Substrate placement optimization using substrate measurement

Abstract

To provide a computer readable medium including instructions that, when executed by a processing device, cause the processing device to perform operations.SOLUTION: Operations include processing a first substrate in a process chamber while the first substrate is supported by a substrate support at a first placement location. The first substrate includes a first surface profile after processing. Operations further include generating a first surface profile map of the first surface profile using a substrate measurement system. Operations further include determining a plurality of etch rates corresponding to a plurality of locations on the first substrate. Operations further include processing data associated with the plurality of etch rates using a model, the model being to output one or more estimated surface profiles associated with one or more estimated placement locations. Operations further include determining a recommended placement for substrates on the substrate support based on the one or more estimated placement locations.SELECTED DRAWING: Figure 10A

Description

Technical Field

[0001] Embodiments of the present disclosure generally relate to optimizing the placement of substrates within a processing chamber, and more particularly to generating a map and / or numerical profiling of substrates processed using the chamber and optimizing the placement of substrates within the processing chamber based on the map and / or numerical profiling of the substrates.

Background Art

[0002] Substrate processing can include a series of processes for fabricating electrical circuits within a semiconductor according to a circuit design. These processes can be implemented within a series of process chambers. The successful operation of modern semiconductor manufacturing equipment can be aimed at facilitating a stable flow of wafers from one chamber to another during the process of forming electrical circuits within the wafer to form a product. In processes that perform many substrate processes, the conditions of the processing chamber may be changed, and as a result, the processed substrates may fail to meet the target conditions and results.

Summary of the Invention

Problems to be Solved by the Invention

[0003] Substrates are placed within a process chamber for processing. The placement of the substrates relative to the chamber components can lead to variations in the quality of the products fabricated using the process chamber and / or the discard of substrates processed using the process chamber.

Means for Solving the Problems

[0004] The following is a simplified overview of the present disclosure to provide a basic understanding of some aspects of the present disclosure. This overview is not an extensive overview of the present disclosure. This overview is not intended to identify key or important elements of the present disclosure, nor to delineate the scope of particular embodiments or the scope of the claims of the present disclosure. Its sole purpose is to present some concepts of the present disclosure in a simplified form as an introduction to the more detailed description that follows.

[0005] In an exemplary embodiment, a computer-readable medium includes instructions that, when executed by a processing device, cause the processing device to perform operations. These operations include processing a first substrate within a process chamber of a substrate processing system while the first substrate is supported at a first placement location on a substrate support by the substrate support. The first substrate includes a first surface profile after processing. These operations further include generating a first surface profile map of the first surface profile using a substrate measurement system. These operations further include determining a first plurality of etching rates corresponding to a first plurality of locations on the first substrate based on the first surface profile map. These operations further include processing data associated with the first plurality of etching rates using a model. This model is for outputting one or more estimated surface profiles associated with one or more estimated placement locations on the substrate support based on the first plurality of etching rates. These operations further include determining a recommended placement for the substrate on the substrate support based on the one or more estimated placement locations.

[0006] In an exemplary embodiment, the system includes a process chamber that includes a substrate support. The system further includes a substrate measurement tool, a memory, and a processing device operably coupled to the memory. The processing device is for processing a first substrate within the process chamber while the first substrate is supported by the substrate support at a first placement location on the substrate support. The first substrate includes a first surface profile after processing. The processing device is further for generating a first surface profile map of the first surface profile using the substrate measurement tool. The processing device is further for determining a first plurality of etching rates corresponding to a first plurality of locations on the first substrate based on the first surface profile map. The processing device is further for processing data associated with the first plurality of etching rates using a model. The model is for outputting one or more estimated surface profiles associated with one or more estimated placement locations on the substrate support based on the first plurality of etching rates. The processing device is further for determining a recommended placement for the substrate on the substrate support based on the one or more estimated placement locations.

[0007] In an exemplary embodiment, the method includes processing a first substrate within a process chamber while the first substrate is supported by a substrate support at a first location on the substrate support. The first substrate includes a first surface profile after processing. The method further includes generating a first surface profile map of the first surface profile using a substrate measurement system. The method further includes determining a first plurality of etching rates corresponding to a first plurality of locations on the first substrate based on the first surface profile map. The method further includes processing data associated with the first plurality of etching rates using a model. The model is for outputting one or more estimated surface profiles associated with one or more estimated locations on the substrate support based on the first plurality of etching rates. The method further includes determining a recommended placement for the substrate on the substrate support based on the one or more estimated locations.

[0008] The present disclosure is shown by way of example and not limitation, and like references in the figures of the accompanying drawings indicate similar elements. Note that various references to "an embodiment" or "one embodiment" in the present disclosure do not necessarily refer to the same embodiment, and such references mean at least one.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2A

Figure 2B

Figure 2C

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10A

Figure 10B

Figure 11A

Figure 11B

Figure 12A

Figure 12B

Figure 13A

Figure 13B

Figure 13C

Figure 14

Figure 15

DETAILED DESCRIPTION

[0010] Embodiments of the present disclosure are directed to systems and methods for optimizing substrate placement within a process chamber using substrate measurements. Process results of a manufacturing process depend on many factors, including process recipes, chamber parameter settings, chamber component conditions, and substrate placement within the process chamber. For example, process results may vary across the surface of a substrate based on the placement of the substrate relative to a process kit ring. The gap between the edge of the substrate and the process kit ring is often related to the influence of substrate processing near the edge of the substrate. Additionally, process results may vary across the surface of the substrate based on conditions of a showerhead, conditions of a substrate support that supports the substrate, conditions of a chamber liner, conditions of pumps and / or valves, etc. An optimized placement of the substrate may be affected by the conditions of the process chamber components described herein. For example, any temporal changes in a substrate support, such as an electrostatic chuck, a clamp, a vacuum chuck, a heater, a support having a pocket with a lip at the edge of the support, and / or a substrate support including one or more embedded features (e.g., a heater, a cooling plate, an electrical element, etc.), slowly affect the substrate results by, for example, temperature changes across the surface of the processed substrate, radio frequency (RF) fields at the edge of the substrate, etc. These effects on the substrate results slowly affect the optimized substrate placement for best process results. Thus, the optimal placement of the substrate on the substrate support may tend to change over time.

[0011] Substrate results can be particularly affected by substrate placement, especially near the edges of the processed substrate. For example, factors contributing to the substrate etching rate (such as temperature, gas flow, etc.) can cause a tilt near the edge of the processed substrate. "Tilt" refers to the tendency for substrate features (such as valleys, walls, pillars, mesas, etc.) not to be perpendicular to the substrate surface. Excessive tilt can lead to the substrate having low quality and / or being discarded. Tilt often affects the substrate near the edge of the substrate, especially near the outermost edge of the substrate (for example, within a range of 5 millimeters from the substrate edge). Changes in substrate placement relative to components of the substrate support (such as a process kit ring, etc.) can affect the processing of the substrate. For example, differences in the gap between the edge of the substrate and the process kit ring (such as the gap surrounding the wafer) can cause a tilt greater than the threshold amount of acceptable tilt, potentially leading to the discarding of the substrate.

[0012] Embodiments described herein provide a mechanism for determining an optimized placement of a substrate for processing in a process chamber. Using some embodiments, a recommended position for a substrate on a substrate support for processing in a process chamber can be determined. Using the recommended position, an offset for a substrate handling robot (such as a transfer chamber robot, etc.) to place the substrate within the process chamber can be determined.

[0013] In some embodiments, the substrate is processed in a process chamber according to a recipe. The substrate can be processed to deposit and / or etch a film layer and / or one or more features (e.g., measurable features) on the surface of the substrate. The substrate can be a bare substrate or a test substrate without products. Alternatively, the substrate can be a product substrate. The features can include features distributed across the surface of the substrate, such as mesas, dots, structures, valleys, walls, lines, trenches, grooves, references, etc. In some examples, the substrate can be supported by a substrate support (e.g., an electrostatic chuck, etc.) in the process chamber during processing. In some examples, after processing, the substrate can have a surface profile (e.g., a thickness profile, an inclination profile, etc.). In an example of an etching process recipe, the surface profile can indicate the etching rate (e.g., an etching rate profile) across the surface of the substrate during the etching process. In some examples, the etching rate can be correlated with the inclination, particularly at locations near the edge of the substrate on the substrate surface.

[0014] After the film and / or features are deposited or etched on the substrate, in some embodiments, the substrate can be removed from the process chamber and placed into a substrate measurement system. In some embodiments, a profile map of the substrate is generated based on the surface profile of the substrate by the substrate measurement system. The substrate measurement system can be, for example, a reflection light measurement system or other measurement system that measures the film thickness of the film and / or features at multiple locations on the substrate. The thickness information can be used to generate a profile map for the substrate. Alternatively, one or more other profile maps (e.g., of optical constants, roughness, particle count, etc.) of the substrate can be generated from other measurement data.

[0015] Next, a model (e.g., a trained machine learning model, a physics-based model, a statistical model, and / or an image processor, etc.) is used to process thickness information of the film and / or features (e.g., a thickness profile map) or other film and / or feature information (e.g., other profile maps such as an optical constant profile map, a particle number profile map, etc.), and fluctuations in one or more film characteristics can be identified. The model can output an estimated substrate placement value for the placement of the substrate relative to one or more components (e.g., an electrostatic chuck, a process kit ring, etc.) within the process chamber. In an embodiment, the model can output a recommended placement position for the substrate and can output one or more predicted film characteristics (e.g., a predicted profile map of the substrate processed from the recommended placement position) associated with the recommended placement position, and so on.

[0016] In some embodiments, the etching rate at multiple locations on the surface of the substrate is determined from the feature thickness information. In some embodiments, a model is used to process data associated with the etching rate and to determine an estimated placement location for the substrate on the substrate support for processing. For example, a numerical model can process the normalized etching rate for a plurality of test substrates (each test substrate is processed with a different substrate placement) at each specified location of the substrate to determine the effect of different substrate placements. The model can output an estimated substrate placement and / or an estimated substrate placement value for one or more components within the process chamber.

[0017] In some embodiments, based on the estimated substrate placement value, a recommended placement for the substrate on the substrate support is determined. In some examples, the recommended placement is an optimized placement location on a substrate support (e.g., an electrostatic chuck, etc.) for processing the substrate such that it meets the target substrate specifications (e.g., has a tilt less than a threshold amount of tilt near the substrate edge, etc.). In some examples, the optimized location of the substrate on the substrate support is a location where there is a uniform gap around the substrate between the edge of the substrate and the inner diameter of the process kit ring. However, in some examples, the optimized location of the substrate does not provide a uniform gap. In such examples, the optimized location of the substrate takes into account process chamber variables such as the conditions of one or more chamber components (e.g., process kit ring conditions, showerhead conditions, electrostatic chuck conditions, etc.). In some embodiments, a robot arm setting for placing the substrate at the recommended placement location is determined, and those settings are used to place the substrate onto the substrate support.

[0018] Accordingly, the embodiments described herein add new detection capabilities to those process chambers without increasing the cost to the process chambers. In some embodiments, these new detection capabilities can be utilized to increase the quality and / or quantity of processed substrates that meet threshold specifications (e.g., threshold tilt specifications for processed substrates, etc.). Additionally or alternatively, the embodiments described herein can be used to reduce the amount of discarded products (e.g., discarded substrates) resulting from products that do not meet the threshold specifications. The embodiments described herein can be used to automatically optimize certain process variables (e.g., substrate placement during processing) to process substrates of improved quality more quickly and efficiently compared to conventional substrate processing systems. In particular, the embodiments described herein can be used to fabricate substrates having better edge characteristics (e.g., tilt, etc.) compared to substrates fabricated by conventional systems. Again, this results in higher quality substrates, fewer discarded products, etc.

[0019] Figure 1 shows an exemplary computer system architecture 100 according to an aspect of the present disclosure. The computer system architecture 100 includes a client device 120, a manufacturing device 122, a substrate measurement system 126, a prediction server 112 (e.g., for generating prediction data, providing model adaptation, using a knowledge base, etc.), and a data store 150. The prediction server 112 can be part of a prediction system 110. The prediction system 110 can further include server machines 170 and 180. In some embodiments, the computer system architecture 100 can include or be part of a manufacturing system for processing substrates, such as the manufacturing system 200 of FIG. 2A. In additional or alternative embodiments, the computer system architecture 100 can include or be part of a substrate placement prediction system (e.g., for evaluating the conditions of one or more chamber components within a process chamber). Further details regarding the substrate placement prediction system are provided with respect to FIGS. 3-4.

[0020] The components of the client device 120, manufacturing equipment 122, substrate measurement system 126, prediction system 110, and / or data store 150 can be coupled to each other via the network 140. In some embodiments, the network 140 is a public network that provides the client device 120 with access to the prediction server 112, data store 150, and other publicly available computing devices. In some embodiments, the network 140 is a private network that provides the client device 120 with access to the manufacturing equipment 122, substrate measurement system 126, data store 150, and / or other privately available computing devices. The network 140 can include one or more wide area networks (WANs), local area networks (LANs), wired networks (e.g., Ethernet networks), wireless networks (e.g., 802.11 networks or Wi-Fi networks), cellular networks (e.g., Long Term Evolution (LTE) networks), routers, hubs, switches, server computers, cloud computing networks, and / or combinations thereof.

[0021] The client device 120 can include computing devices such as a personal computer (PC), laptop, mobile phone, smartphone, tablet computer, netbook computer, network-connected television (“smart TV”), network-connected media player (e.g., Blu-ray (registered trademark) player), set-top box, over-the-top (OTT) streaming device, operator box, and the like.

[0022] The manufacturing machine 122 can manufacture products according to a strategy. In some embodiments, the manufacturing machine 122 can include, or be part of, a manufacturing system that includes one or more stations (e.g., process chambers, transfer chambers, load locks, factory interfaces, etc.) configured to perform various operations on a substrate.

[0023] The substrate measurement system 126 may be a component of a manufacturing system that can be used to measure substrates before and / or after they are processed in one or more process chambers. The substrate measurement system 126 can be configured to generate optical emission spectroscopy data, reflected light measurement data, and / or other measurement data. The substrate measurement system 126 can include one or more components configured to collect and / or generate measurement data associated with one or more portions of the profile of the surface of the substrate after the substrate is removed from the process chamber.

[0024] In some embodiments, the substrate measurement system 126 can be configured to generate measurement data associated with a substrate processed by other manufacturing equipment 122. The measurement data can include one or more values such as film property data (e.g., wafer space film properties such as thickness), dimensions (e.g., thickness, height, etc.), dielectric constant, dopant concentration, density, defects, etc. The measurement data can be for a finished or semi-finished product, or a test substrate such as a blanket wafer. Some embodiments are discussed with reference to using reflected light measurement data and thickness profile maps to determine the condition of chamber components. However, it should be understood that the principles and embodiments described herein in connection with the reflected light measurement data and thickness profile maps are also applicable to other types of measurement data. For example, measurements can be made of the number of particles, the optical constants of a coating, the surface roughness of a coating, the material composition of a coating, etc. Such measurements can be made for many regions on the substrate and can be used to generate profile maps of the number of particles, optical constants, surface roughness, material composition, etc. across the measured substrate.

[0025] The substrate measurement system 126 can be configured to generate measurement data associated with a substrate before and / or after a substrate process. The substrate measurement system 126 can be integrated with a station of a manufacturing system that includes manufacturing equipment 122. In some embodiments, the substrate measurement system 126 can be coupled to or be part of a station of a process tool maintained in a vacuum environment (e.g., a process chamber, a transfer chamber, etc.). Such a substrate measurement system 126 can be referred to as an in-situ measurement device. Thus, the substrate can be measured by the substrate measurement system 126 while the substrate is within the vacuum environment. For example, after a substrate process (e.g., an etching process, a deposition process, etc.) is performed on the substrate, measurement data for the processed substrate can be generated by the substrate measurement system 126 without the processed substrate being removed from the vacuum environment. In other or similar embodiments, the substrate measurement system 126 can be coupled to or be part of a manufacturing system that is not maintained in a vacuum environment (e.g., a factory interface module, etc.). Such a substrate measurement system 126 can be referred to as an in-situ measurement device.

[0026] As an alternative to the substrate measurement system 126 included within the manufacturing system (e.g., attached to a factory interface or transfer chamber), the substrate measurement system 126 may be a device separate from (i.e., external to) the manufacturing equipment 122. For example, the substrate measurement system 126 can be a stand-alone device that is not coupled to any station of the manufacturing equipment 122. To obtain measurements on a substrate using the removed substrate measurement system 126, a user of the manufacturing system (e.g., a technician, an operator) can remove the substrate processed by the manufacturing equipment 122 from the manufacturing equipment 122 and transfer it to the substrate measurement system 126 for measurement. In some embodiments, the substrate measurement system 126 can transfer measurement data generated for a substrate to a client device 120 coupled to the substrate measurement system 126 via the network 140 (e.g., for presentation to a manufacturing user such as an operator or a technician). In other or similar embodiments, a manufacturing system user can obtain measurement data for a substrate from the substrate measurement system 126 and provide the measurement data to a computer system architecture via the graphical user interface (GUI) of the client device 120.

[0027] The data store 150 can be a memory (e.g., random access memory), a driver (e.g., a hard driver, a flash driver), a database system, or another type of component or device capable of storing data. The data store 150 can include multiple storage components (e.g., multiple drivers or multiple databases) spanning multiple computing devices (e.g., multiple server computers). The data store 150 can store profile maps (e.g., generated from reflectance measurement data, spectral data, etc.) such as a film thickness profile map and / or other substrate profile maps. The film thickness profile map and / or other substrate profile maps can include past maps and / or current maps.

[0028] One or more portions of the data store 150 can be configured to store data that is not accessible to a user of the manufacturing system. In some embodiments, all of the data stored in the data store 150 can be made inaccessible to manufacturing system users. In other or similar embodiments, a portion of the data stored in the data store 150 is inaccessible to the user, while another portion of the data stored in the data store 150 is accessible to the user. In some embodiments, the inaccessible data stored in the data store 150 is encrypted using an encryption mechanism unknown to the user (e.g., the data is encrypted using a secret encryption key). In other or similar embodiments, the data store 150 can include a plurality of data stores, with the data inaccessible to the user stored in a first data store and the data accessible to the user stored in a second data store.

[0029] In some embodiments, the prediction system 110 includes server machines 170 and 180. The server machine 170 includes a training set generator 172 capable of generating a training data set (e.g., a set of data inputs and a set of target outputs) for training, validating, and / or testing one machine learning model 190 or a set of machine learning models 190. Some operations of the training set generator 172 are described in detail below with respect to FIG. 4. In some embodiments, the training set generator 172 can partition the training data into a training set, a validation set, and a test set.

[0030] The server machine 180 can include a training engine 182. The engine can refer to hardware (e.g., circuits, dedicated logic, programmable logic, microcode, processing devices, etc.), software (such as instructions executed on a processing device, a general-purpose computer system, or a dedicated machine), firmware, microcode, or a combination thereof. The training engine 182 can be capable of training one machine learning model 190 or a set of machine learning models 190. The machine learning model 190 can refer to a model artifact that results from the training engine 182 using training data that includes training inputs and corresponding target outputs (the correct responses for each training input). The training engine 182 can discover patterns in the training data that map the training inputs to the target outputs (predicted responses) and provide a machine learning model 190 that captures these patterns. The machine learning model 190 can include a linear regression model, a partial least squares regression model, a Gaussian regression model, a random forest model, a support vector machine model, a neural network, a ridge regression model, etc.

[0031] The training engine 182 can also be capable of authenticating the trained machine learning model 190 using the corresponding set of features of the authentication set from the training set generator 172. In some embodiments, the training engine 182 can assign a performance grade to each of a set of trained machine learning models 190. The performance grade can correspond to the accuracy of each trained model, the speed of each model, and / or the efficiency of each model. The training engine 182 can, according to the embodiments described herein, select a trained machine learning model 190 having a performance grade that meets the performance criteria to be used by the prediction engine 114. Further details regarding the training engine 182 are provided with respect to FIG. 5.

[0032] The prediction server 112 includes a prediction engine 114, which provides data from the substrate measurement system 126 (e.g., a film thickness profile map) as an input to a trained machine learning model 190 and is capable of executing the model 190 trained on that input to obtain one or more outputs. In some embodiments, the trained model 190 executed by the prediction engine 114 is selected by the training engine 182 to have a performance grade that meets performance criteria. As will be further described with respect to FIG. 6, in some embodiments, the prediction engine 114 uses the model 190 to process input data and evaluate a substrate placement for processing a substrate within the process chamber.

[0033] Note that in some other embodiments, the functions of the server machines 170 and 180 and the prediction server 112 can be provided by more or fewer machines. For example, in some embodiments, the server machines 170 and 180 can be integrated into a single machine, while in some other or similar embodiments, the server machines 170 and 180 and the prediction server 112 can be integrated into a single machine. Generally, the functions described in one embodiment as being performed by the server machine 170, the server machine 180, and / or the prediction server 112 can also be performed on the client device 120. Additionally, the functions attributed to a particular component can be performed by different or multiple components operating together.

[0034] In embodiments, a "user" can be represented as a single individual. However, other embodiments of the present disclosure also include a "user" that is an entity controlled by multiple users and / or automated sources. For example, a group of individual users integrated as a group of administrators can be considered a "user".

[0035] FIG. 2A is a schematic top view of an exemplary manufacturing system 200 according to an aspect of the present disclosure. The manufacturing system 200 can perform one or more processes on a substrate 202. The substrate 202 can be any suitably rigid, dimensionally fixed planar object suitable for fabricating electronic devices or circuit components thereon, such as, for example, a disk or wafer containing silicon, a patterned wafer, a glass plate, etc., according to an aspect of the present disclosure. In some embodiments, the manufacturing system 200 can include, or be part of, a computer system architecture 110 according to the embodiment described with respect to FIG. 1.

[0036] The manufacturing system 200 can include a process tool 204 and a factory interface 206 coupled to the process tool 204. The process tool 204 can include a housing 208 having a transfer chamber 210 therein. The transfer chamber 210 can include one or more processing chambers (also referred to as process chambers) 214, 216, 218 disposed around and coupled to the transfer chamber 210. The processing chambers 214, 216, 218 can be coupled to the transfer chamber 210 through respective ports such as slit valves. The transfer chamber 210 can also include a transfer chamber robot 212 configured to transfer the substrate 202 between the process chambers 214, 216, 218, load locks 220, etc. The transfer chamber robot 212 can include one or more arms, and each arm can include one or more end effectors at an end of each arm. The end effector can be configured to handle a specific object such as a wafer.

[0037] In some embodiments, the transfer chamber 210 can also include measurement equipment such as a substrate measurement system 126 attached to the transfer chamber 210. The substrate measurement system 126 can be configured to generate measurement data associated with the substrate 202 before or after a substrate process while the substrate is maintained within a vacuum environment. As shown in FIG. 2A, the substrate measurement system 126 can be attached to or disposed within the transfer chamber 210. When the substrate measurement system 126 is disposed within or coupled to the transfer chamber 210, measurement data associated with the substrate 202 can be generated without removing the substrate 202 from the vacuum environment (e.g., transferring it to the factory interface 206).

[0038] The process chambers 214, 216, 218 can be adapted to perform any number of processes on the substrate 202. Within each processing chamber 214, 216, 218, the same or different substrate processes can be performed. Substrate processes can include, for example, atomic layer deposition (ALD), physical vapor deposition (PVD), chemical vapor deposition (CVD), etching, annealing, curing, pre-cleaning, removal of metals or metal oxides, and the like. Other processes can also be performed on the substrates herein.

[0039] The load lock 220 can also be coupled to the housing 208 and the transfer chamber 210. The load lock 220 can be configured to be associated and coupled to the transfer chamber 210 on one side and the factory interface 206 on the other side. In some embodiments, the load lock 220 can have an environmentally controlled atmosphere that can change from a vacuum environment (where substrates can be transferred to and from the transfer chamber 210) to an inert gas atmosphere at atmospheric pressure (or near atmospheric pressure) (where substrates can be transferred to and from the factory interface 206).

[0040] The factory interface 206 can be any suitable housing such as an equipment front-end module (EFEM). The factory interface 206 can be configured to receive the substrate 202 from a substrate carrier 222 (e.g., a front-opening unified pod (FOUP)) docked at various load ports 224 of the factory interface 206. A factory interface robot 226 (shown in dashed lines) can be configured to transfer the substrate 202 between the substrate carrier 222 (also referred to as a container) and the load lock 220. In other and / or similar embodiments, the factory interface 206 can be configured to receive replacement parts from a replacement part storage container.

[0041] In some embodiments, the manufacturing system 200 can include a substrate measurement system 126 attached to the factory interface 206. The substrate measurement system 126 attached to the factory interface can be configured to generate measurement data associated with the substrate 202 before the substrate 202 is placed in a vacuum environment (e.g., transferred to the load lock 220) and / or after the substrate 202 is removed from the vacuum environment (e.g., removed from the load lock 220).

[0042] The manufacturing system 200 can also be connected to a client device (e.g., the client device 120 of FIG. 1) configured to provide information about the manufacturing system 200 to a user (e.g., an operator). In some embodiments, the client device can provide information to the user of the manufacturing system 200 via one or more graphical user interfaces (GUIs). For example, the client device can provide information regarding one or more chamber condition metrics of the processing chambers 214, 216, 218 (e.g., while the substrate process is being executed) via the GUI.

[0043] The manufacturing system 200 can also include, or be coupled to, a system controller 228. The system controller 228 can be, and / or can include, a computing device such as a personal computer, a server computer, a programmable logic controller (PLC), a microcontroller, etc. The system controller 228 can include one or more processing devices, and such processing devices can be general-purpose processing devices such as a microprocessor, a central processing unit, etc. More specifically, the processing device can be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, or a processor that implements other instruction sets, or a combination of instruction sets. The processing device can also be one or more special-purpose processing devices such as an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), a network processor, etc. The system controller 228 can include a data storage device (e.g., one or more disk drives and / or solid-state drives), main memory, static memory, a network interface, and / or other components. The system controller 228 can execute instructions for implementing any one or more of the techniques and / or embodiments described herein. In some embodiments, the system controller 228 can execute instructions for performing one or more operations in the manufacturing system 200 according to a process plan. These instructions can be stored on a computer-readable storage medium, and the computer-readable storage medium can include main memory, static memory, secondary storage, and / or a processing device (during execution of the instructions).

[0044] In some embodiments, system controller 228 can receive data from substrate measurement system 126 based on measurements of substrates that have been processed by process chambers 214, 216, 218. The data received by system controller 228 can include spectral data, reflected light measurement data, and / or other data for all or a portion of substrate 202. The data received from substrate measurement system 126 can be stored within data store 250. Data store 250 can be included as a component within system controller 228 or can be a separate component from system controller 228. In some embodiments, data store 250 can be a portion of or can include a portion of data store 150 as described with respect to FIG. 1.

[0045] FIG. 2B shows one embodiment of a substrate measurement system 251 that can be used to measure a processed substrate. Substrate measurement system 251 can be an integrated measurement and / or imaging system (e.g., an integrated reflected light measurement (IR) system) configured to measure film characteristics (e.g., thickness, etc.) across the surface of substrate 264 after substrate 264 has been processed in a process chamber. Reflected light measurement is a measurement technique that uses measured changes in light reflected from an object to determine geometric and / or material characteristics of the object. A reflectometer measures the intensity of reflected light over a range of wavelengths. In the case of a dielectric film, these intensity variations can be used to determine the thickness of the film.

[0046] Process results including film thickness can be monitored across one or more substrates with respect to etching and deposition processes, for example, using a substrate measurement system 251. While the substrate 264 is still within the device manufacturing system, an integrated measurement and / or imaging system can be used to measure the surface of the substrate 264. In some embodiments, the substrate measurement system 251 can correspond to the substrate measurement system 126. The substrate measurement system 251 can be connected to a factory interface or transfer chamber. Alternatively, the substrate measurement system 251 can be disposed inside the factory interface or transfer chamber. The substrate measurement system 251 can also be a stand-alone system not connected to the manufacturing system. The substrate measurement system 251 can be mechanically isolated from the factory interface and the external environment to protect the substrate measurement system 251 from external vibrations. In some embodiments, the substrate measurement system 251 and the components included therein can provide analytical measurements (e.g., thickness measurements) that can provide a uniformity profile across the surface of the substrate 264, which is referred to herein as a profile map. A computing device can process the data from the substrate measurement system 251 and provide feedback to the user. The substrate measurement system 251 can be an assembly having the ability to measure film thickness and / or other film properties such as optical constants, particle count, roughness, etc., across a portion or the entire substrate after the substrate has been processed in the chamber. The results of the measurements can be used to determine when to perform maintenance on the process chamber, when to perform further tests on the substrate, when to flag the substrate as out of specification, the placement of the substrate during substrate processing, etc.

[0047] When the substrate 264 is lowered onto the substrate support 256 (e.g., a chuck) and fixed to the substrate support 256, the center of the substrate 264 can be displaced from the center of the chuck. The processing device of the substrate measurement system 251 can determine one or more coordinate conversions between the center of the substrate 264 and the center of the chuck 256 (the center of the chuck corresponds to the axis of rotation about which the chuck rotates), and apply one or more coordinate conversions to correct for the offset, as will be described in more detail below.

[0048] The substrate measurement system 251 can include a rotational actuator 252 and a linear actuator 254. The rotational actuator 252 can be a motor, a rotary actuator (e.g., an electric rotary actuator), etc. The linear actuator 254 can be an electric linear actuator and can convert the rotational motion within the motor into linear or straight-line motion along the axis. The substrate measurement system 251 can include a substrate support 256, a camera 258, a sensor 260, and a processing device 262.

[0049] The substrate support 256 can be a vacuum chuck, an electrostatic chuck, a magnetic chuck, a mechanical chuck (e.g., a four-jaw chuck, a three-jaw chuck, an edge / ring clamp chuck, etc.), or other types of chucks. The substrate support 256 can fix the substrate 264 (e.g., a wafer). The rotary actuator 252 can rotate the substrate support 256 around the first axis 253. The rotary actuator 252 can be controlled by a servo controller and / or a servo motor, and the servo controller and / or the servo motor can enable precise control of the rotational position, speed, and / or acceleration of the rotary actuator, and thus the substrate support 256. The linear actuator 254 can linearly move the substrate support 256 along the second axis 255. The linear actuator 254 can be controlled by a servo controller and / or a servo motor 272, and the servo controller and / or the servo motor 272 can enable precise control of the linear position, speed, and acceleration of the linear actuator 254, and thus the substrate support 256.

[0050] The camera 258 can be disposed on the substrate support 256 and can generate one or more images of the substrate 264 held by the substrate support 256. The camera 258 can be an optical camera, an infrared camera, or other suitable types of cameras. The sensor 260 can also be disposed on the substrate support 256 and can measure at least one target position on the substrate at a time (e.g., can generate reflected light measurement or other measurements of the target position). The camera 258 and the sensor 260 can be fixed at a stationary position on the substrate measurement system 251, and the substrate support 256 can be moved in rθ motion by the rotary actuator 252 and the linear actuator 254.

[0051] In some embodiments, the processing device 262 can determine that the substrate 264 is not centered on the substrate support 256 based on one or more images of the substrate 264 generated by the camera 258. The substrate 264 may not be centered on the substrate support 256 when first placed on the substrate support 256. The robotic blade 270 can place the substrate 264 on a transfer station 268 (e.g., a set of lift pins). The substrate support 256 can be moved in a first direction along a second axis 255 such that the substrate support 256 is disposed at the transfer station 268. The transfer station 268 can be located on a lift mechanism 266 (or can be a set of lift pins), and the lift mechanism 266 can move the transfer station 268 vertically (orthogonal to the second axis 255 and parallel to the first axis 253). While the substrate support 256 is disposed at the transfer station 268, the substrate support 256 can receive the substrate 264. The substrate 264 may not be centered on the substrate support 256. The substrate support 256 can be moved in a second direction along the second axis 255 until the edge of the substrate 264 is detected by the sensor 260 to be at a target position.

[0052] The substrate support can be rotated 360 degrees, and an image can be generated during rotation of the substrate support. One or more of measurements and / or images can be obtained at various different θ values of the chuck, and the detected edge locations can vary. The detected edge change can indicate that the center of the substrate (which can be a circular substrate) is offset. Additionally, the determined change in the detected edge can be used to calculate the amount of the offset.

[0053] In one embodiment, the parameters (r, θ) determine the offset of the substrate with respect to the stage. These parameters enable the motion system to perform forward and inverse transformations that convert the (r, θ) coordinates of the stage to the (r, θ) coordinates of the substrate. The motion system can then calculate the trajectory within the space of the substrate while sending commands to drive the motors attached to the substrate support 256. In one embodiment, the motion system can calculate the trajectory within any space because it executes real-time control software connected to the motion drivers of the linear actuator and the rotary actuator (e.g., via an EtherCAT network). The processing device 262 can calculate the corrected trajectory and transmit the commanded position to the motion driver in real time (e.g., at a rate of 1 kHz).

[0054] In some embodiments, the rotation of the substrate support 256 by the rotary actuator 252 for measuring the target position causes an offset between the field of view of the sensor 260 and the target position on the substrate 264 because the substrate 264 is not centered on the substrate support 256. In this case, the linear actuator 254 can linearly move the substrate support 256 along the second axis to correct the offset. The sensor 260 can then measure the target position on the substrate 264. After the measurements of all the target points on the substrate have been taken, the processing device 262 can determine a uniformity profile across the surface of the substrate 264 based on the measurements.

[0055] In some embodiments, the processing device 262 can determine one or more coordinate transformations between the center of the substrate support 256 (corresponding to the first axis 253 about which the substrate support 256 rotates) and the center of the substrate 264 that is applied during the rotation of the substrate support 256 to correct the offset.

[0056] FIG. 2C is a schematic cross-sectional side view of a substrate measurement subsystem 282 according to an aspect of the present disclosure. The substrate measurement subsystem 282 can be configured to obtain measurements on one or more portions of a substrate, such as substrate 202 of FIG. 2A, before or after processing of the substrate in a processing chamber. In an embodiment, the substrate measurement subsystem 282 can correspond to the substrate measurement system 126 of FIG. 2A. The substrate measurement subsystem 282 can obtain measurements on a portion of the substrate 202 by generating data associated with that portion of the substrate 202. In some embodiments, the substrate measurement subsystem 282 can be configured to generate spectral data, position data, and / or other characteristic data associated with the substrate 202.

[0057] The substrate measurement subsystem 282 can be configured to generate one or more types of data for a substrate, including spectral data, position data, substrate characteristic data, etc. The substrate measurement subsystem 282 can generate data for a substrate in response to a request to obtain one or more measurements on the substrate before or after the substrate is processed in a manufacturing system. The substrate measurement subsystem 282 can include one or more components that facilitate the generation of data for the substrate. For example, the substrate measurement subsystem can include spectral sensing components for sensing one or more spectra from a portion of the substrate to generate spectral data for the substrate. In some embodiments, the spectral sensing components can be replaceable components and can be configurable based on the type of process being executed in the manufacturing system or the target type of measurement to be obtained by the substrate measurement subsystem. For example, one or more components of the spectral sensing components can be replaced in the substrate measurement subsystem to enable the collection of reflected light measurement spectral data, ellipsometry spectral data, hyperspectral imaging data, chemical imaging (e.g., X-ray photoelectron spectroscopy (XPS), energy-dispersive X-ray spectroscopy (EDX), X-ray fluorescence (XRF), etc.) data, etc.

[0058] The substrate measurement subsystem 282 can include a controller 283 configured to execute one or more instructions for generating data associated with a portion of the substrate 202. The substrate measurement subsystem 282 can include a substrate sensing component 284 configured to detect when the substrate 202 is transferred to the substrate measurement subsystem 282. The substrate sensing component 284 can include any component configured to detect when the substrate 202 is transferred to the substrate measurement subsystem 282. For example, the substrate sensing component 284 can include an optical sensing component that transmits an optical beam across an entrance to the substrate measurement subsystem 282. The substrate sensing component 284 can detect that the substrate 202 has been transferred to the substrate measurement subsystem 282 in response to the substrate 202 blocking the optical beam transmitted across the entrance to the substrate measurement subsystem 282 when the substrate 202 is disposed within the substrate measurement subsystem 282. In response to detecting that the substrate 202 has been transferred to the substrate measurement subsystem 282, the substrate sensing component 284 can transmit an indication indicating that the substrate 202 has been transferred to the substrate measurement subsystem 282 to the controller 283.

[0059] In some embodiments, the substrate sensing component 284 can be further configured to detect identification information associated with the substrate 202. In some embodiments, when the substrate 202 is transferred to the substrate measurement subsystem 282, the substrate 202 can be embedded within a substrate carrier (not shown). The substrate carrier can include one or more registration features that enable identification of the substrate 202. For example, the optical sensing component of the substrate sensing component 284 can detect that the substrate 202 embedded within the substrate carrier has interrupted an optical beam transmitted across an entrance to the substrate measurement subsystem 282. The optical sensing component can further detect one or more registration features included on the substrate carrier. In response to detecting the one or more registration features, the optical sensing component can generate an optical signature associated with the one or more registration features. The substrate sensing component 284 can transmit the optical signature generated by the optical sensing component to the controller 283 along with an indication that the substrate is disposed within the substrate measurement subsystem 282. In response to receiving the optical signature from the sensing component 284, the controller 283 can analyze the optical signature to determine the identification information associated with the substrate 202. The identification information associated with the substrate 202 can include an identifier for the substrate 202, an identifier for a process for the substrate 202 (e.g., a batch number or a process execution number), an identifier for a certain type of substrate 202 (e.g., a wafer, etc.).

[0060] The substrate measurement subsystem 282 can include one or more components configured to determine the position and / or orientation of the substrate 202 within the substrate measurement subsystem 282. The position and / or orientation of the substrate 202 can be determined based on the identification of a reference location of the substrate 202. The reference location can be a portion of the substrate 202 that includes an identification feature associated with a unique portion of the substrate 202. For example, the substrate 202 can have a reference tag embedded in the central portion of the substrate 202. In another example, the substrate 202 can have one or more structural features included at the center of the substrate 202 on the surface of the substrate 202. The controller 283 can determine the identification feature associated with the unique portion of the substrate 202 based on the determined identification information for the substrate 202. For example, in response to determining that the substrate 202 is a wafer, the controller 283 can determine one or more identification features generally included in a portion of the wafer.

[0061] The controller 283 can identify a reference location for the substrate 202 using one or more camera components 285 configured to capture image data for the substrate 202. The camera components 285 can generate image data for one or more portions of the substrate 202 and transmit the image data to the controller 283. The controller 283 can analyze the image data to identify the identification feature associated with the reference location for the substrate 202. The controller 283 can further determine the position and / or orientation of the substrate 202 shown in the image data based on the identified identification feature of the substrate 202. The controller 283 can determine the position and / or orientation of the substrate 202 based on the identified identification feature of the substrate 202 and the determined position and / or orientation of the substrate 202 shown in the image data.

[0062] In response to determining the position and / or orientation of substrate 202, controller 283 can generate position data associated with one or more portions of substrate 202. In some embodiments, the position data can include one or more coordinates (e.g., Cartesian coordinates, polar coordinates, etc.), each coordinate being associated with a portion of substrate 202 and each coordinate being determined based on a distance from a reference location on substrate 202. For example, in response to determining the position and / or orientation of substrate 202, controller 283 can generate first position data associated with a portion of substrate 202 that includes the reference location, the first position data including Cartesian coordinates of (0,0). Controller 283 can generate second position data associated with a second portion of substrate 202 relative to the reference location. For example, Cartesian coordinates of (0,1) can be assigned to a portion of substrate 202 that is located approximately 2 nanometers (nm) due east from the reference location. In another example, Cartesian coordinates of (1,0) can be assigned to a portion of substrate 202 that is located 5 nm due north from the reference location.

[0063] Based on the position data determined for substrate 202, controller 283 can determine one or more portions of substrate 202 to measure. In some embodiments, controller 283 can receive one or more operations of a process recipe associated with substrate 202. In such embodiments, controller 283 can further determine one or more portions of substrate 202 to measure based on the one or more operations of the process recipe. For example, controller 283 can receive an indication that an etching process has been performed on substrate 202 if some structural features have been etched onto the surface of substrate 202. As a result, controller 283 can determine one or more structural features to measure and the expected locations of such features at various portions of substrate 202.

[0064] The substrate measurement subsystem 282 can include one or more measurement components for measuring the substrate 202. In some embodiments, the substrate measurement subsystem 282 can include one or more spectral sensing components 287 configured to generate spectral data for one or more portions of the substrate 202. As already discussed, the spectral data can correspond to the intensity (i.e., the strength or amount of energy) of the detected energy wave for each wavelength of the detected wave.

[0065] In one embodiment, the reflected energy waves received by the substrate measurement subsystem 282 can include a plurality of wavelengths. Each reflected energy wave can be associated with a different portion of the substrate 202. In some embodiments, for each reflected energy wave received by the substrate measurement subsystem 282, an intensity can be measured. Each intensity can be measured for each wavelength of the reflected energy wave received by the substrate measurement subsystem 282. The relationship between each intensity and each wavelength can form the basis of the spectral data. In some embodiments, one or more wavelengths can be associated with intensity values outside the expected intensity value range. In such embodiments, intensity values outside the expected intensity value range can indicate the presence of a defect in a portion of the substrate 202.

[0066] The measurement components for measuring the substrate 202 can also include non-spectral sensing components configured to collect and generate non-spectral data. For example, the measurement components can include eddy current sensors or capacitive sensors. Although some embodiments of this description may refer to collecting and using spectral data for the substrate 202, the embodiments of this description can also be applicable to non-spectral data collected for the substrate 202.

[0067] The spectrum sensing component 287 can be configured to detect waves of energy reflected from a portion of the substrate 202 and generate spectral data associated with the detected waves. The spectrum sensing component 287 can include a wave generator 288 and a reflected wave receiver 291. In some embodiments, the wave generator 288 can be an optical wave generator configured to generate a light beam towards a portion of the substrate 202. In such embodiments, the reflected wave receiver 291 can be configured to receive the light beam reflected from that portion of the substrate 202. The wave generator 288 can be configured to generate an energy stream 289 (e.g., a light beam) and transmit the energy stream 289 to a portion of the substrate 202. The reflected energy wave 290 can be reflected from that portion of the substrate 202 and received by the reflected wave receiver 291. FIG. 2C shows a single energy wave reflected from the surface of the substrate 202, but multiple energy waves can be reflected from the surface of the substrate 202 and received by the reflected wave receiver 291.

[0068] In response to the reflected wave receiver 291 receiving the reflected energy wave 290 from that portion of the substrate 202, the spectrum sensing component 287 can measure the wavelength of each wave included in the reflected energy wave 289. The spectrum sensing component 287 can further measure the intensity of each measured wavelength. In response to measuring each wavelength and each wavelength intensity, the spectrum sensing component 287 can generate spectral data for that portion of the substrate 202. The spectrum sensing component 287 can transmit the generated spectral data to the controller 283. In response to receiving the generated spectral data, the controller 283 can generate a mapping between the received spectral data and the position data for the measured portion of the substrate 202.

[0069] The substrate measurement subsystem 282 can be configured to generate a specific type of spectral data based on the type of measurement to be obtained by the substrate measurement subsystem 282. In some embodiments, the spectral sensing component 287 can be a first spectral sensing component configured to generate one type of spectral data. For example, the spectral sensing component 287 can be configured to generate reflected light measurement spectral data, ellipsometry spectral data, hyperspectral imaging data, chemical imaging data, thermal spectral data, or conductive spectral data. In such embodiments, the first spectral sensing component can be removed from the substrate measurement subsystem 282 and replaced with a second spectral sensing component configured to generate a different type of spectral data (e.g., reflected light measurement spectral data, ellipsometry spectral data, hyperspectral imaging data, or chemical imaging data).

[0070] Based on the type of measurement to be obtained for one or more portions of the substrate 202, the controller 283 can determine the type of data (i.e., spectral data, non-spectral data) to be generated for the substrate 202. In some embodiments, the controller 283 can determine one or more types of measurements based on a notification received from the system controller 228 of FIG. 2A. In other or similar embodiments, the controller 283 can determine one or more types of measurements based on instructions for generating measurements for a portion of the substrate 202. In response to determining one or more types of measurements to be obtained, the controller 283 can determine the type of data to be generated for the substrate 202. For example, the controller 283 can determine that spectral data should be generated for the substrate 202 and that a second spectral sensing component is the optimal sensing component for obtaining measurements of the determined type for one or more portions of the substrate 202. In response to determining that the second sensing component is the optimal sensing component, the controller 283 can transmit a notification to the system controller indicating that the first spectral sensing component should be replaced with the second spectral sensing component and that the second spectral sensing component should be used to obtain one or more types of measurements for one or more portions of the substrate 202. The system controller 128 can transmit that notification to a client device connected to the manufacturing system, and the client device can provide that notification to a user (e.g., an operator) of the manufacturing system via a GUI.

[0071] In other or similar embodiments, the spectral sensing component 287 can be configured to generate multiple types of spectral data. In such embodiments, the controller 283 can cause the spectral sensing component 287 to generate a specific type of spectral data for one or more portions of the substrate 202 based on the type of measurement to be acquired, according to the foregoing embodiments. In response to determining the type of measurement to be acquired, the controller 283 can determine that a first type of spectral data should be generated by the spectral sensing component 287. Based on the determination that the first type of spectral data should be generated by the spectral sensing component 287, the controller 283 can cause the spectral sensing component 287 to generate the first type of spectral data for one or more portions of the substrate 202.

[0072] As described above, the controller 283 can determine one or more portions of the substrate 202 for measurement by the substrate measurement subsystem 282. In some embodiments, one or more measurement components, such as the spectral sensing component 287, can be stationary components within the substrate measurement subsystem 282. In such embodiments, the substrate measurement subsystem 282 can include one or more position components 295 configured to modify the position and / or orientation of the substrate 202 relative to the spectral sensing component 287. In some embodiments, the position component 295 can be configured to translate the substrate 202 parallel to the spectral sensing component 287 along a first axis and / or a second axis. In other or similar embodiments, the position component 295 can be configured to rotate the substrate 202 relative to the spectral sensing component 287 about a third axis.

[0073] When the spectral sensing component 287 generates spectral data for one or more portions of the substrate 202, the position component 295 can modify the position and / or orientation of the substrate 202 according to one or more determined portions to be measured with respect to the substrate 202. For example, before the spectral sensing component 287 generates spectral data for the substrate 202, the position component 295 can position the substrate 202 at the Cartesian coordinates (0,0), and the spectral sensing component 287 can generate first spectral data for the substrate 202 at the Cartesian coordinates (0,0). In response to the spectral sensing component 287 generating the first spectral data for the substrate 202 at the Cartesian coordinates (0,0), the positioning component 240 can translate the substrate 202 along the first axis, and thus the spectral sensing component 287 is configured to generate second spectral data for the substrate 202 at the Cartesian coordinates (0,1). In response to the spectral sensing component 287 generating the second spectral data for the substrate 202 at the Cartesian coordinates (0,1), the controller 283 can rotate the substrate 202 along the second axis, and thus the spectral sensing component 287 is configured to generate third spectral data for the substrate 202 at the Cartesian coordinates (1,1). This process can be performed multiple times until spectral data is generated for each determined portion of the substrate 202.

[0074] In some embodiments, the surface of substrate 202 can include a layer 297 of one or more materials. The one or more layers 297 can include an etching material, a photoresist material, a mask material, a deposition material, and the like. In some embodiments, the one or more layers 297 can include an etching material to be etched according to an etching process executed in a processing chamber. In such embodiments, spectral data can be collected for one or more portions of the unetched etching material of layer 297 deposited on substrate 202, according to the embodiments already disclosed. In other or similar embodiments, the one or more layers 297 can include an etching material that has already been etched by an etching process in a processing chamber. In such embodiments, one or more structural features (e.g., lines, pillars, openings, etc.) can be etched into one or more layers 297 of substrate 202. In such embodiments, spectral data can be collected for one or more structural features etched into one or more layers 297 of substrate 202.

[0075] In some embodiments, the substrate measurement subsystem 282 can include one or more additional sensors configured to capture additional data for substrate 202. For example, the substrate measurement subsystem 282 can include additional sensors configured to determine the thickness of substrate 202, the thickness of a film deposited on the surface of substrate 202, and the like. Each sensor can be configured to transmit the captured data to controller 283.

[0076] In response to receiving at least one of spectral data, position data, or characteristic data for substrate 202, controller 283 can transmit the received data to system controller 228 for processing and analysis, according to the embodiments described herein.

[0077] In some embodiments, the substrate measurement subsystem 282 includes one or more image capture devices 299 connected to a controller 283, such as a camera (including, for example, a complementary metal oxide semiconductor (CMOS) sensor or a charge coupled device (CCD) sensor). The image capture device 299 can generate images (such as two-dimensional (2D) color images, infrared (IR) images, near-infrared images, etc.). In an embodiment, these images can be processed by one or more trained machine learning models together with the spectral data generated by the spectral sensing component 287 to make a determination regarding one or more chamber components.

[0078] FIG. 3 shows an exemplary system architecture 300 for predicting or evaluating a substrate placement for a processing chamber according to aspects of the present disclosure. In some embodiments, the system architecture 300 can include or be part of one or more components of the computer architecture 100 and / or the manufacturing system 200. The system architecture 300 can include one or more components of the manufacturing equipment 122 (such as the substrate measurement system 126), the server machine 320, and the server machine 350.

[0079] As described above, the manufacturing equipment 122 can produce products by operating according to a strategy or over a period of time. The manufacturing equipment 122 can include a process chamber 310 configured to perform a substrate process on a substrate according to a substrate process strategy. In some embodiments, the strategy can be a blanket wafer strategy of depositing a film on a test substrate. In some embodiments, the strategy can be a blanket wafer strategy of etching the surface of a test substrate. In some embodiments, the process chamber 310 can be any of the process chambers 214, 218, 218 described with respect to FIG. 2A. The manufacturing equipment 122 can also include a substrate measurement system 126 as described herein.

[0080] The manufacturing machine 122 can be coupled to the server machine 320. The server machine 320 can include a processing device 322 and / or a data store 332. In some embodiments, the processing device 322 can be configured to execute one or more instructions for performing operations on the manufacturing machine 122. For example, the processing device 322 can include or be part of the system controller 228 described with respect to FIG. 2A. In some embodiments, the data store 332 can include or be part of the data store 150 and / or the data store 250.

[0081] The processing device 322 can be configured to receive data from one or more components of the manufacturing machine 122 (i.e., via a network). For example, the processing device 322 can receive surface profile data (e.g., wafer map, thickness profile data, etc.) 336 collected by the substrate measurement system 126 after the substrate has been processed in the process chamber. In another example, the processing device 322 can receive measurement data collected by other measurement devices before and / or after the substrate process on the substrate. The measurement data can include measurement values generated for the substrate by an integrated measurement device. In some embodiments, the processing device 322 can store the received spectral data, film thickness profile data, substrate thickness profile data, and / or the received measurement data in the data store 332.

[0082] The processing device 352 can include a substrate placement engine 330. The substrate placement engine 330 in the processing device 322 can be configured to determine a recommended placement (e.g., a recommended location) for a substrate to be processed within the process chamber 310. The process chamber 310 can be a processing chamber that has processed a measured substrate. The substrate placement engine 330 can determine one or more substrate placement metrics for one or more substrates processed within the process chamber 310 that has processed the substrate from the substrate surface profile data 336. In some embodiments, the substrate placement metric can include a series of values (e.g., a vector, a matrix, etc.) that indicate a correlation of a particular combination, correlation, pattern, and / or relationship of data present in the sensor data. For example, the substrate placement metric can include a feature vector that includes binary values indicating the presence or absence of a particular feature in the data.

[0083] The substrate placement metric can be compared to a known pattern and / or combination of substrate placement metrics (e.g., a target substrate placement metric). The target substrate placement metric can be associated with an ideal substrate placement for optimal processing of the substrate. In response to determining that the substrate placement metric for one or more substrate placement positions meets one or more substrate placement criteria (e.g., the conditions for the processed substrate meet a threshold specification such as a threshold slope specification), the substrate placement engine 330 can determine a recommended placement for the substrate to be processed and / or can provide an alert to the user. In some embodiments, the substrate placement criteria can include a specified combination of values indicated by the substrate placement metric. After the recommended substrate placement is determined, the substrate placement engine 330 can output instructions for use when a robotic arm places the substrate on the substrate support according to the coordinates of the recommended substrate placement using a particular set of settings (e.g., an x setting and / or a y setting).

[0084] As shown in FIG. 3, in some embodiments, the processing device 322 can include a training set generator 324 and / or a training engine 326. In some embodiments, the training set generator 324 can correspond to the training set generator 172, as described with respect to FIG. 1, and / or the training engine 326 can correspond to the training engine 182. The training set generator 324 can be configured to generate a training set 340 for training the machine learning model 334 or a set of machine learning models 334. For example, the training set generator 324 can generate training inputs based on past substrate surface profile data 336. The substrate surface profile data 336 (e.g., thickness profile map) can be associated with the etching rate and / or tilt across the surface of one or more substrates processed in the processing chamber. In some embodiments, the training set generator 324 can retrieve past substrate surface profile data 336 (e.g., substrate thickness profile data) from the data store 332 and generate training inputs. The training set generator 324 can generate a target output indicating an estimated substrate placement value (e.g., substrate placement metric) for the training inputs based on the past substrate surface profile data 336. The training set generator 324 can include the generated training inputs and the generated target output in the training set 340. The training set 340 can further include an indicator of the substrate placement (e.g., on a substrate support such as an electrostatic chuck relative to the inner diameter of the process kit ring) for each past substrate thickness profile. Further details regarding generating the training set 340 are provided with respect to FIG. 5.

[0085] The training engine 326 can be configured to train, authenticate, and / or test its machine learning model 334 or multiple sets of machine learning models 334. The training engine 326 can provide a training set 340 to train the machine learning model 334 and store the trained machine learning model 334 in the data store 332. In some embodiments, the training engine 326 can use an authentication set 342 to authenticate the trained machine learning model 334. The authentication set 342 can include surface profile data 336 and associated chamber component condition metrics. The training set generator 324 and / or the training engine 326 can generate the authentication set 342 based on past surface profile data 336. In some embodiments, the authentication set 342 can include past surface profile data 336 that is different from the past surface profile data 336 included in the training set 340.

[0086] The training engine 326 can provide past surface profile data 336 as an input to the trained machine learning model 334 and extract one or more substrate placement metrics for processing a substrate in the processing chamber from one or more outputs of the trained model 334. The input can further include the age of one or more components of the processing chamber and / or one or more images of the substrate used to generate the past surface profile data 236. The training engine 326 can assign a performance score to the trained model 334 based on the accuracy of the substrate placement metrics. The training engine 326 can select the trained model 334 to be used to evaluate the substrate placement for processing a substrate in the process chamber based on the surface profile data for the substrate processed by the process chamber.

[0087] As already discussed, the training set generator 324 and / or the training engine 326 can, in some embodiments, be components of the processing device 322 in the server 320. In additional or alternative embodiments, the training set generator 324 and / or the training engine 326 can also be components of the processing device 352 in the server 350. The server 350 can include, or be part of, a computing system separate from the manufacturing system 200. As described above, the server 320 can include, or be part of, the system controller 228 described with respect to FIG. 2A in some embodiments. In such embodiments, the server 350 can include, or be part of, a computing system that is coupled (i.e., via a network) to the system controller 228 but separate from the system controller 228. For example, a user of the manufacturing system 200 can be provided access to data stored in one or more portions of the data store 332, or to one or more processes executed by the processing device 322. However, a user of the manufacturing system 200 may not be provided access to any data stored in one or more portions of the data store 354, or to any processes executed by the processing device 352.

[0088] Similar to processing device 322, processing device 352 can be configured to execute a training set generator 324 and / or a training engine 326. In some embodiments, server 350 can be coupled to manufacturing equipment 122 and / or in-line metrology equipment 130 via a network. Accordingly, processing device 352 can obtain surface profile data 336 and substrate placement metrics corresponding to the surface profile data 336 to be used by training set generator 324 and / or training engine 326 to generate training set 340 and authentication set 342, according to the embodiments described with respect to processing device 322. In other or similar embodiments, server 350 is not coupled to manufacturing equipment 122 and / or external metrology equipment 130. Accordingly, processing device 352 can obtain surface profile data 336 from processing device 322.

[0089] The training set generator 324 in processing device 352 can generate a training set 340 according to the foregoing embodiments. The training engine 326 in processing device 352 can train and / or authenticate machine learning model 334 according to the foregoing embodiments. In some embodiments, server 350 can be coupled to other manufacturing equipment and / or other server machines different from manufacturing equipment 122 and / or server machine 320. Processing device 352 can obtain surface profile data 336 from other manufacturing equipment and / or server machines according to the embodiments described herein. In some embodiments, training set 340 and / or authentication set 342 can be generated based on surface profile data 336 obtained for substrates processed in process chamber 310, as well as other surface profile data obtained for other substrates processed in process chambers in other manufacturing systems.

[0090] In response to the training engine 326 selecting the trained model 334 to be used, the processing device 352 can transmit the trained model 334 to the processing device 322. As described above, the substrate placement engine 330 can use the trained model 334 to provide substrate placement recommendations.

[0091] FIG. 4 shows a model training workflow 405 and a model application workflow 417 for substrate placement determination according to an embodiment. The model training workflow 405 and the model application workflow 417 can be executed by processing logic executed by a processor of a computing device. One or more of these workflows 405, 417 can be implemented, for example, by one or more machine learning models implemented on a processing device, and / or other software and / or firmware executed on the processing device.

[0092] The model training workflow 405 is for training one or more machine learning models (e.g., deep learning models) to determine an optimal substrate placement for processing a substrate within a process chamber. The model application workflow 417 is for applying one or more trained machine learning models to perform a substrate placement evaluation. Each of the profile maps 412 can be associated with a thickness profile or other surface profile of the processed substrate. For example, each of the profile maps 412 can reflect the corresponding thickness of the substrate after a processing operation (e.g., an etching operation, etc.) performed on the substrate.

[0093] Various machine learning outputs are described herein. A specific number and arrangement of machine learning models are described and illustrated. However, it should be understood that the number and type of machine learning models used, as well as the arrangement of such machine learning models, can be modified to achieve the same or similar final results. Accordingly, the arrangements of the machine learning models described and illustrated are merely examples and should not be construed as limiting.

[0094] In some embodiments, one or more machine learning models are trained to perform one or more substrate placement estimation tasks. Each task can be performed by a separate machine learning model. Alternatively, a single machine learning model can also perform each or a part of the tasks. For example, a first machine learning model can be trained to determine a substrate placement (e.g., a location on a substrate support for substrate processing), and a second machine learning model can be trained to determine a substrate handover offset (e.g., a substrate handling robot handover offset). Additionally or alternatively, different machine learning models can be trained to perform different combinations of tasks. In one example, one or several machine learning models can be trained, and the trained machine learning (ML) model is a single shared neural network having a plurality of shared layers and a plurality of separate higher-level output layers, and each of the output layers outputs different predictions, classifications, identifications, etc. For example, a first higher-level output layer can determine a substrate placement for a first type of chamber component (e.g., an electrostatic chuck), and a second higher-level output layer can determine a substrate placement for a second type of chamber component (e.g., a process kit ring).

[0095] One type of machine learning model that can be used to perform some or all of the above tasks is an artificial neural network such as a deep neural network. An artificial neural network generally includes a feature representation component having a classifier or regression layer that maps features to a target output space. A convolutional neural network (CNN), for example, hosts multiple layers of convolutional filters. Pooling is performed to handle non-linearity in the lower layers, and usually, a multi-layer perceptron is attached thereon to map the upper layer features extracted by the convolutional layer for determination (e.g., classification output). Deep learning is a type of machine learning algorithm that uses a cascade of multiple layers of non-linear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. A deep neural network can learn in a supervised (e.g., classification) and / or unsupervised (e.g., pattern analysis) manner. A deep neural network includes multiple layers of hierarchy, and different layers learn different levels of representation corresponding to different levels of abstraction. In deep learning, each level learns to transform its input data into a slightly more abstract and complex representation. In particular, the deep learning process can learn which features optimally fit naturally at which level. The "deep" in "deep learning" refers to the number of layers through which data is transformed. More precisely, a deep learning system has a substantial contribution assignment path (CAP) depth. The CAP is a chain of input-to-output transformations. The CAP describes the potentially causal connections between the input and the output. In the case of a forward neural network, the depth of the CAP may be the depth of the network and can be taken as the number obtained by adding 1 to the number of hidden layers. In the case of a recurrent neural network where a signal can propagate through one layer more than once, the CAP depth can potentially be unlimited.

[0096] The training of a neural network can be realized in a supervised learning manner, which involves feeding a training data set consisting of labeled inputs through the network, observing its output, defining an error (by measuring the difference between the output and the label value), and using techniques such as deep gradient descent and backpropagation to adjust the quality of the network across all its layers and nodes so that the error is minimized. In many applications, by repeating this process over many labeled inputs in the training data set, a network can be obtained that can produce the correct output when presented with inputs different from those present in the training data set.

[0097] In the case of the model training workflow 405, a training data set containing hundreds, thousands, tens of thousands, hundreds of thousands, or more profile maps 412 of one substrate should be used to form the training data set. The data can include, for example, uniformity profiles determined using a given number of measurements, each associated with a particular target position. This data can be processed to generate one or more training data sets 436 for the training of one or more machine learning models. The training data items in the training data set 436 can include the profile map 412, the substrate placement used to process the substrate measured to generate the profile map, and / or one or more images of those substrates.

[0098] To implement training, the processing logic inputs a training data set 436 into one or more untrained machine learning models. Before inputting the first input into the machine learning model, the machine learning model can be initialized. The processing logic trains the untrained machine learning model based on the training data set to generate one or more trained machine learning models that perform the various operations described above. Training can be performed by inputting into the machine learning one piece of input data at a time, such as one or more profile maps 412 (e.g., thickness profile map, spectral profile map, roughness profile map, particle number profile map, optical constant profile map, etc.), an image of a component, and / or usage year information.

[0099] The machine learning model processes this input to generate an output. An artificial neural network includes an input layer consisting of values within a data point. The next layer is called a hidden layer, and each node in the hidden layer receives one or more of the input values. Each node includes parameters (e.g., mass) to apply to the input values. Thus, each node essentially inputs the input values into a multivariate function (e.g., a non-linear mathematical transformation) to yield an output value. The next layer can be another hidden layer or an output layer. In either case, the nodes in the next layer receive the output values from the nodes in the previous layer, and each node applies a mass to those values and then generates its own output value. This can be done for each layer. The last layer is the output layer, and there is one node for each class, prediction, and / or output that the machine learning model can yield.

[0100] Accordingly, the output can include one or more predictions or inferences (e.g., an estimation of the substrate placement within a process chamber for substrate processing in a process chamber where a measured substrate was processed). The processing logic can compare the output estimated substrate placement to past substrate placements. The processing logic determines an error (i.e., a classification error) based on a difference between the estimated substrate placement and a target substrate placement. The processing logic adjusts the mass of one or more nodes in the machine learning model based on the error. An error term or delta can be determined for each node within the artificial neural network. Based on this error, the artificial neural network adjusts one or more of its parameters (the mass for one or more inputs to a node) for one or more of its nodes. The parameters can be updated by backpropagation, such that the nodes in the highest layer are updated first, followed by the nodes in the next layer, and so on. The artificial neural network includes multiple layers of "neurons", each layer receiving input values from neurons in the previous layer. The parameters for each neuron include the mass associated with the values received from each of the neurons in the previous layer. Accordingly, adjusting the parameters can include adjusting the mass assigned to each of the inputs to one or more neurons in one or more layers within the artificial neural network.

[0101] After the model parameters are optimized, model authentication can be performed to determine whether the model has been improved and to determine the current accuracy of the deep learning model. After one or more trainings, the processing logic can determine whether the stopping criterion is met. The stopping criterion can be a target accuracy level, a target number of processed images from the training dataset, a target amount of change to the parameters with respect to one or more previous data points, combinations thereof, and / or other criteria. In one embodiment, the stopping criterion is met when at least a minimum number of data points have been processed and at least a threshold accuracy has been achieved. The threshold accuracy can be, for example, 70%, 40%, or 90% accuracy. In one embodiment, the stopping criterion is met when the accuracy of the machine learning model stops improving. If the stopping criterion is not met, further training is performed. If the stopping criterion is met, the training can be completed. After the machine learning model has been trained, the model can be tested using the reserved portion of the training dataset. After one or more trained machine learning models 438 are generated, they can be stored in the model storage 445 and added to the substrate placement engine 330.

[0102] According to one embodiment, in the case of the model application workflow 417, the input data 462 can be input to one or more substrate placement determiners 467, each of which can include a trained neural network or other model. Additionally or alternatively, one or more substrate placement determiners 467 can apply an image processing algorithm to determine chamber component conditions. The input data can include a profile map (e.g., of a polymer layer on a substrate measured using an integrated reflectance measurement device or a substrate measurement system). The input data may further include one or more images of the substrate. Based on the input data 462, the substrate placement determiner 467 can output one or more estimated substrate placements 469. The estimated substrate placement 469 can include the placement of the substrate relative to a substrate support structure for processing the substrate within the process chamber (which may be, for example, as an offset from the center of the substrate support such as an electrostatic chuck). In some examples, a coordinate system based on the substrate support (e.g., based on the center point of the substrate support) can be used to correlate the estimated substrate placement (e.g., position) relative to the substrate support.

[0103] Based on the substrate placement 469, the measure determiner 472 can determine one or more measures 470 to execute. In one embodiment, the measure determiner 472 compares the substrate placement estimation with one or more substrate placement thresholds. If one or more of the substrate placement estimations meet or exceed the substrate placement threshold, the measure determiner 472 can determine that it is recommended to update the substrate placement for future substrate placement and can output a recommendation or notification for updating the substrate placement parameters. In some embodiments, the measure determiner 472 automatically updates the substrate placement metric based on the substrate placement 469 that meets one or more criteria. In some examples, the substrate placement 469 can include an estimated position where the substrate is placed with respect to a substrate support (e.g., an electrostatic chuck) for processing and / or with respect to a component of the substrate support (e.g., a process kit ring). The estimated position can be an optimized position for the substrate to minimize the tilt within the processed substrate, particularly near the edge of the substrate. The substrate placement 469 can include the coordinate position of the center point of the substrate support with respect to the center point of the substrate. In some examples, the substrate placement 469 can reflect the offset between the center of the substrate and the center of the substrate support. In some embodiments, the offset can be used to determine one or more offsets (e.g., an updated position for the robot to place and / or "transfer" the substrate, etc.) for the robot to handle the substrate.

[0104] FIG. 5 is a flowchart of a method 500 for generating a training dataset for training a machine learning model to perform substrate placement evaluation according to an aspect of the present disclosure. The method 500 can be executed by processing logic that includes hardware (circuits, dedicated logic, etc.), software (such as that executed on a general-purpose computer system or a dedicated machine), firmware, or some combination thereof. In one embodiment, the method 500 can be executed by a computer system such as the computer system architecture 100 of FIG. 1. In other or similar embodiments, one or more operations of the method 500 can be executed by one or more other machines not shown. In some aspects, one or more operations of the method 500 can be executed by the training set generator 324 of the server machine 320 or the server machine 350 described with respect to FIG. 3.

[0105] At block 510, the processing logic initializes the training set T to an empty set (e.g., {}). At block 512, the processing logic obtains substrate surface data associated with a substrate processed in a process chamber of a manufacturing system (e.g., reflected light measurement data of the surface of a film on a substrate such as a film thickness profile map or a wafer map).

[0106] At block 514, the processing logic obtains substrate placement information for a substrate processed by the process chamber. As described above, the substrate placement information can include the coordinate positions of the substrate with respect to the substrate support and / or with respect to components of the substrate support.

[0107] At block 516, the processing logic generates a training input based on the sensor data obtained for the substrate at block 512. In some embodiments, the training input can include a normalized set of sensor data (e.g., including surface reflectometer data described herein).

[0108] At block 518, the processing logic can generate a target output based on the substrate placement information obtained at block 514. The target output can correspond to a substrate placement metric of the substrate processed in the process chamber (data indicating the placement of one or more substrates processed in the process chamber).

[0109] At block 520, the processing logic generates an input / output mapping. The input / output mapping refers to training inputs that include or are based on data for the substrate, and target outputs for those training inputs, where the target outputs identify substrate placements and the training inputs are associated with (or mapped to) the target outputs. At block 522, the processing logic adds the input / output mapping to the training set T.

[0110] At block 524, the processing logic determines whether the training set T contains a sufficient amount of training data to train a machine learning model. In some embodiments, it can be determined that the training set T is sufficient based simply on the number of input / output mappings in the training set, whereas in some other embodiments, it should be noted that in addition to or instead of the number of input / output mappings, the training set T can be determined to be sufficient based on one or more other criteria (such as the degree of diversity of the training examples, etc.). In response to determining that the training set T contains a sufficient amount of training data to train a machine learning model, the processing logic provides the training set T for training the machine learning model. In response to determining that the training set does not contain a sufficient amount of training data to train a machine learning model, method 500 returns to block 512.

[0111] At block 526, the processing logic provides a training set T for training a machine learning model. In some embodiments, the training set T is provided to the training engine 326 of server machine 320 and / or server machine 350 for performing the training. In the case of a neural network, for example, the input values of a given input / output mapping (e.g., spectral data and / or chamber data for a previous substrate) are input into the neural network, and the output values of the input / output mapping are stored at the output nodes of the neural network. Then, according to a learning algorithm (e.g., backpropagation, etc.), the connection masses within the neural network are adjusted, and the procedure is repeated for other input / output mappings within the training set T. After block 526, the machine learning model 190 can be used to provide a substrate placement (e.g., a substrate placement metric) for a substrate processed within the process chamber.

[0112] FIG. 6 is a flowchart illustrating one embodiment of a method 600 for training a machine learning model to estimate a substrate placement for processing a substrate within a process chamber. The method 600 can be executed by processing logic that includes hardware (e.g., circuitry, dedicated logic, etc.), software (e.g., that executed on a general-purpose computer system or a dedicated machine), firmware, or some combination thereof. In one embodiment, the method 600 can be executed by a computer system such as the computer system architecture 100 of FIG. 1. In other or similar embodiments, one or more operations of the method 600 can be executed by one or more other machines not shown. In some aspects, one or more operations of the method 600 can be executed by the training engine 326 for the server machine 320 or the server machine 350 described with respect to FIG. 3.

[0113] In block 602 of method 600, the processing logic collects a training data set that can include data from multiple substrate profile maps (e.g., a thickness profile map indicating the thickness of a polymer film at multiple locations on a substrate, a substrate surface profile map, a substrate thickness profile map, etc.). Each data item in the training data set can include one or more labels. The data items in the training data set can include input level (e.g., image level) labels indicating the presence or absence of one or more substrate features associated with the substrate placement. For example, some data items can include a label for the slope present in the processed substrate. In some embodiments, each data item includes a substrate map, which can be an image of the substrate (e.g., a heat map of the substrate). The color in the heat map can indicate the substrate thickness and / or other parameter values (e.g., slope, etc.). Alternatively, actual thickness values can be used for each of many coordinates on the surface of the substrate (e.g., of the substrate).

[0114] In block 604, a data item from the training data set is input into an untrained machine learning model. In block 606, the machine learning model is trained to generate a trained machine learning model that classifies or estimates one or more substrate placements for processing a substrate within a process chamber based on the training data set. The machine learning model can also be trained to output one or more other types of predictions, coordinate level classifications, decisions, etc.

[0115] In one embodiment, at block 610, an input of a training data item is input into a machine learning model. This input can include data from a substrate profile map (e.g., a substrate surface profile map) indicating one or more surface characteristics (e.g., thickness, optical constants, particle count, roughness, material properties, etc.) across the substrate. The data can be input as an image or a feature vector in the embodiment. At block 612, the machine learning model processes the input to generate an output. This output can include one or more substrate placements (e.g., substrate placement values, etc.). The substrate placement can be a recommended partial placement for the placement of a future substrate on a substrate support. This output can, additionally or alternatively, include one or more substrate handover offsets for a robotic arm. For example, the handover offset can correlate the initial robotic handover orientation to an updated robotic handover orientation to match the predicted substrate placement for substrate processing.

[0116] At block 614, the processing logic compares the output probability and / or value of the substrate placement metric to the known optimal substrate placement associated with the input. At block 616, the processing logic determines an error based on the difference between the output and the known placement. At block 618, the processing logic adjusts the mass of one or more nodes in the machine learning model based on this error.

[0117] At block 620, the processing logic determines whether a stop criterion is met. If the stop criterion is not met, the method returns to block 610 and another training data item is input into the machine learning model. If the stop criterion is met, the method proceeds to block 625 and the training of the machine learning model is completed.

[0118] In one embodiment, one or more ML models are trained to be applied across a plurality of process chambers, which may be of the same type or model of process chamber. The trained ML model can then be further adjusted for use with a particular instance of a process chamber. The further adjustment can be performed by using additional training data items including a surface profile map of a substrate processed by the process chamber. Such adjustment can account for chamber mismatches between the chamber and / or some process chambers' unique hardware process kits. Additionally, in some embodiments, further training is performed to adjust the ML model for a process chamber after maintenance in the process chamber and / or one or more changes to the hardware of the process chamber.

[0119] FIG. 7 is a flowchart of a method 700 for determining a recommended substrate placement, according to aspects of the present disclosure. Method 700 can be executed by processing logic including hardware (circuits, dedicated logic, etc.), software (such as that executed on a general-purpose computer system or a dedicated machine), firmware, or some combination thereof. In one embodiment, method 700 can be executed by a computer system such as the computer system architecture 100 of FIG. 1. In other or similar embodiments, one or more operations of method 700 can be executed by one or more other machines not shown. In some aspects, one or more operations of method 700 can be executed by the substrate placement engine 330 of the server machine 320 described with respect to FIG. 3.

[0120] In block 706, the processing logic (e.g., of a processing device) determines the center of a substrate support (e.g., an electrostatic chuck) in a process chamber of a substrate processing system (also referred to as a manufacturing system). In some embodiments, the center of the substrate support is determined from data collected by a multi-functional wafer. For example, a multi-functional wafer (e.g., a camera wafer) can collect an image of the electrostatic chuck within the process chamber. The processing device can process these images to determine the center of the electrostatic chuck. The center of the substrate support can correspond to a reference point (e.g., the (0,0) point) of the substrate support.

[0121] In block 708, the substrate is aligned with the center of the substrate support. In some embodiments, the processing logic causes a robot arm (e.g., of a substrate handling robot) to place the substrate on the substrate support with the center of the substrate aligned with the center of the substrate support. In some embodiments, the substrate is aligned to the center on the substrate support to obtain a baseline measurement for the placement of the substrate. In some embodiments, the substrate is a proxy substrate (e.g., a test substrate, etc.).

[0122] In block 710, the process chamber processes the substrate. For example, the process chamber can perform an etching process to partially remove a film on the surface of the substrate or a film deposition process to deposit a film on the substrate. In some embodiments, the film is a polymer. In other embodiments, the film is a ceramic (e.g., a metal oxide). The processing of the substrate can be performed according to a recipe (e.g., an etching process recipe, a deposition process recipe, etc.). During processing, the substrate can be supported by a substrate support (e.g., an electrostatic chuck) in the process chamber. The substrate can be placed in an initial position within the process chamber before processing (e.g., in block 708) and can remain in the initial position during processing. After processing, in some embodiments, the substrate includes a surface profile (e.g., a thickness profile, etc.).

[0123] In block 712, one or more robots transfer a substrate from a process chamber to a substrate measurement system. If the substrate measurement system is connected to or included within the transfer chamber, the transfer chamber robot can remove the substrate from the process chamber and insert the substrate into the substrate measurement system. If the substrate measurement system is connected to or included within the factory interface, the transfer chamber robot can remove the substrate from the process chamber and place the substrate into the load lock. Then the factory interface robot can remove the substrate from the load lock and insert the substrate into the substrate measurement system. The substrate measurement system can be any of the aforementioned substrate measurement systems, such as an integrated reflected light measurement (IR) device.

[0124] In block 714, the substrate measurement system generates measurements at many locations on the surface of the substrate. Each location can have a unique set of coordinates.

[0125] At block 716, the substrate measurement system and / or computing device can generate a profile map of the surface profile of the substrate (e.g., a substrate surface profile map) based on measurements of the substrate measurement system. The profile map can be or include an image, and each pixel in the image corresponds to coordinates on the substrate. Each pixel can have an intensity value corresponding to a measurement value (e.g., a thickness value) at the coordinates of the substrate associated with the pixel. In some embodiments, the profile map shows a thickness profile, and the thickness profile shows an etching rate profile. For example, the profile map can reflect the thickness profile of a substrate that has undergone an etching process over a predetermined amount of time. In some embodiments, the profile map shows substrate surface defects such as inclinations. In some embodiments, the inclination correlates with the etching rate. In some embodiments, the profile can be or include a feature vector, and each entry in the feature vector is associated with coordinates of the substrate, and each entry can have a value representing a value of the surface profile at the coordinates of the substrate. In some embodiments, the processing logic (e.g., of the measurement system and / or computing device) can determine an etching rate profile map corresponding to the etching rate near the edge of the substrate.

[0126] At block 718, the computing device processes data from profile maps (such as thickness profile maps, particle maps, optical constant maps, roughness maps, etching rate profile maps, etc.) using a model. In some embodiments, the computing device processes data from profile maps using one or more trained machine learning models. In some embodiments, the trained machine learning model is trained using data collected from a plurality of substrates processed according to a recipe. For example, a set of substrates is processed at various placements (such as positions) on a substrate support according to a recipe. Profile maps of the processed substrates can be generated. The profile maps and corresponding substrate placements can be input as training data for training the machine learning model.

[0127] In some embodiments, the model is a physics-based model or a statistical model. In some embodiments, the model outputs an estimated substrate placement value (such as an estimated substrate placement metric) for the placement of the substrate relative to one or more components of the substrate support. In some examples, the model outputs a substrate placement metric (such as the coordinate position of the substrate on the substrate support) corresponding to the placement relative to the substrate support (such as an electrostatic chuck) and / or one or more components of the substrate support (such as a process kit ring). In some embodiments, the output of the model is based on the etching rate profile map determined at block 716. In some embodiments, the output of the model indicates that the substrate was not placed in an optimal position for processing. In one embodiment, instead of or in addition to using a trained ML model, one or more computer vision algorithms are used to process the profile map.

[0128] At block 720, the processing logic (e.g., of a computing device) determines a recommended placement of a substrate on a substrate support based on an estimated placement value (e.g., the output from the model at block 718). In some examples, the computing device can use the estimated substrate placement value to determine a location on the substrate support for placement of the substrate. Specifically, the computing device can determine a coordinate position based on the value (or values) output from the model at block 718. In some embodiments, the computing device can determine a gap that exists between an edge of the substrate and the inner diameter of the process kit ring. In some embodiments, the gap is not uniform around the substrate. For example, the gap can be larger on one side of the substrate than on the opposite side of the substrate. Thus, the gap can be correlated to the placement of the substrate (e.g., on an electrostatic chuck, within the inner diameter of the process kit ring, etc.). The processing logic can then place another substrate into the process chamber (e.g., via a substrate handling robot) according to the recommended placement, as described later herein.

[0129] FIG. 8 is a flow diagram of a method 800 for comparing a first estimated substrate placement and a second estimated substrate placement, according to an aspect of the present disclosure. In some embodiments, method 800 is executed in conjunction with method 700 described above herein. For example, method 700 can correspond to processing a first substrate, and method 800 can correspond to processing a second substrate and comparing the results of the first substrate and the results of the second substrate. Method 800 can be executed by processing logic that includes hardware (circuits, dedicated logic, etc.), software (such as that executed on a general-purpose computer system or a dedicated machine), firmware, or some combination thereof. In one embodiment, method 800 can be executed by a computer system such as the computer system architecture 100 of FIG. 1. In other or similar embodiments, one or more operations of method 800 can be executed by one or more other machines not shown. In some aspects, one or more operations of method 800 can be executed by the substrate placement engine 330 of the server machine 320 described with respect to FIG. 3.

[0130] At block 808, a substrate (e.g., a second substrate) is placed within the process chamber according to a recommended placement (e.g., as determined at block 720 of method 700). In some embodiments, the processing logic causes a robot to place the substrate on a substrate support (e.g., an electrostatic chuck) within the process chamber. The robot can place the substrate at a position such that the center of the substrate is offset from the center of the substrate support according to the recommended placement. For example, the recommended placement can specify that the center of the substrate is offset by a specified amount in a specified direction from the center of the electrostatic chuck. The amount and direction of the offset can be the difference between a first robot handover orientation and a second robot handover orientation. In some examples, the first robot handover orientation is a baseline (e.g., default, etc.) orientation, while the second robot handover orientation is an orientation updated based on the offset. The robot can place the substrate on the electrostatic chuck by shifting it by a specified offset amount in the offset direction from the center of the electrostatic chuck.

[0131] At block 810, the substrate is processed within the process chamber according to a strategy (e.g., the strategy of block 710 of method 700). The strategy can be an etching process strategy and / or a deposition process strategy. Similar to the substrate processed at block 710 of method 700, the substrate includes a post - processing surface profile. The surface profile can be a thickness profile.

[0132] At block 812, the substrate is transferred (e.g., similar to block 712 of method 700) from the process chamber to a substrate measurement system (e.g., by one or more transfer robots).

[0133] At block 814, the substrate measurement system measures the surface of the substrate (e.g., similar to block 714 of method 700).

[0134] At block 816, the substrate measurement system and / or computing device can generate a profile map of the surface profile of the substrate based on the measurements of the substrate measurement system (e.g., similar to block 716 of method 700). In some embodiments, the profile can be or can include an image. The profile map can indicate an etching rate profile.

[0135] At block 818, the computing device uses a model (e.g., a trained machine learning model, a physics-based model, a statistical model, etc.) to process data from the profile map (e.g., a thickness profile map, a particle map, an optical constant map, a roughness map, etc.). In some embodiments, the model outputs an estimated substrate placement value (e.g., an estimated substrate placement metric, etc.).

[0136] At block 820, the processing logic (e.g., of the computing device) compares the estimated substrate placement value output from the model at block 818 with another estimated substrate placement value (e.g., the estimated substrate placement value of block 718 of method 700). The processing logic can determine whether the recommended placement should be updated based on the comparison. For example, in response to the estimated substrate placement values being the same (e.g., substantially the same, within a threshold difference of each other, etc.), the processing logic can determine that the recommended placement is sufficient. In response to the estimated substrate placement values being different (e.g., outside the threshold difference of each other, etc.), the processing logic can determine that the recommended placement should be updated.

[0137] At block 822, the processing logic updates the recommended placement based on the comparison in block 820.

[0138] FIG. 9 is a profile map 900 of a processed substrate according to an aspect of the present disclosure. The profile map 900 is a heat map showing the temperature of different locations on the substrate being processed within the process chamber. The temperature can be based on the thickness at different locations of the film deposited or etched during processing. A key 902 is provided to show how to interpret the profile map 900. As shown, the hot spot 905 is not uniform around the edge of the substrate. In some embodiments, the methods described herein can provide a substrate without hot spots (e.g., substantially no hot spots, substantially uniform temperature, etc.). A non-uniform hot spot can indicate an increase in the etching rate, which correlates with an increase in the substrate tilt. The substrate may be too close to the process kit ring (e.g., of the substrate support within the process chamber) on the side close to the hot spot 905 during processing. For example, the gap between the edge of the substrate and the inner diameter of the process kit ring may be too small or too large near the hot spot 905. The non-uniform hot spot 905 around the edge of the substrate can indicate that there is excessive tilt within the features of the processed substrate near the edge of the substrate. Thus, according to some embodiments described herein, the placement of the substrate for processing should be changed.

[0139] FIGS. 10A - 10B are flowcharts of methods for determining an optimal substrate placement according to aspects of the present disclosure. FIG. 10A shows a method 1000A for determining an optimal substrate placement according to some embodiments. FIG. 10B shows a method 1000B for determining an optimal substrate placement according to some embodiments. In some embodiments, the methods 1000A and / or 1000B can be methods for executing a full angle adaptation (AAF) algorithm that recommends wafer placement adjustment. In some embodiments, the methods 1000A and / or 1000B are for optimizing the uniformity of the etching profile, particularly near the outermost edges of the substrate.

[0140] Referring to FIG. 10A, a design of experiments (DOE) is executed in block 1002. In some embodiments, a plurality of substrates (e.g., test substrates) are processed (e.g., etched) at various locations on a substrate support within a process chamber. In some embodiments, a first substrate is disposed at a first location (e.g., a first position) on the substrate support. The first substrate can be processed, and the processed first substrate can have a first surface profile. In some embodiments, the first surface profile is measured using the substrate measurement system described above herein. In some embodiments, a second substrate is disposed at a second location on a substrate support different from the first location. The second substrate is then processed, and the surface profile of the processed second substrate is measured. A third substrate can be processed at a third location, and then the surface profile of the processed third substrate can be measured.

[0141] Referring to FIG. 11A, an exemplary plot diagram 1100A of the substrate arrangement DOE is shown. Referring to FIG. 13A, an exemplary plot diagram 1300A showing the substrate arrangement in the DOE is shown. In some embodiments, the plot diagram 1100A can correspond to the plot diagram 1300A. In some embodiments, in order to perform the DOE, substrates can be arranged at various locations on the substrate support. Referring to FIG. 11A again, in some embodiments, substrates are arranged and processed at each of the arrangement locations 1102 to 1118. In some embodiments, the location 1118 can correspond to the center of the substrate support. In some embodiments, the first substrate can be arranged and processed at the first location 1102, the second substrate can be arranged and processed at the second location 1104, the third substrate can be arranged and processed at the third location 1106, and so on. Although FIG. 11A shows nine possible arrangement locations for processing the substrate, the DOE can also be performed with less than nine processed substrates located at different arrangement locations. In some embodiments, two or fewer arrangement locations can be located on the same line within the two-dimensional space. In some embodiments, at least one arrangement location of the DOE is located away from the straight line formed between the other two arrangement locations. In some embodiments, the DOE can be performed with ten or more processed substrates located at different arrangement locations. By including a larger number of processed substrates at various arrangement locations, the accuracy of the DOE can be increased. When the arrangement locations of the DOE cover more azimuth angles, increased accuracy can be obtained. For example, the arrangement locations shown in FIG. 13A form an "X" - shaped pattern. By adding additional arrangement locations to the DOE that form another "X" - shaped pattern at different angles (e.g., a shallower or deeper angle) between the legs of the "X", the prediction can be made more accurate. In some embodiments, the DOE can be performed with only three processed substrates located at three different arrangement locations.

[0142] Referring back to FIG. 10A, data processing is performed at block 1004. In some embodiments, the etching rate at locations near each edge of the substrate processed by the DOE (e.g., at block 1002) is determined. For example, the etching rate can be determined by subtracting the processed thickness of the substrate from the unprocessed thickness and dividing by the processing time. In some embodiments, the etching rate is determined at locations of the radial position near the edge of the first processed substrate for several azimuth angles. Referring to FIG. 11B, a radial plot of the substrate etching rate versus the azimuth angle θ is shown. In some embodiments, the etching rate is determined for all azimuth angles around the center of the processed substrate. In some embodiments, the etching rate is determined for several azimuth angles around the center of the processed substrate such that the determined etching rate represents the entire etching rate profile. The determined etching rate can represent only all azimuth angles. For example, the etching rate can be determined at azimuth angles such as 0°, 15°, 30°, 45°, etc. around the processed substrate near the edge of the substrate. However, the etching rate can be determined at various azimuth angles with different scales than those shown in FIG. 11B. For example, the etching rate can be determined at 0°, 10°, 20°, 30°, etc., or 0°, 30°, 60°, 95°, etc. FIG. 11B shows the etching rate of the processed substrate at various azimuth angles around the center of the substrate near the edge of the substrate.

[0143] Referring back to FIG. 10A, in block 1004A, the etching rate can be normalized. Normalizing the etching rate can help account for differences in etching chamber conditions. Normalizing the etching rate can help account for differences in the substrate, such as slight differences in the composition or defects. Substrate differences can lead to substrate processing inconsistencies and thus inconsistent data. Normalization of the etching rate can help remove from the data set effects outside the range of defects or processing defects and / or differences within the substrate. In some embodiments, the etching rate is normalized using the average etching rate. In some examples, for a first etching rate profile (e.g., the etching rate profile shown in FIG. 11B or FIG. 12A), a first average etching rate is determined. Each value of the first etching rate profile is divided by the first average etching rate to determine a first normalized etching rate profile. In some similar examples, for a second etching rate profile, a second average etching rate is determined. Each value of the second etching rate profile is divided by the second average etching rate to determine a second normalized etching rate profile. Other methods of normalizing the etching rate data can also be used. Further details regarding data normalization are discussed hereinbelow with respect to FIG. 10B.

[0144] Referring to FIG. 12A, an exemplary plot of the substrate etching rate versus the azimuth angle θ is shown. An etching rate profile 1202A corresponding to the etching rate of the first substrate near the edge of the first substrate is shown. An etching rate profile 1204A corresponding to the etching rate of the second substrate near the edge of the second substrate is shown. Referring to FIG. 12B, an exemplary plot of the normalized substrate etching rate versus the azimuth angle θ is shown. The normalized etching rate profile 1202B can correspond to the etching rate profile 1202A of FIG. 12A, and the normalized etching rate profile 1204B can correspond to the etching rate profile 1204A of FIG. 12A. By normalizing the etching rate profiles, at least some of the discrepancies between the processed substrates can be removed from the data, allowing for a comparison of the etching rate values at discrete azimuth angles (e.g., discrete values of θ).

[0145] In block 1004B, a linear fit is performed using the corresponding values of the normalized etching rate of the substrate processed as part of the DOE (e.g., the normalized etching rate values of the processed substrate at the same azimuth angle). Referring to FIG. 13B, an exemplary graphical representation 1300B of the normalized substrate etching rate of substrates processed at various locations is shown. For a particular azimuth angle 1354 (45° shown in FIG. 13B), the normalized etching rate is extracted from each normalized etching rate profile 1352 of the processed substrate. Referring to FIG. 13C, a plot 1300C of the linear fit to the normalized substrate etching rate is shown. The normalized etching rate 1372 for each processed substrate at azimuth angle 1354 is plotted against the differential position along vector 1310 of FIG. 13A. Further details regarding vector 1310 of FIG. 13A are described later in this specification. The plotted normalized etching rate 1372 forms a linear fit 1380. The linear fit 1380 can represent the predicted etching rate of the processed substrate at the corresponding azimuth angle at various positions along vector 1310. The linear fit can be determined for the normalized etching rate at each azimuth angle.

[0146] Referring back to FIG. 10A, at block 1006, an optimal substrate placement location is determined using the linear fit data determined at block 1004B. In some embodiments, the linear fit data can be used to predict an etching rate profile for any substrate placement. By predicting the etching rate profiles at various placement locations, an optimal location that satisfies one or more metrics can be determined. For example, a placement location that minimizes an etching rate range (e.g., an etching rate range near the edge of the substrate) or an etching rate standard deviation (e.g., an etching rate standard deviation near the edge of the substrate) can be determined. By minimizing the etching rate range and / or the etching rate standard deviation, a more consistently processed substrate can be obtained, particularly near the edge of the substrate. After the optimal substrate placement location is determined, the optimal placement is recommended to the substrate processing system. In accordance with the recommended placement, the substrate can be placed on a substrate support within the process chamber.

[0147] Referring to FIG. 10B, a method 1000B for determining an optimal substrate placement for processing in a process chamber is shown. The method 1000B will be described with reference to an etching process, but it can be equally applied to a deposition process. Thus, any description referring to etching, etching rate, etching rate profile, etc. can also be applied to deposition, deposition rate, deposition rate profile, etc. The method 1000B can also be applicable to any other metric that exhibits a linear or higher-order response to substrate placement at a particular azimuth angle. For example, an etching rate gradient for a blanket substrate (e.g., the difference in etching rates from a radius of 146 mm and a radius of 148 mm) and an etching tilt profile for a patterned substrate can also demonstrate a similar response to substrate placement. In block 1010, the substrate is placed at a placement location on a substrate support. The substrate can be a test substrate that is processed as part of a DOE. The substrate can be placed at one of the locations 1102 - 1118 shown in FIG. 11A. In block 1020, an etching operation can be performed on the substrate to remove material from the substrate (alternatively, a deposition operation can be performed to add material to the substrate). In block 1030, a substrate measurement system can be used to measure the etching rate or deposition rate near the edge of the substrate at a plurality of azimuth angles radially spaced from the center of the substrate. In some examples, the etching rate or deposition rate is measured at a distance of about 140 mm to 150 mm from the center of the substrate around the central axis of the substrate. Using the measured etching rates or deposition rates at various azimuth angles, an etching rate profile or deposition rate profile (e.g., shown in FIG. 11B for a single substrate and in FIG. 12A for two substrates) can be constructed. In block 1040, the etching rate profile or deposition rate profile is normalized. In some embodiments, the etching rate profile or deposition rate profile is normalized using the average etching rate for the etching rate profile or the average deposition rate for the deposition rate profile.For example, referring to FIG. 12A, for the etching rate profile 1202A, the average etching rate can be determined from azimuth angle 0° to azimuth angle 360°. Each value of the etching rate in the etching rate profile can be divided by the average etching rate to calculate the normalized etching rate profile 1202B of FIG. 12B.

[0148] Referring to FIG. 10B again, blocks 1010 to 1040 can be repeated multiple times for a plurality of substrates processed as part of the DOE. Each time block 1010 is repeated, the associated substrate is placed at a different location on the substrate support. In some embodiments, blocks 1010 to 1040 are repeated 9 times to process 9 test substrates at 9 different locations. In some embodiments, blocks 1010 to 1040 are repeated only 3 times to process only 3 test substrates at only 3 different locations. Whether to include a larger or smaller number of substrates in the DOE (and thus repeat blocks 1010 to 1040 a larger or smaller number of times) depends on the accuracy threshold of the DOE. For example, if the accuracy threshold is higher, more test substrates are processed. Similarly, if the accuracy threshold is lower, fewer test substrates can be processed.

[0149] In block 1050, a normalized etching rate profile for each of the substrates processed in blocks 1010 - 1040 (e.g., during each iteration of blocks 1010 - 1040) in various substrate arrangements is compiled. Referring to FIG. 13B, a graphical display 1300B of the normalized etching rate profile is shown. The normalized etching rate profile 1352 can represent the etching rate profile for the substrates processed at each of the placement locations 1102 - 1118 shown in FIG. 11A and / or at each of the placement locations 1302 shown in FIG. 13A. Referring again to FIG. 10B, in block 1055, using the normalized etching rate profile compiled in block 1050, the normalized etching rate at each azimuth angle for each of the processed substrates is determined. Referring to FIG. 13B, the normalized etching rate is determined from the corresponding normalized etching rate profile 1352 at the azimuth angle 1354. The azimuth angle 1354 is shown as 45°. However, in some embodiments, depending on how deep the substrate etching rate sampling map is, several normalized etching rates for each of the processed substrates are determined from the normalized etching rate profile 1352 at all azimuth angles.

[0150] Referring back to FIG. 10B, at block 1060, a linear fit is performed for each azimuth angle for which the normalized etch rate was determined at block 1055. The linear fit can be performed using various linear and non-linear higher-order fitting methods known to those skilled in the art. Referring to FIG. 13A, an exemplary plot 1300A showing the substrate placement in the DOE is shown. The substrates can be processed while each is placed at a respective substrate placement location 1302 on a substrate support. Vector 1310 can correspond to azimuth angle 1354 of FIG. 13B. Vector 1310 can make an angle equal to the value of azimuth angle 1354 with respect to the X-axis. The placement locations 1302 can be projected onto vector 1310, and each location of the projected placement locations on vector 1310 is converted to a value y'. As shown, y' is at an angle of 45° from the X-axis of plot 1300A, and azimuth angle 1354 is similarly at a corresponding angle θ of 45°. Referring to FIG. 13C, the normalized etch rate 1372 at azimuth angle 1354 is shown with respect to dy'. The normalized etch rate 1372 is plotted for each of the processed substrates. A linear fit 1380 is calculated to fit the plotted normalized etch rate 1372. The process of projecting placement locations 1302 onto vector 1310, converting each location of the projected placement locations on vector 1310 to y', and plotting the normalized etch rate 1372 with respect to dy' can be repeated for each of the data corresponding to each of several azimuth angles.

[0151] Referring again to FIG. 10B, at block 1070, a predicted etching rate profile is calculated for the estimated substrate placement locations using one or more linear fits calculated at block 1060. For example, etching rate data and / or linear fits can be used to determine estimated locations where a substrate can be fabricated that meets one or more threshold criteria. The threshold criteria can include a threshold etching rate profile range, a threshold etching rate profile minimum value, a threshold etching rate profile maximum value, and / or a threshold etching rate profile standard deviation. The predicted value of the etching rate at a particular azimuth angle can be calculated for the estimated substrate placement locations using the linear fit 1380 corresponding to the particular azimuth angle. After the predicted etching rates at all azimuth angles have been determined, the predicted etching rates can be combined to form a predicted etching rate profile. At block 1080, an optimal substrate placement location for creating an optimized etching rate profile is determined. In some embodiments, the processing logic explores all substrate placement locations to determine which location has an optimal etching rate profile (e.g., meets one or more of the threshold criteria described above). The optimal placement location can be determined experimentally. In some embodiments, the machine learning model described herein can be used to determine the optimal placement location. The machine learning model can be trained with past data such as past etching rate profiles and / or past substrate placement locations to determine the optimal placement for fabricating a substrate having an optimized etching rate profile. At block 1090, the substrate can be placed at the optimal placement location for processing.

[0152] Referring again to FIG. 12A, an exemplary plot 1200A of the substrate etching rate versus the azimuth angle θ according to an aspect of the present disclosure is shown. In some embodiments, the etching rate profile 1202A is the etching rate profile of a substrate processed at an optimal location on the substrate support. The optimal location can be determined using one or more methods described herein. In contrast, the etching rate profile 1204A is the etching rate profile of a substrate processed at a non-optimal location on the substrate support.

[0153] Referring to FIG. 12B, an exemplary plot 1200B of the normalized etching rate versus the azimuth angle θ according to an aspect of the present disclosure is shown. In some embodiments, the normalized etching rate profile 1202B is the normalized etching rate profile of a substrate processed at an optimal location on the substrate support. In contrast, the normalized etching rate profile 1204B is the normalized etching rate profile of a substrate processed at a non-optimal location on the substrate support. As shown by plot 1200B, the normalized etching rate profile 1202B has a more consistent normalized etching rate over all azimuth angles θ. Thus, the etching rate of a substrate processed at an optimal location is more consistent, and processing the substrate at an optimal location results in a better substrate than when processing the substrate at a non-optimal location.

[0154] FIG. 14 is a flowchart of a method 1400 for determining an optimal substrate placement according to an aspect of the present disclosure. Method 1400 can be executed by processing logic that can include hardware (circuits, dedicated logic, etc.), software (such as that executed on a general-purpose computer system or a dedicated machine), firmware, or some combination thereof. In one embodiment, method 1400 can be executed by a computer system such as the computer system architecture 100 of FIG. 1. In other or similar embodiments, one or more operations of method 1400 can be executed by one or more other machines not shown.

[0155] At block 1410, a first substrate is processed within a process chamber. For example, the process chamber can execute an etching process for partially removing a film on the surface of the substrate or a film deposition process for depositing a film on the substrate. In some embodiments, the film is a polymer. In other embodiments, the film is a ceramic (such as a metal oxide). The processing of the substrate can be executed according to a recipe (such as an etching process recipe, a deposition process recipe, etc.). During processing, the substrate can be supported by a substrate support (such as an electrostatic chuck) of the process chamber. The substrate can be placed at an initial position within the process chamber before processing and can remain at the initial position during processing. After processing, in some embodiments, the substrate includes a surface profile (such as a thickness profile, etc.).

[0156] In block 1412, one or more robots transfer a substrate from a process chamber to a substrate measurement system. If the substrate measurement system is connected to or included within a transfer chamber, a transfer chamber robot can remove the substrate from the process chamber and insert the substrate into the substrate measurement system. If the substrate measurement system is connected to or included within a factory interface, the transfer chamber robot can remove the substrate from the process chamber and place the substrate into a load lock. Then a factory interface robot can remove the substrate from the load lock and insert the substrate into the substrate measurement system. The substrate measurement system can be any of the aforementioned substrate measurement systems, such as an integrated reflectance measurement (IR) device.

[0157] In block 1414, the substrate measurement system generates measurements for a number of locations on the surface of the substrate. Each location can have a unique set of coordinates.

[0158] In block 1416, the substrate measurement system and / or the computing device can generate a profile map (e.g., a substrate surface profile map) of the surface profile of the substrate based on the measurements of the substrate measurement system. The profile map can be an image or can include an image, and each pixel in the image corresponds to coordinates on the substrate. Each pixel can have an intensity value corresponding to a measurement value (e.g., a thickness value) at the coordinates of the substrate associated with the pixel. In some embodiments, the profile map shows a thickness profile, and the thickness profile shows an etching rate profile. For example, the profile map can reflect the thickness profile of a substrate that has undergone an etching process over a predetermined amount of time. In some embodiments, the profile map shows substrate surface defects such as inclinations. In some embodiments, the inclination is correlated with the etching rate. In some embodiments, the profile can be or can include a feature vector, and each entry in the feature vector is associated with the coordinates of the substrate, and each entry can have a value representing the value of the surface profile at the coordinates of the substrate. In some embodiments, the processing logic (e.g., of the measurement system and / or the computing device) can determine an etching rate profile map corresponding to the etching rate near the edge of the substrate.

[0159] In block 1418, the computing device can determine a plurality of etching rates corresponding to a plurality of locations on the substrate. The computing device can use the surface profile map generated in block 1416 to determine an etching rate profile of the etching rate near the edge of the substrate at several azimuth angles around the center of the substrate.

[0160] At block 1420, the processing logic processes data associated with the plurality of etching rates determined at block 1418. In some embodiments, the computing device uses a model to process the data. The model can include a trained machine learning model, a mathematical model, a linear fitting model, and / or a statistical model. The model can output one or more estimated surface profiles associated with one or more estimated placement locations on the substrate support. For example, the model can estimate the predicted surface profile for the substrate processed at the estimated placement location using a numerical method. In some embodiments, the model normalizes the etching rate profile (e.g., determined at block 1418) and determines the normalized etching rate for various values of the azimuth angle θ. In some embodiments, the model performs a linear fit using the normalized etching rates from several processed substrates for each value of the azimuth angle θ. Using the linear fit, the model can determine one or more estimated placement locations on the substrate support for processing a substrate having an optimized etching rate profile.

[0161] At block 1422, the processing logic (e.g., of the computing device) determines a recommended placement for the substrate on the substrate support based on the one or more estimated placement locations (e.g., output by the model at block 1420). In some examples, the computing device can use the estimated placement locations to determine a location on the substrate support for placement of the substrate. Specifically, the computing device can determine a coordinate position based on the value (or values) output from the model at block 1420. The processing logic can then cause another substrate to be placed in the process chamber (e.g., via a substrate handling robot) according to the recommended placement, as described herein.

[0162] FIG. 15 shows a diagrammatic representation of an example form of a machine 1500 of a computing device capable of executing a set of instructions for causing a machine to execute any one or more of the techniques discussed herein. In alternative embodiments, the machine can be connected (e.g., network connection) to other machines in a local area network (LAN), intranet, extranet, or the Internet. The machine can operate in the capacity of a server or client machine in a client-server network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The machine can be a personal computer (PC), tablet computer, set-top box (STB), personal digital assistant (PDA), cellular phone, web appliance, server, network router, switch or bridge, or any machine capable of executing (sequentially or otherwise) a set of instructions that specify actions to be taken by that machine. Further, although only a single machine is shown, the term "machine" shall also be construed to include any collection of machines (e.g., computers) that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the techniques discussed herein. In some embodiments, computing device 1500 can correspond to one or more of server machine 170, server machine 180, prediction server 112, system controller 228, server machine 320, or server machine 350 as described herein.

[0163] The exemplary computing device 1500 includes a processing device 1502, main memory 1504 (e.g., read only memory (ROM), flash memory, dynamic random access memory (DRAM), such as synchronous DRAM (SDRAM), etc.), static memory 1506 (e.g., flash memory, static random access memory (SRAM), etc.), and secondary memory (e.g., data storage device 1528), which communicate with each other via bus 1508.

[0164] The processing device 1502 can represent one or more general-purpose processors such as a microprocessor or a central processing unit. More specifically, the processing device 1502 can be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor implementing other instruction sets, or a processor implementing a combination of instruction sets. The processing device 1502 can also be one or more dedicated processing devices such as an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP), or a network processor. The processing device 1502 can also be or include a system on chip (SoC), a programmable logic controller (PLC), or other types of processing devices. The processing device 1502 is configured to execute processing logic for performing the operations discussed herein.

[0165] The computing device 1500 can further include a network interface device 1522 for communicating with the network 1564. The computing device 1500 can also include a video display unit 1510 (e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT)), an alphanumeric input device 1512 (e.g., a keyboard), a cursor control device 1514 (e.g., a mouse), and a signal generation device 1520 (e.g., a speaker).

[0166] The data storage device 1528 can include a machine-readable storage medium (or more specifically, a non-transitory computer-readable storage medium) 1524 storing one or more sets of instructions 1526 that implement any one or more of the techniques or functions described herein. For example, the instructions 1526 can include instructions for the substrate placement engine 330. The non-transitory storage medium refers to a storage medium other than a carrier wave. The instructions 1526 can also be fully or at least partially resident in the main memory 1504 and / or within the processing device 1502 during its execution by the computer device 1500, the main memory 1504, and the processing device 1502, which also constitute a computer-readable storage medium.

[0167] In an exemplary embodiment, the computer-readable storage medium 1524 is shown as a single medium, but the term "computer-readable storage medium" should be interpreted to include a single medium or multiple media (e.g., a centralized or distributed database, and / or an associated cache and server) storing one or more sets of instructions. The term "computer-readable storage medium" should also be interpreted to include any medium capable of storing or encoding a set of instructions for causing a machine to execute any one or more of the techniques of the present disclosure. Thus, the term "computer-readable storage medium" should be interpreted to include, but not be limited to, solid-state memory as well as optical and magnetic media.

[0168] The above description sets forth numerous specific details, such as examples of particular systems, components, methods, etc., in order to provide a good understanding of some embodiments of the present disclosure. However, it will be apparent to those skilled in the art that at least some embodiments of the present disclosure can be practiced without these specific details. In other instances, well-known components or methods have not been described in detail or are presented in a simplified block diagram format to avoid unnecessarily obscuring the present disclosure. Accordingly, the specific details described are merely illustrative. Specific embodiments may vary from these illustrative details and still be contemplated within the scope of the present disclosure.

[0169] Throughout this specification, references to "one embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic described in connection with that embodiment is included in at least one embodiment. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Additionally, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or". When the terms "about" or "approximately" are used in this specification, it is intended that the stated nominal value be accurate within ±10%.

[0170] The operations of the methods described herein are illustrated and described in a particular order, but the order of the operations of each method can be changed, and thus a particular operation can be performed in the reverse order, and a particular operation can be performed at least partially concurrently with other operations. In another embodiment, the instructions for separate operations or sub-operations can also be performed intermittently and / or alternately.

[0171] It should be understood that the foregoing description is intended to be illustrative rather than restrictive. Many other embodiments will be apparent to those of ordinary skill in the art upon reading and understanding the above description. Accordingly, the scope of the present disclosure should be determined with reference to the appended claims, along with the full scope of equivalents to such claims.

Claims

1. Processing a first substrate in a process chamber of a substrate processing system according to a strategy while the first substrate is supported by a substrate support of the process chamber, wherein the first substrate includes a first surface profile after the processing; and Generating a first profile map of the first surface profile of the first substrate using a substrate measurement system of the substrate processing system; and Processing data from the first profile map using a model, wherein the model outputs a first estimated substrate placement value for placement of the first substrate relative to one or more components of the substrate support; and Determining a recommended placement for substrates on the substrate support based on the first estimated substrate placement value A method comprising the above.

2. Further comprising placing a second substrate in the process chamber according to the recommended placement, wherein the one or more components of the substrate support include a process kit ring, and the second substrate is positioned within the inner diameter of the process kit ring according to the recommended placement. The method according to claim 1.

3. Processing the second substrate in the process chamber according to the strategy, wherein the second substrate includes a second surface profile after the processing; and Generating a second profile map of the second surface profile using the substrate measurement system of the substrate processing system; and Processing data from the second profile map using the model, wherein the model outputs a second estimated substrate placement value; and Comparing the first estimated substrate placement value and the second estimated substrate placement value; and Updating the recommended placement based on the comparison The method according to claim 2, further comprising the above.

4. Determining the center of the substrate support; and Aligning the first substrate with the center of the substrate support before the processing of the first substrate The method according to claim 1, further comprising the above.

5. The method according to claim 4, wherein for the recommended placement of the substrate, the center of the substrate is offset from the center of the substrate support.

6. The method according to claim 1, further comprising determining a substrate transfer offset based on the recommended placement, wherein the substrate transfer offset is an offset with respect to a robot arm from a first robot transfer orientation to a second robot transfer orientation.

7. The method according to claim 1, wherein the first surface profile includes a first thickness profile.

8. The method according to claim 1, further comprising determining a first etching rate profile of the first substrate with respect to an etching rate profile near an edge of the first substrate based on the first profile map, wherein the model outputs the first estimated substrate placement value for the placement of the first substrate with respect to one or more components of the substrate support based on the first etching rate profile. The method according to claim 1.

9. The method according to claim 1, wherein the model includes at least one of a trained machine learning model, a physics-based model, or a statistical model.

10. The model includes a trained machine learning model, and the method further comprises training a machine learning model to create the trained machine learning model, wherein the machine learning model is trained using data from a plurality of processed substrates processed according to the strategy. The method according to claim 1.

11. A process chamber, a substrate measurement tool, a memory, and a processing device coupled to the memory, the processing device being configured to: process a first substrate in the process chamber according to a strategy while the first substrate is supported by a substrate support of the process chamber, the first substrate including a first surface profile after the processing; generate a first profile map of the first surface profile of the first substrate using the substrate measurement tool; process data from the first profile map using a model, the model outputting a first estimated substrate placement value for the placement of the first substrate with respect to one or more components of the substrate support; and determine a recommended placement for the substrate on the substrate support based on the first estimated substrate placement value. System.

12. The processing device further It is for arranging a second substrate in the process chamber according to the recommended arrangement, wherein the one or more components of the substrate support include a process kit ring, and the second substrate is positioned within the inner diameter of the process kit ring according to the recommended arrangement. The system according to claim 11.

13. The processing device further processing the second substrate in the process chamber according to the strategy, wherein the second substrate includes a second surface profile after the processing, and the processing; generating a second profile map of the second surface profile using the substrate measurement tool; processing data from the second profile map using the model, wherein the model outputs a second estimated substrate placement value; comparing the first estimated substrate placement value and the second estimated substrate placement value; updating the recommended arrangement based on the comparison. The system according to claim 12.

14. The processing device further determining the center of the substrate support; aligning the first substrate with the center of the substrate support before the processing of the first substrate. The system according to claim 11.

15. For the recommended arrangement for the substrate, the center of the substrate is offset from the center of the substrate support. The system according to claim 11.

16. The model includes a trained machine learning model, and the processing device further is for training a machine learning model to create the trained machine learning model, wherein the machine learning model is trained using data from a plurality of processed substrates processed according to the strategy. The system according to claim 11.

17. A computer-readable medium including instructions that, when executed by a processing device, cause the processing device to perform operations, the operations including processing a first substrate in a process chamber according to a strategy while the first substrate is supported by a substrate support of the process chamber, wherein the first substrate includes a first surface profile after the processing, and the processing; Using the substrate measurement system of the substrate processing system to generate a first profile map of the first surface profile of the first substrate; Processing data from the first profile map using a model, the model outputting a first estimated substrate placement value for the placement of the first substrate relative to one or more components of the substrate support; Determining a recommended placement for a substrate on the substrate support based on the first estimated substrate placement value. A computer-readable medium comprising: **Claim 18** The operation further comprises: Placing a second substrate in the process chamber according to the recommended placement, the one or more components of the substrate support including a process kit ring, the second substrate being positioned within the inner diameter of the process kit ring according to the recommended placement. The computer-readable medium of claim 17. **Claim 19** The operation further comprises: Processing the second substrate in the process chamber according to the strategy, the second substrate including a second surface profile after the processing; Using the substrate measurement system to generate a second profile map of the second surface profile; Processing data from the second profile map using the model, the model outputting a second estimated substrate placement value; Comparing the first estimated substrate placement value and the second estimated substrate placement value; Updating the recommended placement based on the comparison. The computer-readable medium of claim 18. **Claim 20** The model includes a trained machine learning model, and the operation further comprises: Training a machine learning model to create the trained machine learning model, the machine learning model being trained using data from a plurality of processed substrates processed according to the strategy. The computer-readable medium of claim 17. **Claim 21** A computer-readable medium including instructions that, when executed by a processing device, cause the processing device to perform operations, the operations including: Processing a first substrate in a process chamber of a substrate processing system while the first substrate is supported by a substrate support at a first placement location on the substrate support, wherein the first substrate includes a first surface profile after the processing; Generating a first surface profile map of the first surface profile using a substrate measurement system; Determining a first plurality of etching rates corresponding to a first plurality of locations on the first substrate based on the first surface profile map; Processing data associated with the first plurality of etching rates using a model, wherein the model is for outputting one or more estimated surface profiles associated with one or more estimated placement locations on the substrate support based on the first plurality of etching rates; Determining a recommended placement for a substrate on the substrate support based on the one or more estimated placement locations. A computer-readable medium comprising: Claim 22 The operation further comprises: Placing a second substrate in the process chamber on the substrate support according to the recommended placement within the inner diameter of the process kit ring. The computer-readable medium according to claim 21 Claim 23 The operation further comprises: Processing a second substrate in the process chamber while the second substrate is supported by the substrate support at a second placement location on the substrate support, wherein the second substrate includes a second surface profile after the processing; Generating a second surface profile map of the second surface profile using the substrate measurement system; Determining a second plurality of etching rates corresponding to a second plurality of locations on the second substrate based on the second surface profile map; Processing data associated with the second plurality of etching rates using the model, wherein the one or more estimated surface profiles associated with the one or more estimated placement locations on the substrate support are further based on the second plurality of etching rates. The computer-readable medium according to claim 21 Claim 24 The computer-readable medium according to claim 21, wherein the recommended arrangement is offset from the center of the substrate support.

25. The computer-readable medium according to claim 1, wherein the model includes at least one of a trained machine learning model, a linear fitting model, or a statistical model.

26. The model includes the trained machine learning model, and the operation The computer-readable medium according to claim 25, further comprising training a machine learning model to create the trained machine learning model, wherein the machine learning model is trained using data from a plurality of processed substrates processed in the process chamber.

27. The computer-readable medium according to claim 21, wherein the plurality of locations on the first substrate correspond to locations at a radial distance from the center of the first substrate in a plurality of azimuth angles.

28. Processing the data associated with the plurality of first etching rates includes generating a linear fit of at least one first etching rate of the plurality of first etching rates corresponding to at least one first location of the plurality of first locations, and the one or more estimated surface profiles are based on the linear fit. The computer-readable medium according to claim 21.

29. Processing the data associated with the plurality of first etching rates includes normalizing each of the plurality of first etching rates based on an average etching rate of the plurality of first etching rates. The computer-readable medium according to claim 21.

30. The recommended arrangement corresponds to an optimized arrangement location on the substrate support for fabricating a second substrate having a plurality of second etching rates at a plurality of second locations on the second substrate that match one or more values of one or more metrics. The computer-readable medium according to claim 21.

31. The computer-readable medium according to claim 21, wherein the first surface profile includes a first thickness profile.

32. A process chamber comprising a substrate support, A substrate measurement tool, A memory, A processing device operably coupled to the memory, the processing device Processing the first substrate in the process chamber while the first substrate is supported by the substrate support at a first placement location on the substrate support, wherein the first substrate includes a first surface profile after the processing; Generating a first surface profile map of the first surface profile using the substrate measurement tool; Determining a first plurality of etching rates corresponding to a first plurality of locations on the first substrate based on the first surface profile map; Processing data associated with the first plurality of etching rates using a model, wherein the model is for outputting one or more estimated surface profiles associated with one or more estimated placement locations on the substrate support based on the first plurality of etching rates; Determining a recommended placement for the substrate on the substrate support based on the one or more estimated placement locations; A system.

33. The processing device further comprises: For placing a second substrate in the process chamber on the substrate support according to the recommended placement within the inner diameter of the process kit ring, the system according to claim 32.

34. The processing device further comprises: Processing the second substrate in the process chamber while the second substrate is supported by the substrate support at a second placement location on the substrate support, wherein the second substrate includes a second surface profile after the processing; Generating a second surface profile map of the second surface profile using the substrate measurement tool; Determining a second plurality of etching rates corresponding to a second plurality of locations on the second substrate based on the second surface profile map; For performing processing data associated with the second plurality of etching rates using the model, wherein the one or more estimated surface profiles associated with the one or more estimated placement locations on the substrate support are further based on the second plurality of etching rates, the system according to claim 32.

35. The model includes a trained machine learning model, and the processing device further trains a machine learning model to create the trained machine learning model, the machine learning model being trained using data from a plurality of processed substrates processed in the process chamber, the system of claim 32. **Claim 36** processing data associated with the first plurality of etching rates, normalizing each of the first plurality of etching rates based on an average etching rate of the first plurality of etching rates, generating a linear fit of at least one first etching rate of the first plurality of etching rates corresponding to at least one first location of the first plurality of locations, the one or more estimated surface profiles being based on the linear fit, the system of claim 32. **Claim 37** The recommended placement corresponds to an optimized placement location on the substrate support for fabricating a second substrate having a second plurality of etching rates at a second plurality of locations on the second substrate that match one or more values of one or more metrics, the system of claim 32. **Claim 38** processing a first substrate in a process chamber while the first substrate is supported by a substrate support at a first placement location on the substrate support, the first substrate including a first surface profile after the processing, generating a first surface profile map of the first surface profile using a substrate measurement system, determining a first plurality of etching rates corresponding to a first plurality of locations on the first substrate based on the first surface profile map, processing data associated with the first plurality of etching rates using a model, the model being for outputting one or more estimated surface profiles associated with one or more estimated placement locations on the substrate support based on the first plurality of etching rates, determining a recommended placement for the substrate on the substrate support based on the one or more estimated placement locations comprising a method. **Claim 39** Placing a second substrate in the process chamber on the substrate support according to the recommended placement within the inner diameter of the process kit ring The method according to claim 38, further comprising: **Claim 40** Processing the data associated with the first plurality of etching rates includes generating a linear fit of at least one first etching rate of the first plurality of etching rates corresponding to at least one first location of the first plurality of locations, wherein the one or more estimated surface profiles are based on the linear fit. The method according to claim 38.

Images