameters of the contact thermal resistance in the thermomechanical coupling model based on the current wear status.

[0010] In one implementation of the present application, when there is a worn area, the topographic image data is input into a pre-trained convolutional neural network to extract the position coordinates and depth values ​​of the worn area. Before generating the wear feature vector, the method also includes: based on the ImageNet pre-trained model, using transfer learning to initialize the network weights, and using an image database annotated with the type and degree of wear for fine-tuning, the wear types include scratches, dents and corrosion; designing a dual-branch network structure, wherein the first branch extracts geometric features, the geometric features include concentric circle distortion rate and stripe break length, and the second branch extracts texture features, the texture features include surface roughness and reflectivity distribution.

[0011] In one implementation of the present application, the method further includes: triggering an emergency deceleration program when it is detected that the axial runout exceeds a preset distance for a consecutive preset number of times; locating the wear area, driving the robotic arm to spray perfluoropolyether lubricant, and automatically restarting the process after recovery.

[0012] In one implementation of the present application, a speed compensation value is calculated for the target speed of the rotating base drive motor based on the deformation variable prediction value, and a displacement correction value is calculated for the piezoelectric actuator of the clamping component, specifically including: comparing the deformation variable prediction value with the expected deformation variable value, and calculating the difference as an error index; setting a rolling time domain window based on the deviation between the current axial runout and the clamping stress, and the window length covers at least one rotation cycle of the rotating base; constructing an objective function, the objective function including the target value of the axial runout and the mean value of the clamping stress; generating a compensation speed sequence and a displacement correction value sequence within a future preset period.

[0013] In one implementation of the present application, the method also includes: obtaining edge vibration spectrum data of the rotating base, performing fast Fourier transform on the edge vibration spectrum data, and extracting the amplitude and phase of the fundamental frequency and harmonic components; calculating the imbalance vector of the harmonic components through the least squares method to generate the mass and position of the counterweight block; and automatically installing the compensating counterweight by driving the micro-robotic arm to make the residual vibration amount less than a preset threshold.

[0014] In one implementation of the present application, the method further includes: coating an alumina thermal insulation coating on the surface of the rotating base, and monitoring the temperature difference between the inside and outside of the coating in real time; when the temperature difference is greater than a temperature threshold, starting an air cooling nozzle to perform non-contact cooling of the base.

[0015] In a second aspect, an embodiment of the present application further provides a control device for a semiconductor wafer processing device, the device comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so as to enable the at least one processor to: based on the fact that the semiconductor wafer processing device comprises a rotating base and a clamping component, monitor the axial runout of the rotating base in real time through a laser displacement sensor, and simultaneously obtain the clamping stress distribution of the clamping component through an optical fiber strain gauge; collect surface temperature field data of the rotating base, and establish a thermomechanical coupling model of the rotating base and the clamping component in combination with the axial runout and the clamping stress distribution, and calculate a predicted value of the deformation variable; calculate a speed compensation value for the target speed of the rotating base drive motor based on the predicted value of the deformation variable, and simultaneously calculate a displacement correction value for the piezoelectric actuator of the clamping component; and control the speed of the drive motor and the displacement of the piezoelectric actuator in real time based on the speed compensation value and the displacement correction value.

[0016] On the third aspect, an embodiment of the present application also provides a non-volatile computer storage medium for controlling a semiconductor wafer processing device, which stores computer executable instructions, and the computer executable instructions are set to: based on the semiconductor wafer processing device including a rotating base and a clamping component, the axial runout of the rotating base is monitored in real time by a laser displacement sensor, and the clamping stress distribution of the clamping component is obtained by an optical fiber strain gauge; the surface temperature field data of the rotating base is collected, and combined with the axial runout and the clamping stress distribution, a thermal coupling model of the rotating base and the clamping component is established, and a deformation variable prediction value is calculated; according to the deformation variable prediction value, a speed compensation value is calculated for the target speed of the rotating base drive motor, and at the same time, a displacement correction value is calculated for the piezoelectric actuator of the clamping component; according to the speed compensation value and the displacement correction value, the speed of the drive motor and the displacement of the piezoelectric actuator are controlled in real time.

[0017] The embodiments of the present application provide a control method, device, and medium for semiconductor wafer processing equipment. The method uses a laser displacement sensor to monitor the axial runout of the rotating base in real time, and uses an optical fiber strain gauge to obtain the clamping stress distribution of the clamping component. This method can accurately grasp the dynamic changes of the equipment during operation. A thermomechanical coupling model is established in combination with surface temperature field data to calculate the predicted value of the deformation variable, taking into account the influence of thermal deformation on processing accuracy, so that the deformation variable can be predicted and controlled more accurately. Based on the predicted value of the deformation variable, a speed compensation value is calculated for the target speed of the rotating base drive motor, and a displacement correction value is calculated for the piezoelectric actuator of the clamping component. This real-time compensation and correction mechanism helps to maintain the stability of the equipment during high-speed rotation. Real-time control of the speed of the drive motor and the displacement of the piezoelectric actuator ensures the dynamic adjustment capability of the equipment during operation, further enhancing the stability of the system. Wear detection replaces manual inspections and maintains response time. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 A flow chart of a control method for semiconductor wafer processing equipment provided in an embodiment of the present application;

[0020] Figure 2 A schematic diagram of the internal structure of a control device for semiconductor wafer processing equipment provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0022] The embodiments of the present application provide a control method, equipment and medium for semiconductor wafer processing equipment, which solves the problem in the prior art of semiconductor wafer manufacturing that, during high-speed rotation, thermal deformation causes uneven wafer clamping force, further causing position offset and poor control accuracy.

[0023] The technical solutions proposed in the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0024] Figure 1This is a flow chart of a control method for semiconductor wafer processing equipment provided in an embodiment of the present application. Figure 1 As shown, the embodiment of the present application provides a control method for semiconductor wafer processing equipment, which specifically includes the following steps:

[0025] Step 10: Based on the fact that the semiconductor wafer processing equipment includes a rotating base and a clamping component, the axial runout of the rotating base is monitored in real time by a laser displacement sensor, and the clamping stress distribution of the clamping component is obtained by an optical fiber strain gauge.

[0026] In this step, for example, a laser displacement sensor with a wavelength of 632.8 nm and a sampling rate of 10 kHz monitors the axial runout of the rotating base in real time, and a fiber optic strain gauge with a resolution of 0.1 με obtains the clamping stress distribution of the clamping component to generate a clamping stress matrix.

[0027] Step 20: Collect the surface temperature field data of the rotating base, and combine it with the axial runout and clamping stress distribution to establish a thermal-mechanical coupling model of the rotating base and the clamping component, and calculate the predicted value of the deformation variable.

[0028] As an optional embodiment, the surface temperature field data of the rotating base is collected, and combined with the axial runout and the clamping stress distribution, a thermal coupling model of the rotating base and the clamping component is established, and the deformation variable prediction value is calculated. Specifically, it may include: Step 201: Extracting the characteristic curve of temperature change with time through the surface temperature field data; Step 202: Introducing the material thermal expansion coefficient database, and constructing a three-dimensional transient model including contact thermal resistance based on the characteristic curve and the material thermal expansion coefficient database; Step 203: Defining the boundary condition of the three-dimensional transient model as a composite load of vacuum adsorption force and centrifugal force; Step 204: Outputting the deformation variable prediction value of the rotating base at different speeds by iteratively solving the three-dimensional transient model.

[0029] In this step, based on the material thermal expansion coefficient database, the thermal expansion coefficient of silicon carbide is 4.5×10 -6 / ℃, a three-dimensional transient model including contact thermal resistance was constructed, and the boundary conditions of the model were defined as a composite load of 50N at a vacuum adsorption force of -90kPa and a centrifugal force at a rotation speed of 3000rpm.

[0030] Step 30: Calculate a speed compensation value for the target speed of the rotating base drive motor based on the predicted value of the deformation amount, and simultaneously calculate a displacement correction value for the piezoelectric actuator of the clamping component;

[0031] As an optional embodiment, based on the deformation variable prediction value, a speed compensation value is calculated for the target speed of the rotating base drive motor, and at the same time, a displacement correction value is calculated for the piezoelectric actuator of the clamping component. Specifically, it may include: step 301: comparing the deformation variable prediction value with the expected deformation variable value, and calculating the difference as an error index; step 302: setting a rolling time domain window according to the deviation between the current axial runout and the clamping stress, and the window length covers at least one rotation cycle of the rotating base; step 303: constructing an objective function, the objective function including the target value of the axial runout and the mean value of the clamping stress; step 304: generating a compensation speed sequence and a displacement correction sequence within a future preset period.

[0032] In this step, set the rolling time domain optimization window, for example, the duration is 300ms, which corresponds to 1.5 cycles at a speed of 3000rpm. Where w1 = 0.6 (weight of deviation between axial runout and target value), w2 = 0.3 (weight of deviation between clamping force and mean value), w3 = 0.1 (weight of time delay), x k Current axial position, x ref is the target value of axial runout, Fk is the current clamping force, and Favg is the average clamping force. The following constraints are introduced: the speed change rate of the driving motor is ≤500rpm / s, and the response delay of the piezoelectric actuator is ≤5ms. Hardware acceleration is achieved through FPGA, and the interior point method is used to solve the optimization problem to generate the compensation speed sequence and displacement correction value sequence for the next three control cycles.

[0033] Step 40: According to the speed compensation value and the displacement correction amount, the speed of the driving motor and the displacement of the piezoelectric actuator are controlled in real time.

[0034] As an optional embodiment, the method may also include: obtaining topographic image data of the surface of the clamping component through a confocal microscope to determine whether there is a wear area; if there is a wear area, inputting the topographic image data into a pre-trained convolutional neural network, extracting the position coordinates and depth value of the wear area, and generating a wear feature vector; when the maximum radial wear depth in the wear feature vector is greater than the wear threshold, triggering an automatic replacement instruction, and updating the parameters of the contact thermal resistance in the thermomechanical coupling model based on the current wear status.

[0035] In this step, based on the micron-scale feature pattern on the surface of the clamping component, the concentric circle spacing is 10 μm, the radial stripe width is 2 μm, and the lateral resolution is 0.2 μm through a confocal microscope to obtain morphological image data. The morphological image data is input into the pre-trained convolutional neural network CNN, MobileNetV3 architecture, and the position coordinates and depth values ​​of the wear area are extracted to generate a wear feature vector. When the maximum radial wear depth in the wear feature vector is greater than 3 μm, the automatic replacement instruction is triggered, and the contact thermal resistance parameters in the thermomechanical coupling model are updated based on the current wear state, and the update amplitude is a square function of the wear depth.

[0036] As an optional embodiment, when there is a worn area, the topographic image data is input into a pre-trained convolutional neural network to extract the position coordinates and depth values ​​of the worn area. Before generating the wear feature vector, the method may also include: based on the ImageNet pre-trained model, using transfer learning to initialize the network weights, and using an image database annotated with the type and degree of wear for fine-tuning, where the wear types include scratches, dents, and corrosion; designing a dual-branch network structure, where the first branch extracts geometric features, including concentric circle distortion rate and stripe break length, and the second branch extracts texture features, including surface roughness and reflectivity distribution.

[0037] In this step, for example, 5,000 annotated images are used for fine-tuning, with a learning rate of 0.001 and 50 iterations. The key detection areas are visualized through gradient-weighted class activation mapping (Grad-CAM), and a wear quantification report with a confidence level of ≥90% is output.

[0038] As an optional embodiment, the method may further include: triggering an emergency deceleration program when it is detected that the axial runout exceeds a preset distance for a consecutive preset number of times; locating the wear area, driving the robotic arm to spray perfluoropolyether lubricant, and automatically restarting the process after recovery.

[0039] In this step, for example, when the axial runout is detected to exceed 1 μm three times in a row, the emergency deceleration program is triggered and the rotation speed is reduced to below 500 rpm; the abnormal friction point is located by the acoustic emission sensor, and the robotic arm is driven to spray perfluoropolyether lubricant with a viscosity of 100 cSt. After recovery, the process is automatically restarted.

[0040] As an optional embodiment, the method may also include: obtaining edge vibration spectrum data of the rotating base, performing fast Fourier transform on the edge vibration spectrum data, and extracting the amplitude and phase of the fundamental frequency and harmonic components; calculating the imbalance vector of the harmonic components by the least squares method, and generating the mass and position of the counterweight block; and automatically installing the compensating counterweight by driving the micro-robotic arm to make the residual vibration amount less than a preset threshold.

[0041] In this step, based on the piezoelectric vibration sensor array embedded in the edge of the rotating base, for example, 16 sensors with equal angle distribution, the vibration spectrum data is obtained with a sampling frequency of ≥50kHz, and the vibration spectrum data is subjected to fast Fourier transform to extract the amplitude and phase of the fundamental frequency (corresponding to the rotational speed frequency) and the second harmonic component. Based on the harmonic components, the unbalance vector is calculated by the least squares method, and the mass and position adjustment scheme of the counterweight block is generated. The micro-manipulator is driven with a repeatable positioning accuracy of ±5μm, and the compensation counterweight is automatically installed to make the residual vibration <0.1g, and the dynamic balance parameters are updated to the control algorithm. The calculation of the unbalance vector by the least squares method is specifically to decompose the vibration signal into radial and tangential components in the polar coordinate system. The radial component is related to the centrifugal force, and the tangential component is related to the friction force. According to the mass distribution model of the rotating base, in the embodiment of the present application, the density of the silicon carbide matrix is ​​3.21g / cm 3 Taking the unbalance phase angle as an example, the correlation equation between the phase angle of the unbalance amount and the phase of the harmonic component is established; the required counterweight mass is solved by nonlinear optimization to meet the following requirements:

[0042]

[0043] where m i is the mass of the counterweight, r i is the installation radius, θi is the phase angle, ΔUx and ΔUy are the unbalanced components.

[0044] As an optional embodiment, the method may also include: coating an alumina thermal insulation coating on the surface of the rotating base, and monitoring the temperature difference between the inside and outside of the coating in real time; when the temperature difference is greater than a temperature threshold, starting an air cooling nozzle to perform non-contact cooling on the base.

[0045] In this step, an alumina thermal insulation coating with a thickness of 50 μm and a thermal conductivity of 30 W / m·K is applied to the surface of the rotating base. The temperature difference between the inside and outside of the coating is monitored in real time by a thermocouple. When the temperature difference is greater than 10°C, an air cooling nozzle is activated, for example, with a nitrogen flow rate of 10 L / min, to cool the base non-contact to a temperature gradient of ≤2°C / cm.

[0046] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, the embodiment of this application also provides a control device for semiconductor wafer processing equipment, whose structure is as follows: Figure 2 shown.

[0047] Figure 2 This is a schematic diagram of the internal structure of a control device for a semiconductor wafer processing device provided in an embodiment of the present application. Figure 2 As shown, the equipment includes:

[0048] at least one processor 201;

[0049] and, a memory 202 communicatively coupled to the at least one processor;

[0050] Among them, the memory 202 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 201 so that the at least one processor 201 can: based on the semiconductor wafer processing equipment including a rotating base and a clamping component, monitor the axial runout of the rotating base in real time through a laser displacement sensor, and obtain the clamping stress distribution of the clamping component through an optical fiber strain gauge; collect surface temperature field data of the rotating base, and combine the axial runout and the clamping stress distribution to establish a thermal coupling model of the rotating base and the clamping component, and calculate the deformation variable prediction value; according to the deformation variable prediction value, calculate the speed compensation value for the target speed of the rotating base drive motor, and calculate the displacement correction value for the piezoelectric actuator of the clamping component; according to the speed compensation value and the displacement correction value, control the speed of the drive motor and the displacement of the piezoelectric actuator in real time.

[0051] Some embodiments of the present application provide corresponding Figure 1 A non-volatile computer storage medium for controlling semiconductor wafer processing equipment stores computer-executable instructions, wherein the computer-executable instructions are configured to: based on the semiconductor wafer processing equipment including a rotating base and a clamping component, monitor the axial runout of the rotating base in real time through a laser displacement sensor, and simultaneously obtain the clamping stress distribution of the clamping component through an optical fiber strain gauge; collect surface temperature field data of the rotating base, and establish a thermal-mechanical coupling model of the rotating base and the clamping component in combination with the axial runout and the clamping stress distribution, and calculate a predicted value of the deformation variable; calculate a speed compensation value for a target speed of a rotating base drive motor based on the predicted value of the deformation variable, and simultaneously calculate a displacement correction value for a piezoelectric actuator of the clamping component; and control the speed of the drive motor and the displacement of the piezoelectric actuator in real time based on the speed compensation value and the displacement correction value.

[0052] The various embodiments in this application are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences from the other embodiments. In particular, the IoT device and media embodiments are generally similar to the method embodiments, so their description is relatively simple. For relevant portions, refer to the description of the method embodiments.

[0053] The system and medium provided in the embodiments of the present application correspond one-to-one to the method. Therefore, the system and medium also have similar beneficial technical effects to their corresponding methods. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0054] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0055] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0056] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0057] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0058] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0059] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0060] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0061] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0062] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A control method for semiconductor wafer processing equipment, characterized in that: The method comprises: Based on the semiconductor wafer processing equipment including a rotating base and a clamping component, the axial runout of the rotating base is monitored in real time by a laser displacement sensor, and the clamping stress distribution of the clamping component is obtained by an optical fiber strain gauge; Collecting surface temperature field data of the rotating base, and combining the axial runout and clamping stress distribution, establishing a thermal-mechanical coupling model of the rotating base and the clamping component, and calculating a predicted value of the deformation variable; calculating a speed compensation value for a target speed of the rotating base drive motor according to the predicted value of the deformation amount, and calculating a displacement correction value for the piezoelectric actuator of the clamping component; The rotation speed of the driving motor and the displacement of the piezoelectric actuator are controlled in real time according to the rotation speed compensation value and the displacement correction amount.

2. The control method of semiconductor wafer processing equipment according to claim 1, characterized in that: The surface temperature field data of the rotating base is collected, and combined with the axial runout and the clamping stress distribution, a thermal-mechanical coupling model of the rotating base and the clamping component is established to calculate the deformation prediction value, specifically including: Extracting a characteristic curve of temperature variation over time through the surface temperature field data; A material thermal expansion coefficient database is introduced, and a three-dimensional transient model including contact thermal resistance is constructed according to the characteristic curve and the material thermal expansion coefficient database; The boundary condition of the three-dimensional transient model is defined as a composite load of vacuum adsorption force and centrifugal force; The three-dimensional transient model is solved iteratively to output predicted values ​​of the deformation of the rotating base at different rotational speeds.

3. The control method of semiconductor wafer processing equipment according to claim 2, characterized in that: The method further comprises: Obtaining topographic image data of the surface of the clamping component through a confocal microscope to determine whether there is a worn area; When the wear area exists, the topographic image data is input into a pre-trained convolutional neural network to extract the position coordinates and depth value of the wear area to generate a wear feature vector; When the maximum radial wear depth in the wear feature vector is greater than a wear threshold, an automatic replacement instruction is triggered, and the parameters of the contact thermal resistance in the thermomechanical coupling model are updated based on the current wear state.

4. The control method of semiconductor wafer processing equipment according to claim 3, characterized in that: When the wear area exists, the method further includes: inputting the topographic image data into a pre-trained convolutional neural network to extract the position coordinates and depth value of the wear area, and generating a wear feature vector. Based on the ImageNet pre-trained model, we used transfer learning to initialize the network weights and fine-tuned them using a database of images annotated with the types and degrees of wear, including scratches, dents, and corrosion. A dual-branch network structure is designed, wherein the first branch extracts geometric features, including concentric circle distortion rate and stripe break length, and the second branch extracts texture features, including surface roughness and reflectivity distribution.

5. The control method of semiconductor wafer processing equipment according to claim 3, characterized in that: The method further comprises: When it is detected that the axial runout exceeds a preset distance for a consecutive preset number of times, an emergency deceleration program is triggered; The wear area is located, the robotic arm is driven to spray perfluoropolyether lubricant, and the process is automatically restarted after recovery.

6. The control method of semiconductor wafer processing equipment according to claim 1, characterized in that: Calculating a speed compensation value for a target speed of the rotating base drive motor according to the deformation prediction value, and calculating a displacement correction value for the piezoelectric actuator of the clamping component, specifically including: Comparing the predicted value of the deformation variable with the expected deformation variable value, and calculating the difference as an error indicator; According to the deviation between the current axial runout and the clamping stress, a rolling time domain window is set, wherein the window duration covers at least one rotation cycle of the rotating base; Constructing an objective function, wherein the objective function includes a target value of the axial runout and a mean value of the clamping stress; Generate a compensation speed sequence and a displacement correction sequence within a future preset period.

7. The control method of semiconductor wafer processing equipment according to claim 1, characterized in that: The method further comprises: Acquiring edge vibration spectrum data of the rotating base, performing fast Fourier transform on the edge vibration spectrum data, and extracting the amplitude and phase of the fundamental frequency and harmonic components; Calculate the unbalance vector of the harmonic component by the least square method to generate the mass and position of the counterweight; By driving the micro-manipulator to automatically install the compensating weight, the residual vibration amount is reduced to less than the preset threshold.

8. The control method of semiconductor wafer processing equipment according to claim 1, characterized in that: The method further comprises: Coating an alumina thermal insulation coating on the surface of the rotating base and monitoring the temperature difference between the inside and outside of the coating in real time; When the temperature difference is greater than the temperature threshold, the air cooling nozzle is started to perform non-contact cooling on the base.

9. A control device for semiconductor wafer processing equipment, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Based on the semiconductor wafer processing equipment including a rotating base and a clamping component, the axial runout of the rotating base is monitored in real time by a laser displacement sensor, and the clamping stress distribution of the clamping component is obtained by an optical fiber strain gauge; Collecting surface temperature field data of the rotating base, and combining the axial runout and clamping stress distribution to establish a thermal-mechanical coupling model of the rotating base and the clamping component, and calculating a predicted value of the deformation variable; calculating a speed compensation value for a target speed of the rotating base drive motor according to the predicted value of the deformation amount, and calculating a displacement correction value for the piezoelectric actuator of the clamping component; The rotation speed of the driving motor and the displacement of the piezoelectric actuator are controlled in real time according to the rotation speed compensation value and the displacement correction amount.

10. A non-volatile computer storage medium for controlling semiconductor wafer processing equipment, storing computer-executable instructions, characterized in that: The computer executable instructions are configured to: Based on the semiconductor wafer processing equipment including a rotating base and a clamping component, the axial runout of the rotating base is monitored in real time by a laser displacement sensor, and the clamping stress distribution of the clamping component is obtained by an optical fiber strain gauge; Collecting surface temperature field data of the rotating base, and combining the axial runout and clamping stress distribution to establish a thermal-mechanical coupling model of the rotating base and the clamping component, and calculating a predicted value of the deformation variable; calculating a speed compensation value for a target speed of the rotating base drive motor according to the predicted value of the deformation amount, and calculating a displacement correction value for the piezoelectric actuator of the clamping component; The rotation speed of the driving motor and the displacement of the piezoelectric actuator are controlled in real time according to the rotation speed compensation value and the displacement correction amount.

Images