Displacement Measurement in Semiconductor Wafer Processing

Abstract

A wafer that starts as a flat surface during the semiconductor manufacturing process may warp or curve as layers and features are added to the underlying substrate. This warp can be detected during the manufacturing process by rotating the wafer adjacent to a displacement sensor. The displacement sensor generates displacement data relative to a baseline measurement to identify areas of the wafer that warp up and down. The displacement data can then be mapped to positions on the wafer relative to alignment features. This mapping can then be used to adjust parameters of subsequent semiconductor processes, including how the carrier head on the polishing process holds the wafer or applies pressure to the wafer as the wafer is polished. A model can be trained to provide control signals to the polishing / washing process or to generate measurement data.

Description

Technical Field

[0001] Cross - Reference to Related Applications

[0001] This application is a continuation - in - part of U.S. application Ser. No. 17 / 334,407, filed on May 28, 2021, which is hereby incorporated by reference herein in its entirety.

[0002]

[0002] This disclosure generally relates to the measurement of wafer warp between semiconductor manufacturing processes. Specifically, this disclosure describes measuring displacement data around a wafer to characterize the warp / curvature of the wafer, and then using that displacement data to control subsequent processes to correct for the warp / curvature.

Background Art

[0003]

[0003] Integrated circuits are typically formed on a substrate by sequentially depositing conductive, semiconductive, and / or insulating layers on a silicon wafer. In various manufacturing processes, planarization of the layers on the substrate is used between processing steps. In some applications, such as polishing a metal layer to form vias, plugs, and / or lines in trenches of a patterned layer, the upper layer is planarized until the upper surface of the patterned layer is exposed. In other applications, such as planarizing a dielectric layer for photolithography, the upper layer is polished until a desired thickness remains on top of the lower layer.

[0004]

[0004] Chemical - mechanical polishing (CMP) is one common method of planarization. In this planarization method, it is usually necessary to attach the substrate to a carrier or polishing head. The exposed surface of the substrate is typically positioned in contact with a rotating polishing pad. The carrier head applies a controllable load to the substrate, pressing the substrate against the polishing pad. Typically, a polishing slurry for polishing is supplied to the surface of the polishing pad.

[0005]

[0005] One problem in CMP and other semiconductor processes is to keep the surface on the wafer flat. Even if the wafer starts as a relatively flat silicon crystal, various semiconductor processes can deposit, grow, add, etch, remove, and / or otherwise dispose layers or features on the wafer. These additional layers and features can stack up and cause stress on the wafer. And that stress can cause the wafer to curve or warp. This warping can cause the problem that the wafer surface becomes non-uniform during polishing or cleaning of the wafer surface.

Summary of the Invention

[0006]

[0006] In some embodiments, the system may include a platform configured to support a wafer and rotate the wafer around the center of the wafer, and one or more displacement sensors arranged to measure the displacement of the wafer when the wafer rotates.

[0007]

[0007] In some embodiments, a method of measuring the displacement of a wafer between semiconductor manufacturing processes includes rotating the wafer around the center of the wafer, measuring the displacement of the wafer at a predetermined distance from the center of the wafer when the wafer rotates to generate displacement data, and using the displacement data to control a polishing process or a cleaning process performed on the wafer.

[0008]

[0008] In some embodiments, when executed by one or more processors, the non-transitory computer-readable medium causes the one or more processors to receive displacement data generated using a displacement sensor for a wafer, the displacement data indicating a curved or warped area on the wafer; identify parameters of a carrier head corresponding to a location of the curved or warped area on the wafer, the carrier head being part of a chemical mechanical polishing (CMP) apparatus or a wafer cleaning apparatus; and adjust the parameters of the carrier head to correct the curved or warped area on the wafer during a cleaning or polishing process. The non-transitory computer-readable medium may include instructions that cause the one or more processors to perform the operations including those described above.

[0009]

[0009] In any embodiment, any and all of the following features may be implemented in any combination, without limitation. The system may also include an alignment sensor arranged to detect a notch in the wafer as the wafer rotates. One or more displacement sensors may include laser displacement sensors. The alignment sensor may include a through-beam sensor. Also, one or more displacement sensors may be arranged to detect a notch in the wafer as the wafer rotates. One or more displacement sensors may include a displacement sensor arranged above the wafer. One or more displacement sensors may include a displacement sensor arranged below the wafer. One or more displacement sensors may include a plurality of displacement sensors arranged along a radial line of the wafer. One or more displacement sensors may include a plurality of displacement sensors arranged at different rotational angles around the wafer. This method / operation may also include measuring the displacement of a baseline wafer to generate baseline displacement data representative of a flat wafer surface. Generating displacement data may include determining the displacement of the wafer relative to the baseline displacement data. This method / operation may also include mapping the displacement data to two-dimensional coordinates on the wafer based on alignment data. Also, this method / operation may include mapping the displacement data to a rotational angle on the wafer based on alignment data. Also, this method / operation may include identifying a displacement area on the wafer in the displacement data and providing this displacement area to a polishing process or a cleaning process. Adjusting the parameters of the carrier head may include adjusting the angle at which the carrier head holds the wafer during a cleaning or polishing process. Adjusting the parameters of the carrier head may include adjusting the amount of pressure provided to a curved or warped area on the wafer during a cleaning or polishing process. Adjusting the amount of pressure may include identifying a chamber in the carrier head adjacent to a curved or warped area on the wafer and adjusting the pressure in the chamber to correct the curved or warped area on the wafer.Adjusting the amount of pressure can include adjusting the pressure at which the brush cleans a curved or warped area on the wafer during the cleaning process. Displacement data can be generated using a displacement sensor by rotating the displacement sensor around the wafer.

[0010]

[0010] In some embodiments, the system can include one or more displacement sensors arranged to measure the displacement of a wafer as the wafer rotates on a platform, a cleaning or polishing chamber configured to clean or polish the wafer, and a computer system. The computer system can perform operations including receiving displacement data generated using one or more displacement sensors for the wafer, where the displacement data can indicate the displacement of the wafer relative to the one or more displacement sensors; providing the displacement data to a model trained using a measurement data set and a corresponding displacement data set; generating a control signal for the cleaning or polishing chamber based on the output from the model in response to receiving the displacement data as an input; and using the control signal to control a cleaning or polishing process for the wafer.

[0011]

[0011] In some embodiments, the method can include receiving, for a wafer, displacement data generated using a displacement sensor, where the displacement data can indicate the displacement of the wafer relative to the displacement sensor; providing the displacement data to a model trained using a measurement data set and a corresponding displacement data set; and generating measurement data for the wafer based on the output from the model in response to receiving the displacement data as an input to the model.

[0012] In some embodiments, the non-transitory computer-readable medium, when executed by one or more processors, causes the one or more processors to receive displacement data generated using one or more displacement sensors for a wafer, where the displacement data can indicate a displacement of the wafer relative to the one or more displacement sensors, provide the displacement data to a model trained using the displacement data set, and generate a control signal for a cleaning or polishing chamber based on an output from the model in response to receiving the displacement data as an input. The non-transitory computer-readable medium may include instructions that cause the one or more processors to perform operations including these actions.

[0013]

[0013] In any embodiment, any and all of the following features may be implemented without limitation and in any combination. Controlling a cleaning or polishing process for a wafer may include selecting a cleaning or polishing process from a plurality of different cleaning or polishing processes. This cleaning or polishing process may have a run time that is shorter than at least one of a plurality of different cleaning or polishing processes. Controlling a cleaning or polishing process for a wafer may include controlling the rotational speed of a platen that supports the wafer in the cleaning or polishing process. Controlling a cleaning or polishing process for a wafer may include controlling the rotational speed of a cleaning or polishing head in the cleaning or polishing process. Controlling a cleaning or polishing process for a wafer may include controlling the flow of slurry used in the cleaning or polishing process. Controlling a cleaning or polishing process for a wafer may include controlling the pressure applied to a zone within the cleaning or polishing head in the cleaning or polishing process. This displacement data may indicate a curved or warped area on the wafer. This method / operation may also include using measurement data to control a cleaning or polishing process for a wafer. The measurement data may include the thickness of a thin film or feature on the wafer. This method / operation may also include rotating the wafer about the center of the wafer, measuring the displacement of the wafer at a predetermined distance from the center of the wafer as the wafer rotates to generate displacement data, and / or measuring the displacement of a baseline wafer to generate baseline displacement data representative of a flat wafer surface. Generating displacement data may include determining the displacement of the wafer relative to the baseline displacement data. This method / operation may also include mapping the displacement data to two-dimensional coordinates on the wafer based on alignment data, or mapping the displacement data to a rotation angle on the wafer based on alignment data. This method / operation may also include identifying a displacement area on the wafer in the displacement data and providing this displacement area to a polishing process or a cleaning process.

[0014]

[0014] A further understanding of the nature and advantages of the various embodiments can be realized by referring to the remainder of the specification and the drawings. In the drawings, similar reference numerals are used throughout several of the drawings to refer to similar components. In some instances, a sub-label is associated with the reference numeral to indicate one of a plurality of similar components. When a reference is made to a reference numeral without designating an existing sub-label, it is intended to refer to all such similar components.

Brief Description of the Drawings

[0015]

Figure 1

[0015] A schematic cross-sectional view of an example of a polishing apparatus according to some embodiments is shown.

Figure 2

[0016] A measurement spectrum from an in-situ optical monitoring system according to some embodiments is shown.

Figure 3

[0017] A path of a series of spectral measurements on a substrate according to some embodiments is shown.

Figure 4

[0018] A system for measuring wafer displacement according to some embodiments is shown.

Figure 5A

[0019] A displacement sensor disposed at the edge of a wafer according to some embodiments is shown.

Figure 5B

[0020] A displacement sensor disposed to measure the displacement of the bottom edge of a wafer according to some embodiments is shown.

Figure 5C

[0021] A plurality of displacement sensors according to some embodiments is shown.

Figure 5D

[0022] A plurality of displacement sensors disposed at different rotational angles according to some embodiments is shown.

Figure 6

[0023] A three-dimensional graph of displacement data according to some embodiments is shown.

Figure 7A

[0024] Shows a baseline wafer that can be measured by a displacement sensor according to some embodiments.

Figure 7B

[0025] Shows a convex wafer according to some embodiments.

Figure 7C

[0026] Shows a concave wafer according to some embodiments.

Figure 8

[0027] Shows a graph of displacement data of a warped wafer according to some embodiments.

Figure 9

[0028] Shows a flowchart of various processes that can be performed as part of a semiconductor manufacturing process according to some embodiments.

Figure 10

[0029] Shows a flowchart of a method for measuring wafer displacement during a semiconductor manufacturing process according to some embodiments.

Figure 11

[0030] Shows a block diagram of a process for training a model according to some embodiments.

Figure 12

[0031] Shows a block diagram of a system for using a trained model to control a cleaning or polishing process according to some embodiments.

Figure 13

[0032] Shows a block diagram of a process for using a model to generate a control signal for a cleaning or polishing process according to some embodiments.

Figure 14

[0033] Shows a block diagram of how a model can be used to generate measurement data according to some embodiments.

Figure 15

[0034] Shows a flowchart of a method for training and using a model using displacement data according to some embodiments.

Figure 16

[0035] Shows an exemplary computer system in which various embodiments can be implemented.

Best Mode for Carrying Out the Invention

[0016]

[0036] FIG. 1 shows an example of a polishing apparatus 100. The polishing apparatus 100 may include a rotatable disk-shaped platen 120 where a polishing pad 110 can be located. The platen may be operable to rotate around an axis 125. For example, a motor 121 may rotate a drive shaft 124 to rotate the platen 120. The polishing pad 110 may be a two-layer polishing pad having an outer polishing layer 112 and a more flexible backing layer 114.

[0017]

[0037] The polishing apparatus 100 may include a port 130 for discharging a polishing liquid 132, such as slurry, onto the polishing pad 110. The polishing apparatus may also include a polishing pad conditioner for polishing the polishing pad 110 to maintain the polishing pad 110 in a constant polishing state.

[0018]

[0038] The polishing apparatus 100 may include at least one carrier head 140. The carrier head 140 may be operable to hold the substrate 10 in contact with the polishing pad 110. The carrier head 140 may separately control polishing parameters (such as pressure) related to each substrate.

[0019]

[0039] In particular, the carrier head 140 may include a holding ring 142 for holding the substrate 10 under a flexible membrane 144. The carrier head 140 may also include a plurality of individually controllable pressurizable chambers defined by the membrane, for example, three chambers 146a - 146c. These chambers may apply independently controllable pressures to related zones on the flexible membrane 144 and thus on the substrate 10. For simplicity of explanation, only three chambers are shown in FIG. 1, but in other embodiments, there may be one or two chambers, or four or more chambers, for example, five chambers.

[0020]

[0040] The carrier head 140 is suspended from a support structure 150, such as a carousel or a track, and can be connected to a carrier head rotation motor 154 by a drive shaft 152 so that the carrier head can rotate about an axis 155. Optionally, the carrier head 140 can oscillate laterally, for example, by a slider on the carousel 150 or the track, or by the rotational vibration of the carousel itself. During operation, the platen rotates about its central axis 125, the carrier head rotates about its central axis 155, and / or the upper surface of the polishing pad can be translated laterally in parallel across the entire area.

[0021]

[0041] Although only one carrier head 140 is shown, more carrier heads may be provided to hold additional substrates so that the surface area of the polishing pad 110 can be used efficiently. The polishing apparatus may also include an in-situ monitoring system 160. The in-situ monitoring system can generate a series of time-varying values that depend on the thickness of the layer on the substrate. The in-situ monitoring system 160 can include an optical monitoring system. In particular, the in-situ monitoring system 160 can measure a series of spectra of light reflected from the substrate during polishing.

[0022]

[0042] Optical access 108 through the polishing pad can be provided by including an aperture (i.e., a hole through the pad) or a solid window 118. The solid window 118 can be fixed to the polishing pad 110, for example, as a plug that fills the aperture in the polishing pad. In some embodiments, the solid window can be supported on the platen 120 and protrude into the aperture of the polishing pad, but alternatively, it can be formed integrally with the polishing pad or adhesively fixed.

[0023]

[0043] The optical monitoring system 160 may include a light source 162, a photodetector 164, and a remote controller 190, such as a computer, and a circuit 166 for transmitting and receiving signals between the light source 162 and the photodetector 164. One or more optical fibers can be used to transmit light from the light source 162 to the optical access of the polishing pad and to transmit the light reflected from the substrate 10 to the detector 164. For example, a branched optical fiber 170 can be used to transmit light from the light source 162 to the substrate 10 and then to the detector 164 again. The branched optical fiber can include a trunk 172 disposed proximate to the optical access and two branches 174 and 176 respectively connected to the light source 162 and the detector 164.

[0024]

[0044] In some embodiments, the upper surface of the platen can include a recess 128 to which an optical head 168 that holds one end of the trunk 172 of the branched fiber is adapted. The optical head 168 can include a mechanism for adjusting the vertical distance between the upper surface of the trunk 172 and the solid window 118.

[0025]

[0045] The output of the circuit 166 can be a digital electrical signal that passes through a rotary coupler 129 (e.g., a slip ring) of the drive shaft 124 to the controller 190 of the optical monitoring system. Similarly, in response to a control command of a digital electrical signal reaching the optical monitoring system 160 from the controller 190 through the rotary coupler 129, the light source can be switched on or off. Alternatively, the circuit 166 can communicate with the controller 190 by wireless signals.

[0026]

[0046] The light source 162 can be operable to emit ultraviolet (UV), visible, or near-infrared (NIR) light. The photodetector 164 can be a spectrometer. A spectrometer is an optical instrument that measures the intensity of light in a part of the electromagnetic spectrum. For example, a grating spectrometer can be used. The normal output of a spectrometer can include the intensity of light as a function of wavelength (or frequency). FIG. 2 shows an example of a measurement spectrum 200 with intensity as a function of wavelength.

[0027]

[0047] As described above, the light source 162 and the photodetector 164 can be connected to a computing device (e.g., the controller 190) operable to control their operations and receive their signals. The computing device can include a microprocessor located near the polishing apparatus. For example, the computing device can be a programmable computer. With respect to control, the computing device can synchronize, for example, the operation of the light source and the rotation of the platen 120. A display 192 (e.g., an LED screen) and a user input device 194 (e.g., a keyboard and / or a mouse) can be connected to the controller 190.

[0028]

[0048] During operation, the controller 190 can receive a signal that conveys information representing, for example, the spectrum of light received by the photodetector, for a particular blink of the light source or a time frame of the detector. Thus, this spectrum can be the spectrum measured in situ during polishing. Without being bound by any particular theory, the spectrum of light reflected from the substrate 10 can be regarded as the polishing progress due to changes in the thickness of the outermost layer, and thus a spectrum that varies over a series of times can be obtained.

[0029]

[0049] The optical monitoring system 160 can be configured to generate a series of measurement spectra at a measurement frequency, i.e., "spectral data". Due to the relative movement between the substrate 10 and the optical access 108, that series of spectra are measured at different positions on the substrate 10. In some embodiments, the light beam generated by the light source 162 can emerge from a point that rotates with the platen 120 (indicated by arrow R in FIG. 3). As shown in FIG. 3, in such an embodiment, due to the relative movement between the substrate 10 and the optical access 108, the spectrum can be measured at position 300 on the path across the substrate 10. In some embodiments, only one spectrum is measured per rotation of the platen. Further, in some embodiments, the light-emitting point of the light beam is stationary, and the measurement is performed only when the optical access 108 is aligned with the light beam.

[0030]

[0050] The CMP process represents one of many different processes that can be performed during the manufacture of semiconductor wafers. As different layers and features are added to the substrate, a CMP process can be used to planarize the wafer and remove a specific amount of material between steps. Ideally, the wafer can begin as a completely flat silicon crystal substrate. However, when layers and features are added to the substrate, this additional material can stress the structure and cause the wafer to warp or bend. This warp can cause problems during the CMP process where the wafer is polished unevenly and a layer of uniform thickness is not formed after the CMP process is completed.

[0031]

[0051] Embodiments described herein solve these and other technical problems by characterizing the vertical displacement of wafers during semiconductor manufacturing processes. Displacement sensors can be used to make displacement measurements on the outer perimeter of the wafer. The resulting displacement data can then be used to control the polishing process, the cleaning process, and / or the angle or orientation at which the wafer is processed. This allows subsequent semiconductor processes to correct for wafer warping.

[0032]

[0052] FIG. 4 shows a system 400 for measuring wafer displacement according to some embodiments. The system 400 can include a platform 412 configured to support a wafer 404 and rotate the wafer 404 about a central axis 414 of the wafer 404. For example, an operator or robotic arm can place the wafer 404 on the platform 412 before inserting it into a CMP tool. The platform 412 can then rotate the wafer 404 about the central axis 414. During rotation, various sensors can measure attributes of the wafer 404.

[0033]

[0053] In some embodiments, system 400 may include an alignment sensor. The alignment sensor may be implemented using a through-beam sensor configured to pass a beam of light between a first component 401 and a second component 403. The alignment sensor may be configured to detect when the beam is blocked between the first component 401 and the second component 403. Thus, the alignment sensor may be used in combination with the rotation of the wafer 404 provided by the platform 412 to align the wafer 404 in a predetermined orientation. For example, the wafer 404 may include a notch 416 or other edge feature along the outer perimeter of the wafer 404. Typically, the wafer 404 will block the beam between the first component 401 and the second component 403 as the wafer 404 rotates about the central axis 414. However, when the position of the notch 416 along the edge of the wafer 404 passes above the first component 401 of the alignment sensor, the beam may be detected by the second component 403 and thus indicate the position of the notch 416.

[0034]

[0054] Once the position of the notch 416 is identified in the wafer 404, the system 400 may optionally rotate the wafer 404 to a predetermined orientation. For example, in some cases, the system 400 may stop the rotation of the wafer 404 when the notch 416 is in position. In other cases, the system 400 may continue to rotate the wafer 404 until a predetermined rotation angle is reached. This process performed by the system 400 may be used to ensure that the wafer 404 is rotated to a known orientation before being transferred to subsequent machines in a semiconductor manufacturing process. For example, some systems may use robotic arms to process the wafer 404 as it moves between various machines. The wafer 404 can be rotated into a known position before being placed on the polishing pad of a CMP apparatus (or any other semiconductor manufacturing apparatus). As will be described below, this alignment and rotational orientation of the wafer 404 can also be used to identify curved or warped locations on the wafer 404.

[0035]

[0055] System 400 can be at least partially implemented by a machine referred to as an aligner. Specifically, the aligner can be configured to rotate the wafer 404 until the notch 416 is positioned. In some embodiments, the aligner can be modified to also measure a distance or displacement as the wafer 404 rotates. System 400 can further include a displacement sensor 406. As used herein, the term "displacement sensor" can include any sensor configured to measure the distance of a surface from the sensor. In some embodiments, for example, a laser displacement sensor can be used. The laser displacement sensor can emit one or more laser beams toward the surface of the wafer 404 and receive the reflection from the wafer 404. The displacement sensor 406 can then calculate the distance between the displacement sensor 406 and the surface of the wafer 404 in the direction in which the laser beam is directed. As the wafer 404 rotates about the central axis 414, the displacement sensor 406 can continuously sample distance measurements with respect to the surface of the wafer 404.

[0036]

[0056] When modifying the arena, system 400 may also include a computer system that controls and / or records displacement data received from displacement sensor 406. The computer system may include one or more processors (e.g., microprocessors, microcontrollers, digital controllers, FPGAs, programmable hardware, etc.) configured to control the operation of displacement sensor 406 and record displacement data. The one or more processors may be an integrated part of system 400. Alternatively, the one or more processors may be part of another computer system that communicates with displacement sensor 406 through a wired or wireless interface. Instructions for controlling displacement sensor 406 may be stored in one or more memory devices such as a non-transitory computer-readable medium. These instructions may cause the one or more processors to perform operations such as receiving and processing displacement data, rotating wafer 404, and repackaging displacement data. An example of a computer system is shown in FIG. 11 below.

[0037]

[0057] The displacement sensor may be arranged to measure the displacement of wafer 404 as the wafer 404 rotates. By measuring the displacement of wafer 404, displacement data may be generated. The displacement data may include distance measurements from displacement sensor 406 to wafer 404. Alternatively, the displacement data may include the displacement of wafer 404 from a baseline position. For example, the baseline position of wafer 404 may be determined by measuring the displacement data of a bare silicon substrate or other wafer known to be flat as a reference. If wafer 404 curves downward such that the displacement measurement is longer than the baseline displacement, the displacement data may include negative values. If wafer 404 curves upward such that the displacement measurement is shorter than the baseline displacement, the displacement data may include corresponding positive values.

[0038]

[0058] The example of FIG. 4 includes a system 400 that combines an aligner and a displacement sensor 406. However, instead of modifying the aligner to include the displacement sensor 406, in other systems, the aligner may be omitted and a dedicated displacement sensor may be provided with a platform that rotates the wafer 400. In other embodiments, while the wafer 404 remains stationary, the displacement sensor 406 itself may rotate around the central axis 414. In these embodiments, the displacement sensor itself serves as an aligner, and the displacement sensor 406 can perform an alignment function. For example, the displacement sensor 406 can collect displacement data and detect the position of the notch 416.

[0039]

[0059] FIG. 5A shows a displacement sensor 506a disposed at the edge of a wafer 504 according to some embodiments. In the example of FIG. 4 described above, the displacement sensor 506 can be directed towards the outer edge of the wafer. For example, the outer edge of the wafer can include the outermost 1 cm of the wafer 504 such that displacement measurements characterize displacement along the outer edge of the wafer 504. This location of the displacement sensor 506a can provide certain technical advantages. Specifically, the warp or curvature of the wafer 504 can be most pronounced at the edge. Since the wafer 504 is attached to the central portion of the wafer 504 on the platform, the maximum displacement can be measured along the edge of the wafer 504. Further, when directed towards the edge of the wafer, the displacement sensor 506a can also perform the function of an aligner. Specifically, the displacement sensor 506a can continuously sample displacement measurements from the wafer 504. When a notch is formed in the wafer 504, the displacement measurement can exceed a negative threshold distance. The displacement sensor 506a can interpret this measurement as the position of the notch. Thus, the displacement sensor 506a can determine the orientation and displacement data of the wafer 504.

[0040]

[0060] Figure 5B shows a displacement sensor 506b arranged to measure the displacement of the bottom edge of the wafer 504, according to some embodiments. Instead of being arranged above the wafer 504 as shown in Figure 5A, the displacement sensor 506b may be placed below the wafer 504. This position of the displacement sensor 506b may provide certain technical advantages. Specifically, when a robotic arm is used to move the wafer 504 to / from the system, typically the movement of the wafer 504 by the robotic arm when lifting the wafer 504 will not be hindered by the displacement sensor 506b placed under the wafer 504. Another technical advantage provided by this arrangement includes the impact of the light-emitting displacement sensor on the semiconductor device. Usually, the devices on the wafer can be laid out and exposed on the upper surface of the wafer 504. By placing the displacement sensor 506b under the wafer 504, the system can avoid shining a laser or other high-intensity light source on these semiconductor devices. This can be advantageous when these semiconductor devices are particularly sensitive to high-intensity light.

[0041]

[0061] FIG. 5C shows a plurality of displacement sensors 506c, 508c according to some embodiments. In this example, the plurality of displacement sensors 506c, 508c can be arranged on a radial line 510 extending toward the center of the wafer 504. Thereby, displacement data can be measured at a plurality of points for each rotation angle. Although the example of FIG. 5C illustrates two displacement sensors 506c, 508c, the number of these displacement sensors is provided by way of example only and does not imply a limitation. In other embodiments, three or more displacement sensors may be included. By measuring displacement data along the radial line 510 with a plurality of displacement sensors, the system can generate a displacement map of a plurality of positions on the wafer 504 and create a displacement mapping of the entire surface of the wafer 504, not just the edge of the wafer 504. Prior to the present disclosure, a metrology station that performs a laser scan of the entire surface of the wafer 504 was required to generate an accurate view of many different sides of the wafer 504. However, metrology stations are costly and time-consuming to operate. As depicted in FIG. 5C, by providing a plurality of displacement sensors 506c, 508, at least a portion of the operations performed by the metrology station can be replaced with a low-cost and high-speed process to provide a surface mapping of the displacement data of the wafer 504.

[0042]

[0062] FIG. 5D shows a plurality of displacement sensors 506d, 508d arranged at different rotation angles according to some embodiments. Instead of placing the displacement sensors 506d, 508d at different radial distances along the same radial line, in some embodiments, the displacement sensors 506d, 508d may be arranged at the same radial distance separated by a known rotation angle 512. By these embodiments, redundant displacement data regarding a certain position can be provided as a backup in case one of the displacement sensors 506d, 508d fails. These embodiments may also use the redundant displacement data to characterize, calibrate, and / or detect faults in the displacement sensors 506d, 508d. Note also that three or more displacement sensors may be used without limitation. Another technical advantage provided by aligning the plurality of displacement sensors 506d, 508d at the same radial distance is to collect parallel data of the wafer 504. For example, by placing the plurality of displacement sensors 506d, 508d about 180° apart on the wafer 504, the entire outer periphery of the wafer can be measured in a half rotation instead of a full rotation. Similarly, by arranging four displacement sensors about 90° apart on the wafer 504, the entire outer periphery of the wafer can be measured in a quarter rotation instead of a full rotation. Therefore, with these configurations, the total time required for collecting displacement data can be reduced, such as by 50%, 25%, etc.

[0043]

[0063] The different combinations of the number and / or position of displacement sensors shown in FIGS. 5A - 5B can be used in any combination without limitation. For example, some embodiments may include multiple displacement sensors at different rotational angles and / or different radial distances on the upper side of the wafer, while optionally including additional displacement sensors at different rotational angles and / or different radial distances on the bottom side of the wafer. Also, some embodiments may use different sensor types or settings when multiple displacement sensors are used. For example, some embodiments may use multiple laser displacement sensors each operating at a different optical frequency. Since reflections from the wafer may be different for different frequencies, using different optical frequencies for each sensor can improve the measurement accuracy of the overall displacement data. Further, some embodiments may use different sensor types when multiple displacement sensors are used. For example, a laser displacement sensor may be used in one location while an ultrasonic displacement sensor may be used in another location.

[0044]

[0064] FIG. 6 shows a three - dimensional (3D) graph 600 of displacement data according to some embodiments. The graph 600 includes distance measurements relative to the default or baseline displacement of the wafer. Positions on the wafer can be mapped to Cartesian coordinates in millimeters. These coordinates can be assigned based on the alignment data of the notch. For example, the notch position can be assigned the coordinate position (0, 150) in the (x, y) plane of the graph 600. Thus, once the alignment position of the displacement data is captured, some embodiments can rotate the displacement data to conform to the coordinate position based on the notch position.

[0045]

[0065] In this example, the displacement data is stored as the vertical distance relative to the baseline position. For example, the ring 602 may represent the baseline position of the wafer when there is no curvature or warp. Data points 604 representing distances measured above the baseline position may be represented as positive displacements. These data points 604 may correspond to positions on the wafer that are curved or warped upward relative to the center of the wafer. Data points 606 representing distances measured below the baseline position may be represented as negative displacements. These data points 606 may correspond to positions on the wafer that are curved or warped downward relative to the center of the wafer.

[0046]

[0066] The displacement data may be stored for each wafer rotating on the platform. Further, the displacement data may be stored for each displacement sensor within the system that measures the wafer. In order to generate a 3D mapping of the displacement across the entire wafer surface, displacement data from various displacement sensors may be combined for a single wafer. This displacement data may then be passed to other machines in the semiconductor processing pipeline and used to control the operation of those machines, as described below.

[0047]

[0067] FIG. 7A shows a baseline wafer 704 that may be measured by a displacement sensor 706, according to some embodiments. The baseline wafer 704 may be an ideally flat wafer in the z-plane. In other words, the baseline wafer 704 may generate displacement data indicating a constant baseline displacement 720 that aligns with the surface of the wafer 704. The displacement data received from the baseline wafer 704 may be used to characterize the relative displacement of other subsequent wafers measured by the system. The baseline wafer 704 may be measured as part of the calibration or initialization process of the system. Displacement data from subsequent measurements of subsequent wafers may be subtracted from the displacement data from the baseline wafer. Although not explicitly shown in FIG. 7A, embodiments including multiple displacement sensors may store baseline displacement data for each sensor. Displacement data measured from subsequent wafers may be subtracted from the baseline displacement data for the corresponding displacement sensor.

[0048]

[0068] FIG. 7B shows a convex wafer 704b according to some embodiments. The convex shape indicates that the edge of the wafer 704b is bent or warped downward with respect to the center of the wafer 704b. The displacement 722 may be greater than the baseline displacement 720, such that when subtracted from the baseline displacement 720, the displacement 722 is a negative value. Similarly, FIG. 7C shows a concave wafer 704c according to some embodiments. The concave shape indicates that the edge of the wafer 704c is bent or warped upward with respect to the center of the wafer 704c. The displacement 724 may be less than the baseline displacement 720, such that when subtracted from the baseline displacement 720, the displacement 724 is a positive value.

[0049]

[0069] FIG. 8 shows a graph 800 of displacement data for a warped wafer according to some embodiments. Instead of being mapped to 2D coordinates on a 3D axis, the displacement data can be mapped to a 2D axis where the X-axis represents the rotation angle and the Y-axis represents the displacement relative to the baseline. The mapping to the rotation angle can also be based on alignment data for determining the origin of the rotation. The displacement data 802 corresponds to a wafer that may include recesses and / or protrusions. This type of wafer can be characterized as having a "potato chip" shape that undulates up and down along the edge of the wafer. The displacement data 804 corresponds to a wafer where one side is curled or warped upward. The graph 800 shows how displacement data regarding any type of warped or curved state within the wafer can be characterized by the system described herein.

[0050]

[0070] The mapping to the 2D coordinates of FIG. 6, or the mapping to the angular rotation of FIG. 8, can be used to control subsequent processes. For example, the 2D coordinates of FIG. 6 can be used to identify 2D regions within the wafer that should be polished more aggressively, cleaned more aggressively, or subjected to differential pressure during the polishing process. For example, these differential pressures can include lower pressures in some areas and higher pressures in other areas to correct for irregularities in the wafer represented by the displacement data. Continuous displacement areas on the wafer can be grouped together within one region and mapped to specific pressurization chambers within the CMP carrier head. These regions on the wafer can be identified within the mapping data described above.

[0051]

[0071] FIG. 9 shows a flowchart 900 of various processes that can be performed as part of a semiconductor manufacturing process according to some embodiments. Note that the wafer may have been processed using various semiconductor machines, such as machines that perform various deposition processes, etching processes, etc., prior to the start of flowchart 900. After these processes have been performed, the robotic arm can move the wafer onto the wafer aligner / displacement measurement system 902. This system 902 can be implemented using the system 400 described above. The wafer aligner / displacement measurement system 902 can generate displacement data 908.

[0052]

[0072] The robotic arm can move the wafer onto the CMP device 904 to perform the CMP process. The displacement data 908 can be sent to the handling control 910 and / or the endpoint control 912 of the CMP device 904. This displacement data can then be used to control the polishing process performed on the wafer. Specifically, the CMP device 904 can include a carrier head that holds or retains the wafer. The carrier head can be associated with a number of parameters. These parameters can control the angle at which the wafer is held by the carrier head and / or the amount of pressure applied to the wafer at various positions. These parameters can be adjusted on the carrier head to correct for curved or warped areas on the wafer during the cleaning or polishing processes described below.

[0053]

[0073] For example, the displacement data 908 can be used to control how the handling control 910 holds the wafer. For example, a flat wafer can be held by the carrier head with a stronger force than a curved wafer. The CMP device can receive the displacement data and adjust the gripping force applied to the wafer based on the amount of displacement identified within the displacement data. Further, if the wafer is bent along a portion of the wafer outer periphery, the handling control 910 can hold the wafer at a slight angle such that the bent portion protrudes slightly further from the carrier head 140 of the CMP device 100 shown in FIG. 1 than the remaining portion of the wafer. Further, the chamber 146 can be pressurized based on the displacement data 908. A particular chamber 146 behind the warped portion of the wafer can be pressurized more than other chambers to push the warped portion in line with the remaining portion of the wafer or to apply a greater pressure during the polishing process. Thereby, a flat surface can be generated on the wafer when the wafer is pressed against the polishing pad of the CMP device 904. Since the orientation of the wafer is known from the alignment procedure, the displacement data can be mapped to specific chambers 146 within the carrier head 140 over the warped portion of the wafer. These chambers can be pressurized more or less based on the positive / negative displacement data associated with each corresponding area of the wafer.

[0054]

[0074] The displacement data 908 can also be used by the endpoint control 912 of the CMP process executed by the CMP apparatus 904. For example, when polishing a wafer using the processes described above with reference to FIGS. 1-3, the thickness of the topmost layer on the wafer can be measured in real time. For example, a flat wafer can be polished faster and with a stronger force than a curved or warped wafer. In the absence of access to displacement data, the polishing process generally uses an average or worst-case polishing rate / pressure to accommodate both flat and warped wafers. However, when the displacement data can be used to characterize the wafer as being flat or warped, the rate / pressure applied during the polishing process can be adjusted accordingly. The CMP apparatus can use the displacement data to determine whether the wafer is flat. If the wafer is flat, the CMP apparatus can then increase the rate / pressure of the polishing process. If the wafer is not flat, the CMP apparatus can then decrease the rate or pressure of the polishing process. This can potentially improve the throughput of the wafer by 5% to 10% throughout the polishing process. Also, the displacement data can be provided to the CMP apparatus 904 such that both flat and warped wafers are polished to have the same desired post-polish characteristics. For example, to create an overall flat surface on the wafer, the curved portions of the wafer can be polished more than the flat portions of the wafer. Some embodiments can also adjust other parameters of the polishing process based on the displacement data. For example, a substantially flat wafer can use a higher temperature or more polishing slurry to polish faster, while a warped wafer can use less polishing slurry to polish more delicately, or vice versa. Additionally, temperature and chemical additives can be applied to different zones on the wafer during polishing. For example, the warped portions of the wafer can use a first chemical additive and / or temperature to the slurry. On the other hand, the flat portions of the wafer can use a second chemical additive and / or temperature.

[0055]

[0075] The measurement of the reflected wavelength may be affected by the displacement from the polishing pad of the wafer. The displacement data 908 can be used to correct for curved or warped locations on the wafer. As a result, the thickness measurement of the surface being polished may be inaccurate. For example, positive displacement data indicating that the wafer is bent towards the polishing pad can add or subtract a proportional amount from the thickness measurement based on the effect of the displacement on the reflected wavelength received by the spectrometer. Ultimately, the endpoint can be adjusted so that more of the warped portion of the wafer is polished than other portions of the wafer, creating an overall flat surface on the wafer at subsequent stages of the semiconductor manufacturing pipeline.

[0056]

[0076] Next, the wafer can be moved to a cleaner 906 or wafer washer configured to clean the wafer from debris remaining after the polishing process. The displacement data 908 can be passed to software implementing the handling control 914 and / or cleaning recipe 916 of the cleaner 906. The cleaner 906 can include a carrier head similar to the carrier head described above for the CMP apparatus 904. Next, the displacement data 908 can also be used to control the cleaning process performed on the wafer. For example, the handling control 914 can be changed to grip the wafer in a different manner based on the displacement data. Thus, the wafer becomes more uniformly oriented for the cleaning process, as described above for the polishing process. Further, the cleaning recipe 916 can be changed based on the warped / curved shape of the wafer. The portion of the wafer corresponding to the warped area can be cleaned more or less based on the relative positive / negative values of the displacement data. For example, the pressure at which a brush is applied to the wafer can be adjusted with the positive / negative displacement data to apply more or less pressure to the protruding area of the wafer within the washer.

[0057]

[0077] Figure 10 shows a flowchart 1000 of a method for measuring the displacement of a wafer during a semiconductor manufacturing process according to some embodiments. This method may include rotating the wafer around the center of the wafer (1002). This rotation can be performed when the wafer is supported on the platform as described above with reference to FIG. 4. This rotation can also be used to simultaneously identify and align the position of the notch on the wafer using an alignment sensor.

[0058]

[0078] This method may further include measuring the displacement of the wafer at a predetermined distance from the center of the wafer when rotating the wafer (1004) to generate displacement data. The predetermined distance may correspond to the position where the displacement sensor reads the displacement data from the wafer. The predetermined distance may be located at any point along a radial line extending from the center of the wafer along the outer edge of the wafer and / or at an angular displacement from an alignment sensor or another displacement sensor as described above with reference to FIGS. 5A - 5D. The displacement data may characterize displacement measurements from a plurality of different displacement sensors. The displacement sensor may be implemented using a laser displacement sensor or other types of displacement sensors configured to measure distance.

[0059]

[0079] This method may further include using displacement data (1006) to control a polishing or cleaning process performed on the wafer. This portion of the method may be optional, and depending on the implementation of the method, displacement data may be used to characterize the wafer without using it to control any other process. For example, the displacement data may be used to characterize the wafer surface and / or to characterize or test a previous process performed on the wafer. Controlling the polishing process may include using the displacement data to adjust handling control and / or to change the orientation in which the carrier head holds the wafer. Controlling the polishing process may include using the displacement data to apply various amounts of pressure to the back side of the wafer to correct for the curvature of the wafer as it is pressed against the polishing pad. Some embodiments may also use displacement data to control other processes such as a cleaning process.

[0060]

[0080] The optional step of using displacement data to control a polishing or cleaning process performed on the wafer may be performed by a computer system of the corresponding polishing or cleaning machine. For example, software instructions on a computer system of the polishing machine may cause one or more processors to receive displacement data generated using a displacement sensor. As described above, the displacement data may indicate at least one curved or warped area on the wafer. These instructions may also cause the machine to identify parameters of the carrier head corresponding to positions on the curved or warped area of the wafer. The computer system may then adjust those parameters on the carrier head to correct for the curved or warped area on the wafer. As described above, these parameters may adjust the angle at which the carrier head holds the wafer, the pressure applied during the polishing process, the orientation of the wafer during the process, the pressure applied to the back side of the wafer using various chambers within the carrier head, and so forth.

[0061]

[0081] It should be understood that the specific steps shown in FIG. 10 provide a specific method for measuring the displacement of wafers between semiconductor manufacturing processes according to various embodiments. Also, other sequences of steps may be performed according to alternative embodiments. For example, alternative embodiments may perform the above steps in a different order. Further, each individual step shown in FIG. 10 may include a plurality of sub-steps that may be performed in various sequences suitable for the individual steps. Additionally, depending on the specific application, additional steps may be added or removed. Many variations, modifications, and alternatives are also within the scope of the present disclosure.

[0062] Machine learning control using displacement data

[0082] As described above, the process of generating measurement data for wafers can be a complex and time-consuming process, often requiring special measurement chambers that can impose significant costs on wafer manufacturers. For example, a measurement station may perform a laser scan of the wafer surface to identify displacements such as curvature or warp of the wafer shape, along with other irregularities in the wafer surface or shape. The measurement data can also be used to measure the thickness of thin films and other features on the wafer. For example, the measurement data may include the thickness or position of metal traces, semiconductor circuits, or other features formed on the wafer. A measurement station performing a laser scan or other analysis of the wafer may require a significant amount of time to perform this analysis, which can take from a few minutes to up to an hour depending on the size of the wafer and the resolution of the scan.

[0063]

[0083] Some of the embodiments described herein may use displacement data generated using the systems and methods described above to replace and / or generate measurement data without the need to use a measurement station for each new wafer. By this practical application of the machine learning principle of using specific displacement data inputs to generate control signals or measurement data, the need for complex measurement stations and the need to perform complex measurement scans for each new wafer are eliminated, significantly improving the wafer manufacturing process. Instead, the displacement sensor system described above may be used to generate displacement data. A trained model may then be used to generate the control signals required for the polishing or cleaning process. Some embodiments may also generate or select measurement data representative of a wafer without performing a full measurement scan. This improves the throughput of the wafer manufacturing process and may exclude measurement stations from the wafer manufacturing pipeline. As a result, wear on the measurement stations is reduced and the service life is extended.

[0064]

[0084] FIG. 11 shows a block diagram 1100 of a process for training a model according to some embodiments. As described above, one or more displacement sensors may be positioned relative to a rotating platform that receives wafer 1104. As the platform rotates, one or more displacement sensors may measure displacement data 1112 of wafer 1104. One or more displacement sensors may be part of a displacement measurement system 1106, which may include any of the embodiments described above. For example, displacement measurement system 1106 may include an alignment sensor that identifies the position of the notch of wafer 1104. Generally, the displacement sensors measure the displacement of wafer 1104 relative to one or more displacement sensors. For example, one or more displacement sensors may measure the distance between one or more displacement sensors and the surface of wafer 1104 as wafer 1104 rotates.

[0065]

[0085] In addition to generating displacement data 1112, in some embodiments there may be other sensors 1108 to generate additional sensor data. The sensor 1108 may be part of the displacement measurement system 1106. The sensor 1108 may alternatively or additionally be included in other systems or processing chambers used to process the wafer 1104 at an initial stage of the wafer manufacturing pipeline. The sensor 1108 may generate sensor data 1114. This sensor data 1114 may also be used as an input when training or using the model 1122. The sensor 1108 may include a camera that captures an image of the wafer 1104 as sensor data 1114. The sensor 1108 may also include an eddy current sensor that can be used to determine the thickness of the copper film on the wafer 1104. The sensor 1108 may also include a rotational accelerometer or other sensor configured to measure the position or shape dimensions of the wafer 1104. Note that while some embodiments may use only the displacement data 1112, other embodiments may augment the displacement data 1112 with additional sensor data 1114. Other embodiments may rely on the sensor data 1114 without requiring the displacement data 1112.

[0066]

[0086] Model 1122 can be trained based on the type of output that Model 1122 needs to generate. In the example of FIG. 11, Model 1122 can be trained to generate measurement data. To train Model 1122, measurement station 1102 can perform a measurement analysis on wafer 1104. Measurement station 1102 can generate measurement data 1110. In some embodiments, a complete set of measurement data from measurement station 1102 can be used as measurement data 1110 for training Model 1122. In other embodiments, a subset of data points within the measurement data generated by measurement station 1102 can be included in measurement data 1110 for training Model 1122. For example, measurement data 1110 can include film thickness or displacement measurements at a subset of predetermined locations on wafer 1104. The displacement data of wafer 1104 can be captured at a plurality of points along a radius across the surface of wafer 1104. Note that displacement data 1112 from displacement measurement system 1106 can include displacement data captured at a predetermined radius of wafer 1104 as wafer 1104 rotates. Measurement data 1110 can include a complete 2D set of measurements across the surface of wafer 1104. This 2D set can include the predetermined radius of displacement measurement system 1106, along with displacement measurements at a plurality of additional radii, to map the entire surface of wafer 1104.

[0067]

[0087] To train model 1122, displacement data 1112 can be provided as training data 1118 for training model 1122, along with sensor data 1114 (which may be optionally included). Model 1122 can be implemented using any type of classification model. For example, training data 1118 can be used by a least squares regression algorithm to set the weights or node values of model 1122. For example, model 1122 can be implemented using a logistic regression model, a k-nearest neighbor model, a decision tree, a support vector machine, a naive Bayes model, a random forest, a gradient boosting model, and / or any other classification model type. Labels 1120 of training data 1118 can be generated using measurement data 1110. For example, model 1122 can be configured to output a classification of the shape of wafer 1104. Measurement data 1110 can be used to select one of the shape outputs of model 1122 that is used as label 1120 of training data 1118. Alternatively, model 1122 can be configured to output a displacement mapping that includes displacement measurements for positions on wafer 1104. Measurement data 1110 can use displacement values in a 2D mapping of wafer 1104 as label 1120 of training data 1118.

[0068]

[0088] Note that the example of FIG. 11 trains model 1122 using measurement data to generate wafer characteristics or measurement data. Thereby, when using the trained model 1122, measurement data can be generated by model 1122 based on displacement data 1112 without requiring measurement station 1102 for subsequent wafers processed by the system. However, other models 1122 may be trained to generate control signals for a cleaning or polishing process instead of measurement data. Although not explicitly shown in FIG. 11, measurement data 1110 used as label 1120 for training model 1122 may be replaced with a control signal that matches the shape dimensions of wafer 1104.

[0069]

[0089] For example, the measurement data 1110 can be used to select or calculate control signal values for a cleaning or polishing process. When the curvature on one side of the wafer 1104 is detected by the displacement data 1112 or the measurement data 1110, the control signal for the polishing process can increase the polishing pressure in the zone of the polishing head behind the curved area of the wafer 1104. These control signals can be selected as the label 1120 based on the measurement data 1110 or the displacement data 1112, depending on the embodiment.

[0070]

[0090] FIG. 12 shows a block diagram 1200 of a system for using a trained model to control a cleaning or polishing process, according to some embodiments. After training the model 1122 using the process described above with reference to FIG. 11, the process may bypass the measurement station and instead use the displacement data 1112. The displacement data 1112 can be provided as an input to the trained model 1122. Optionally, some embodiments may also include other sensor data from additional sensors if sensor data was used to train the model 1122. The model 1122 can propagate these inputs through the internal layers and nodes of the model 1122 to generate a classification output that classifies the displacement data 1112. This classification can generate an output that can be used to control the polishing or cleaning process.

[0071]

[0091] In this example, controlling the cleaning or polishing process may include selecting from among a plurality of different cleaning or polishing processes. For example, a first cleaning or polishing process 1202-1 may be performed on a substantially flat wafer. Thus, the polishing or cleaning process may be performed at a higher speed. In contrast, a second cleaning or polishing process 1202-2 may be configured to polish a wafer having significant curvature or warpage. Thus, the wafer may be polished more carefully at a slower speed. Thus, the classification performed by model 1122 may be integrated into the overall wafer manufacturing pipeline to classify the wafers individually and maintain parallel lanes of manufacturing optimized for the wafer type. By feeding substantially flat wafers into the first polishing or cleaning process 1202-1, these wafers are polished significantly faster, and bottleneck wafers are fed into the second polishing or cleaning process 1202-2 and may be performed in parallel and separately. This improves the overall throughput of the process, eliminates the need to accommodate every wafer shape dimension, and allows the speed of the individual polishing or cleaning processes to be optimized for a particular wafer shape. For example, instead of selecting a polishing speed corresponding to the shape dimensions of all wafer surfaces, each of the plurality of polishing or cleaning processes 1202 may be optimized to process a particular type (e.g., flat, curved, warped, "potato chip" shaped, etc.).

[0072]

[0092] FIG. 13 shows a block diagram 1300 of a process for using a model to generate control signals for a cleaner polishing process, according to some embodiments. In this example, model 1122 may be trained to generate specific control signals that can be used to control a cleaning or polishing process for a wafer. When receiving displacement data 1112 as input, model 1122 may generate a control signal 1302 that can be provided as part of a recipe or real-time control signal for cleaning or polishing process 1202-1. For example, the output of model 1122 may be included as part of a recipe. This recipe includes control signals for all of the processes that are part of the semiconductor manufacturing stage. The recipe may then be provided to the cleaning or polishing process to be executed. Alternatively, control signal 1122 may be provided directly to the process during execution of the process. Thereby, model 1122 can control the cleaning or polishing process in real time.

[0073]

[0093] Although not explicitly shown in FIG. 13, some embodiments may include intermediate steps from FIG. 12 to generate measurement data. For example, model 1122 may generate measurement data as described above. The measurement data may be used to select or set the control signals shown in FIG. 13. For example, the thickness of the film determined by the measurement data may be used to control the polishing rate or pressure of that portion of the wafer.

[0074]

[0094] The control signal generated by model 1122 can include any of the inputs that can be provided to any semiconductor manufacturing process. In the case of this specific polishing or cleaning process, the control signal can be provided to control the rotational speed 1302-1 of the platen or pedestal that supports the wafer in the cleaning or polishing process. The control signal can also include the head rotational speed 1302-2 for the head that presses the wafer against the polishing or cleaning pad and rotates and holds it. As described above, the rotational speed for each of these two parameters can be adjusted based on the displacement data and the surface shape dimensions of the wafer. The control signal can also control the flow of the slurry used in the polishing or cleaning process. This can include not only the type of slurry used, but also the flow rate of the slurry. For example, if more aggressive polishing is required to improve the overall processing time, a more abrasive slurry can be used. As described above, some polishing or cleaning heads can include zones that can apply different pressures to different parts of the wafer within the polishing or cleaning head. The control signal can include the zone pressure 1302-4 for each of these different zones. For example, by increasing the pressure in a specific zone corresponding to the curved portion of the wafer, more aggressive polishing or cleaning can be performed on that wafer area.

[0075]

[0095] It should be noted that the control signal provided to the cleaning or polishing process 1202-1 shown in FIG. 13 is provided by way of example only and is not intended to be limiting. The cleaning or polishing process can include many additional controls such as temperature control, the flow rate of various gases or other substances within the chamber, chamber pressure control, and / or other environmental parameter controls. Some embodiments can also provide each of these controls as a time series of values such that the control values change over time. For example, model 1122 can be trained to generate a time series output of the speed for the head rotational speed 1302-2. In order to flatten the curved portion of the wafer, it can be polished at a high speed initially and then the speed can be gradually reduced to more evenly and carefully polish the entire flat wafer.

[0076]

[0096] Figure 14 shows a block diagram 1400 of how a model can be used to generate measurement data 1402, according to some embodiments. Note that the model 1122 need not provide values for the entire data set of the measurement data 1402. Instead, some embodiments may provide a subset of the values of the measurement data 1402. For example, displacement data 1112 and / or other sensor data 1116 may be used to characterize the thickness of a film on the surface of a wafer. This thickness may be used to input into a field of the measurement data 1402. Thus, the measurement data 1402 may include less data than a complete set of the measurement data 1402.

[0077]

[0097] In some embodiments, a subset of the values provided by the model 1122 may be combined with other values from the actual measurement process to generate a complete measurement data set 1402. For example, the measurement process may be reduced such that only a subset of the values are measured and the overall measurement process time is shortened. The remaining values may be input using the model 1122. In other embodiments, the model 1122 may estimate all of the measurement data 1402. For example, many of the values of the measurement data 1402 may be strongly correlated with the shape and topology of the wafer measured by the displacement data 1112. The model 1122 may be trained to recognize these correlations and generate estimated values of the measurement data 1402 based on the measured displacements.

[0078]

[0098] In some embodiments, model 1122 may be trained to select a set of existing measurement data that can be used to input measurement data 1402. For example, measurement data 1402 may include data fields that characterize the thickness of a film on a wafer. Multiple sets of values of these thickness data fields may be stored from previous wafer tests or training data. When model 1122 receives sensor data 1116, model 1122 may be configured to select one of the existing data sets that characterize the thickness of the film on the wafer. For any other set of fields of measurement data 1402, the same process may be used to select an existing data set.

[0079]

[0099] FIG. 15 shows a flowchart 1500 of a method for training and using a model using displacement data, according to some embodiments. The method may include receiving displacement data (1502) generated using a displacement sensor. The displacement data may be measured for a wafer. The displacement data may indicate the relative displacement of the wafer with respect to the displacement sensor. In some embodiments, this may include rotating the wafer around the center of the wafer and measuring the displacement of the wafer at a predetermined distance from the center of the wafer. Some embodiments may also measure additional sensor data as described above.

[0080]

[0100] The method may further include providing the displacement data to a model trained using a measurement data set and a corresponding displacement data set (1504). For example, the displacement data may be provided to the model as a labeled training data set from a previous wafer process. The model may be trained as a classification model to recognize known patterns in the displacement data and other inputs and then select a corresponding output set based on the categorization of the inputs.

[0081]

[0101] This method may further include generating wafer measurement data based on an output from a model in response to providing displacement data as an input to the model (1506). In some embodiments, control signals for a cleaning or polishing chamber may be generated based on the output from the model. The output of the model may be used to control a cleaning or polishing process for the same wafer in a subsequent processing chamber. For example, a plurality of cleaning or polishing pipelines with different speeds may be arranged. Here, the output of the model guides the wafer to different polishing processes based on the flatness of the wafer. The output from the model may include control signals for controlling polishing pressure, speed, slurry flow rate, polishing material, etc. based on wafer displacement data.

[0082]

[0102] Each of the methods described herein can be implemented by a computer system. Each step of these methods can be automatically executed by a computer system and / or provided with user-involved input / output. For example, a user can provide input for each step in the method, and each of these inputs can be in response to a specific output that requests such input, and the output is generated by the computer system. Each input can be received in response to the corresponding requested output. Further, the input can be received from the user, received from another computer system as a data stream, retrieved from a memory location, retrieved via a network, requested from a web service, etc. Similarly, the output can be provided to the user, provided to another computer system as a data stream, stored in a memory location, sent via a network, provided to a web service, etc. In short, each step of the methods described herein can be implemented by a computer system and can involve any number of inputs, outputs, and / or requests to and from the computer system, which may or may not involve the user. Steps that do not involve the user can be said to be automatically implemented by a computer system without human intervention. Thus, in light of the present disclosure, it will be understood that each step of each method described herein can be modified to include input and output to and from the user or can be automatically performed by a computer system without human intervention where any decision is made by a processor. Further, some embodiments of each of the methods described herein can be implemented as a set of instructions stored on a tangible, non-transitory storage medium to form a tangible software product.

[0083]

[0103] FIG. 16 shows an exemplary computer system 1600 in which various embodiments can be implemented. The computer system 1600 can be used to implement any of the computer systems described above. For example, the computer system 1600 can be used to control displacement sensors and store displacement data. Also, the computer system 1600 can be used to transmit displacement data to other semiconductor manufacturing devices such as a CMP apparatus or a cleaner. The CMP apparatus and / or the cleaner can also include a computer system 1600 that controls a polishing and / or cleaning process using the displacement data.

[0084]

[0104] As shown in the figure, the computer system 1600 includes a processing unit 1604 that communicates with several peripheral subsystems via a bus subsystem 1602. These peripheral subsystems can include a processing acceleration unit 1606, an I / O subsystem 1608, a memory subsystem 1618, and a communication subsystem 1624. The memory subsystem 1618 includes a tangible computer-readable storage medium 1622 and a system memory 1610.

[0085]

[0105] The bus subsystem 1602 provides a mechanism for the various components and subsystems of the computer system 1600 to communicate with each other as intended. The bus subsystem 1602 is shown schematically as a single bus, but alternative embodiments of the bus subsystem can utilize multiple buses. The bus subsystem 1602 can be any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, and a local bus that uses any of various bus architectures. For example, such architectures can include an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an Extended ISA (EISA) bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus that can be implemented as a mezzanine bus manufactured in accordance with the IEEE P1386.1 standard.

[0086]

[0106] The processing unit 1604, which may be implemented as one or more integrated circuits (e.g., a conventional microprocessor or microcontroller), controls the operation of the computer system 1600. One or more processors may be included within the processing unit 1604. These processors may include single-core or multi-core processors. In some embodiments, the processing unit 1604 is implemented as one or more independent processing units 1632 and / or 1634, and a single or multi-core processor may be included within each processing unit. In other embodiments, the processing unit 1604 may also be implemented as a quad-core processing unit formed by integrating two dual-core processors on a single chip.

[0087]

[0107] In various embodiments, the processing unit 1604 can execute various programs in response to program code and can maintain multiple programs or processes to be executed simultaneously. At a given time, some or all of the program code to be executed may reside in one or more processors 1604 and / or in the memory subsystem 1618. Through suitable programming, one or more processors 1604 can provide the various functions described above. The computer system 1600 may further include a processing acceleration unit 1606, which can include a digital signal processor (DSP), an application-specific processor, and the like.

[0088]

[0108] The I / O subsystem 1608 may include a user interface input device and a user interface output device. The user interface input device may include a keyboard, a pointing device such as a mouse or trackball, a touchpad or touch screen incorporated into a display, a scroll wheel, a click wheel, a dial, a button, a switch, a keypad, an audio input device having a voice command recognition system, a microphone, and other types of input devices. The user interface input device may include, for example, a motion detection and / or gesture recognition device such as a Microsoft Kinect (registered trademark) motion sensor that enables a user to control and interact with an input device, such as a Microsoft Xbox (registered trademark) 360 game controller, through a natural user interface using gestures and spoken commands. The user interface input device may also include an eye gesture recognition device such as a Google Glass (registered trademark) blink detector that detects eye activity from the user (e.g., a "blink" while taking a photo and / or making a menu selection) and converts the eye gesture into an input to the input device (e.g., Google Glass (registered trademark)). Further, the user interface input device may include an audio recognition detection device that enables a user to interact with a voice recognition system (e.g., a Siri (registered trademark) navigator) through voice commands.

[0089]

[0109] The user interface input device may also include, but is not limited to, a three-dimensional (3D) mouse, joystick or pointing stick, game pad and graphic tablet, audio / visual devices such as speakers, digital cameras, digital camcorders, portable media players, webcams, image scanners, fingerprint scanners, barcode readers, 3D scanners, 3D printers, laser rangefinders, and eye tracking devices. Further, the user interface input device may include medical imaging input devices such as, for example, computed tomography, magnetic resonance imaging, positron emission tomography, medical ultrasound examination devices, etc. The user interface input device may also include audio input devices such as, for example, MIDI keyboards, digital musical instruments, etc.

[0090]

[0110] The user interface output device may include a display subsystem, indicator lights, or non-visual displays such as audio output devices. The display subsystem may be a flat panel device such as using a cathode ray tube (CRT), liquid crystal display (LCD) or plasma display, a projection device, a touch screen, etc. Generally, the use of the term "output device" shall include all conceivable types of devices and mechanisms for outputting information from the computer system 1600 to the user or other computers. For example, the user interface output device may include, but is not limited to, monitors, printers, speakers, headphones, automotive navigation systems, plotters, audio output devices, and modems, and various display devices for visually communicating text, graphics, and audio / video information.

[0091]

[0111] The computer system 1600 may include a memory subsystem 1618 that includes software elements shown as being currently located within the system memory 1610. The system memory 1610 may store program instructions that are loadable and executable on the processing unit 1604, as well as data generated during the execution of these programs.

[0092]

[0112] Depending on the configuration and type of computer system 1600, system memory 1610 can be volatile (such as random access memory (RAM)) and / or non-volatile (such as read-only memory (ROM), flash memory, etc.). RAM is typically immediately accessible to processing unit 1604 and / or contains data and / or program modules that are currently being operated on and executed by processing unit 1604. In some embodiments, system memory 1610 can include multiple different types of memory, such as static random access memory (SRAM) or dynamic random access memory (DRAM). In some embodiments, a basic input / output system (BIOS), which includes basic routines that help transfer information between elements within computer system 1600, such as during startup, can generally be stored in ROM. By way of example and not limitation, system memory 1610 also shows application programs 1612, which can include client applications, web browsers, middle tier applications, relational database management systems (RDBMS), etc., program data 1614, and operating system 1616. By way of example, operating system 1616 can include various versions of Microsoft Windows (registered trademark), Apple Macintosh (registered trademark), and / or Linux operating systems (including, but not limited to, various GNU / Linux operating systems, Google Chrome (registered trademark) OS, etc.), various commercially available UNIX (registered trademark) or UNIX-like operating systems, and / or mobile operating systems such as iOS, Windows (registered trademark) Phone, Android (registered trademark) OS, BlackBerry (registered trademark) 10 OS, and Palm (registered trademark) OS.

[0093]

[0113] The memory subsystem 1618 may also provide a tangible computer-readable storage medium for storing the basic programming and data structures that provide the functionality of some embodiments. When executed by a processor, software (programs, code modules, instructions) that provides the functionality described above may be stored in the memory subsystem 1618. These software modules or instructions may be executed by the processing unit 1604. The memory subsystem 1618 may also provide a repository for storing data used in accordance with some embodiments.

[0094]

[0114] The memory subsystem 1600 may also include a computer-readable storage medium reader 1620 that may be further connected to a computer-readable storage medium 1622. Together with and, optionally, in combination with the system memory 1610, the computer-readable storage medium 1622 may comprehensively represent remote, local, fixed, and / or removable storage devices and storage media for temporarily and / or more persistently containing, storing, transmitting, and retrieving computer-readable information.

[0095]

[0115] The computer-readable storage medium 1622 that includes the code, or portions of code, can include any suitable medium including storage media and communication media, such as volatile and non-volatile, removable and non-removable media implemented in any method or technology for the storage and / or transmission of information. This can include tangible computer-readable storage media, such as RAM, ROM, electrically erasable programmable ROM (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or other tangible computer-readable media. This can also include non-tangible computer-readable media, such as data signals, data transmissions, or any other medium that can be used to transmit the desired information and can be accessed by computing system 1600.

[0096]

[0116] As an example, computer-readable storage medium 1622 can include a hard disk drive that reads from or writes to a non-removable non-volatile magnetic medium, a magnetic disk drive that reads from or writes to a removable non-volatile magnetic disk, and an optical disk drive that reads from or writes to a removable non-volatile optical disk such as a CD ROM, DVD, and Blu-Ray (registered trademark) disk, or other optical media. Computer-readable storage medium 1622 can include, without limitation, a Zip (registered trademark) drive, a flash memory card, a Universal Serial Bus (USB) flash drive, a Secure Digital (SD) card, a DVD disk, a digital video tape, and the like. Computer-readable storage medium 1622 can also include a solid state drive (SSD) based on flash memory, an enterprise flash drive, a solid state ROM, etc., an SSD based on non-volatile memory, a solid state RAM, a dynamic RAM, a static RAM, a DRAM-based SSD, a magnetic resistance RAM (MRAM) SSD, etc., an SSD based on volatile memory, and a hybrid SSD that uses a combination of a DRAM-based SSD and a flash memory-based SSD. Disk drives and their associated computer-readable media can provide non-volatile storage of computer-readable instructions, data structures, program modules, and other data for computer system 1600.

[0097]

[0117] The communication subsystem 1624 provides an interface to other computer systems and networks. The communication subsystem 1624 serves as an interface for receiving data from other systems to the computer system 1600 and for transmitting data to other systems from the computer system 1600. For example, the communication subsystem 1624 may enable the computer system 1600 to connect to one or more devices via the Internet. In some embodiments, the communication subsystem 1624 may include radio frequency (RF) transceiver components, a global positioning system (GPS) receiver component, and / or other components for accessing wireless voice and / or data networks (e.g., using cellular phone technology, advanced data network technologies such as 3G, 4G, or EDGE (Enhanced Data rates for Global Evolution), WiFi (IEEE802.11 family of standards), or other mobile communication technologies, or any combination thereof). In some embodiments, the communication subsystem 1624 may provide wired network connectivity (e.g., Ethernet) in addition to or instead of a wireless interface.

[0098]

[0118] In some embodiments, the communication subsystem 1624 may also receive input communications in the form of structured and / or unstructured data feeds 1626, event streams 1628, event updates 1630, etc., for one or more users who may use the computer system 1600.

[0099]

[0119] As an example, the communication subsystem 1624 may be configured to receive in real time data feeds 1626 such as Twitter (registered trademark) feeds, Facebook (registered trademark) updates, web feeds such as Rich Site Summary (RSS) feeds, and / or real-time updates, etc., from one or more third-party information sources from users of social networks and / or other communication services.

[0100]

[0120] Furthermore, communication subsystem 1624 may also be configured to receive data in the form of a continuous data stream. The data may include an event stream 1628 of real-time events and / or event updates 1630, which may have no explicit end and may be substantially continuous or infinite. Examples of applications that generate continuous data may include, for example, sensor data applications, financial tickers, network performance measurement tools (such as network monitoring and traffic management applications), clickstream analysis tools, automotive traffic monitoring, and the like.

[0101]

[0121] Communication subsystem 1624 may also be configured to output structured and / or unstructured data feeds 1626, event streams 1628, event updates 1630, etc. to one or more databases coupled to one or more streaming data source computers coupled to computer system 1600.

[0102]

[0122] Computer system 1600 may be one of various types, including a handheld portable device (such as an iPhone (registered trademark) cellular phone, an iPad (registered trademark) computing tablet, a PDA), a wearable device (such as a Google Glass (registered trademark) head-mounted display), a PC, a workstation, a mainframe, a kiosk, a server rack, or any other data processing system.

[0103]

[0123] Due to the ever-changing nature of computers and networks, the description of the computer system 1600 shown in the figures is only as a specific example. Many other configurations with more or fewer components than the systems shown in the figures are possible. For example, customized hardware may also be used, and / or certain elements may be implemented in hardware, firmware, software (including applets), or combinations. Additionally, connections to other computing devices, such as network input / output devices, may be employed. Based on the disclosure and teachings provided herein, other ways and / or methods for implementing various embodiments should be apparent.

[0104]

[0124] In the above description, for the sake of convenience of explanation, numerous specific details have been described to provide a complete understanding of various embodiments. However, it will be apparent that some embodiments can be practiced without some of these specific details. In other instances, well-known structures and devices are shown in block diagram form.

[0105]

[0125] The above description provides only exemplary embodiments and does not limit the scope, applicability, or configuration of the present disclosure. Rather, the above description of various embodiments provides a possible disclosure for implementing at least one embodiment. It should be understood that various changes can be made in the functions and arrangements of elements without departing from the spirit and scope of some of the embodiments recited in the appended claims.

[0106]

[0126] Specific details are given in the above description to provide a complete understanding of the embodiments. However, it should be understood that the embodiments may be practiced without these specific details. For example, circuits, systems, networks, processes, and other components may sometimes be shown as components in block diagram form in order not to obscure the embodiments with unnecessary details. In other instances, well-known circuits, processes, algorithms, structures, and techniques may sometimes be shown without unnecessary detail in order to avoid obscuring the embodiments.

[0107]

[0127] Also, note that individual embodiments have been described as a process, shown as a flowchart, a flow diagram, a data flow diagram, a structure diagram, or a block diagram. Although a flowchart may describe the operations as a sequential process, many of the operations may be performed in parallel or simultaneously. Further, the order of the operations may be rearranged. A process is terminated when its operations are completed, but it may have additional steps not included in the figure. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc. When a process corresponds to a function, its termination may correspond to the return of the function to the calling function or the main function.

[0108]

[0128] The term "computer-readable medium" includes, without limitation, portable or fixed storage devices, optical storage devices, wireless channels, and various other media capable of storing, containing, or carrying one or more instructions and / or data. A code segment or machine-executable instruction can represent a procedure, a function, a subprogram, a program, a routine, a subroutine, a module, a software package, a class, or any combination of instructions, data structures, or program statements. A code segment can be coupled to another code segment or a hardware circuit by passing and / or receiving information, data, arguments, parameters, or memory contents. Information, arguments, parameters, data, etc. can be passed, forwarded, or transmitted via any suitable means including memory sharing, message passing, token passing, network transmission, etc.

[0109]

[0129] Furthermore, embodiments can be implemented by hardware, software, firmware, middleware, microcode, a hardware description language, or any combination thereof. When implemented in software, firmware, middleware or microcode, the program code or code segments for performing the necessary tasks can be stored in a machine-readable medium. One or more processors can perform the necessary tasks.

[0110]

[0130] In the foregoing specification, features have been described with reference to specific embodiments thereof, but it should be recognized that not all embodiments are limited thereto. The various features and aspects of some embodiments can be used individually or together. Furthermore, embodiments can be utilized in any number of environments and applications other than those described herein without departing from the broader spirit and scope of the specification. Accordingly, the specification and drawings are to be regarded as illustrative rather than restrictive.

[0111]

[0131] Furthermore, for purposes of explanation, the methods have been described in a particular order. It should be understood that in alternative embodiments, the methods may be performed in a different order than that described. It should also be understood that the methods described above may be implemented by hardware components or may be embodied as a sequence of machine-executable instructions used to cause a machine, such as a general purpose or special purpose processor or logic circuitry programmed by instructions, to perform the methods. These machine-executable instructions may be stored on one or more machine-readable media, such as a CD-ROM or other type of optical disk, a floppy disk, a ROM, a RAM, an EPROM, an EEPROM, a magnetic or optical card, a flash memory, or other type of machine-readable media suitable for storing electronic instructions. Alternatively, the methods may be implemented by a combination of hardware and software.

Claims

1. One or more displacement sensors arranged to measure the displacement of the wafer as the wafer rotates on a platform; A cleaning or polishing chamber configured to clean or polish the wafer; A computer system; A system comprising: Receiving displacement data generated using the one or more displacement sensors for the wafer, the displacement data indicating the displacement of the wafer relative to the one or more displacement sensors; Providing the displacement data to a model trained using a displacement data set; Generating a control signal for the cleaning or polishing chamber based on an output from the model in response to receiving the displacement data as an input; Using the control signal to control the cleaning or polishing process for the wafer. A system configured to perform operations including the above.

2. Controlling the cleaning or polishing process for the wafer includes selecting the cleaning or polishing process from a plurality of different cleaning or polishing processes, the cleaning or polishing process having a shorter runtime than at least one of the plurality of different cleaning or polishing processes. The system according to Claim 1.

3. Controlling the cleaning or polishing process for the wafer includes controlling the rotational speed of a platen that supports the wafer in the cleaning or polishing process. The system according to Claim 1.

4. Controlling the cleaning or polishing process for the wafer includes controlling the rotational speed of a cleaning or polishing head in the cleaning or polishing process. The system according to Claim 1.

5. Controlling the cleaning or polishing process for the wafer includes controlling the flow of slurry used in the cleaning or polishing process. The system according to Claim 1.

6. Controlling the cleaning or polishing process for the wafer includes controlling the pressure applied to zones within a cleaning or polishing head in the cleaning or polishing process. The system according to Claim 1.

7. The system of claim 1, wherein the displacement data indicates a curved or warped area on the wafer. **Claim 8** Receiving displacement data generated using a displacement sensor for a wafer, wherein the displacement data indicates displacement of the wafer relative to the displacement sensor; Providing the displacement data to a model trained using a measurement data set and a corresponding displacement data set; Generating measurement data for the wafer based on an output from the model in response to receiving the displacement data as an input to the model A method comprising: **Claim 9** Using the measurement data to control a cleaning or polishing process for the wafer. The method of claim 8, further comprising: **Claim 10** The method of claim 8, wherein the measurement data includes thickness of a thin film or feature on the wafer. **Claim 11** Rotating the wafer about a center thereof; Measuring displacement of the wafer at a predetermined distance from the center of the wafer as the wafer rotates to generate the displacement data The method of claim 8, further comprising: **Claim 12** Measuring displacement of a baseline wafer to generate baseline displacement data representative of a flat wafer surface. The method of claim 11, further comprising: **Claim 13** The method of claim 12, wherein generating the displacement data includes determining displacement of the wafer relative to the baseline displacement data. **Claim 14** The method of claim 11, further comprising mapping the displacement data to two-dimensional coordinates on the wafer based on alignment data. **Claim 15** The method of claim 11, further comprising mapping the displacement data to a rotation angle on the wafer based on alignment data. **Claim 16** The method of claim 11, further comprising identifying a displacement area on the wafer in the displacement data and providing the displacement area to a polishing or cleaning process. **Claim 17** A non-transitory computer-readable medium that, when executed by one or more processors, causes the one or more processors to: Receiving displacement data generated using one or more displacement sensors for a wafer, wherein the displacement data indicates displacement of the wafer relative to the one or more displacement sensors; Providing the displacement data to a model trained using a displacement data set; Generating a control signal for a cleaning or polishing chamber based on an output from the model in response to receiving the displacement data as an input; A non-transitory computer-readable medium comprising instructions for causing an operation to be performed, the operation including the above. **Claim 18** The operation further includes: Using the control signal to control the cleaning or polishing process for the wafer. The non-transitory computer-readable medium according to claim 17, further comprising the above. **Claim 19** The non-transitory computer-readable medium according to claim 18, wherein controlling the cleaning or polishing process for the wafer includes controlling a rotational speed of a platen that supports the wafer in the cleaning or polishing process. **Claim 20** The non-transitory computer-readable medium according to claim 18, wherein controlling the cleaning or polishing process for the wafer includes selecting the cleaning or polishing process from a plurality of different cleaning or polishing processes.

Images