Metrology in substrate chamber for process characterization and improvement

Abstract

A method includes receiving, by a processing device, first data generated by a first sensor of a substrate processing system. The first data is generated in response to the first sensor receiving electromagnetic radiation from a substrate held by a robotic arm of a transfer chamber in the free radical plate processing system. The method further includes processing the first data to obtain second data. The second data includes a first indication of performance of the substrate processing system. The method further includes causing execution of a corrective action associated with the substrate processing system in view of the second data.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to process control and process learning for substrate processing systems. Embodiments of the present disclosure further relate to a metrology system capable of generating metrology measurements of substrates while those substrates are held by a robotic arm (eg, of a transfer chamber). Background Art

[0002] Chambers are used in many types of processing systems. Examples of chambers include etching chambers, deposition chambers, annealing chambers, etc. Typically, a substrate (such as a semiconductor wafer) is placed on a substrate support within the chamber, and conditions in the chamber are set and maintained to process the substrate. Detailed knowledge of the processing conditions, the effects of the conditions on the substrate, and the evolution of these parameters over time enables tight control of product properties. Measuring one or more properties of the substrate (e.g., performing metrology operations) can inform decisions or actions associated with updating or maintaining processing conditions for the substrate. Summary of the invention

[0003] The following is a brief summary of the disclosure in order to provide a basic understanding of some aspects of the disclosure. This summary is not an extensive review of the disclosure. It is neither intended to identify the key or important elements of the disclosure nor to describe any scope of a specific implementation of the disclosure or any scope of the claims. Its sole purpose is to present some concepts of the disclosure in a simplified form as a preface to a more detailed description presented later.

[0004] A method includes receiving, by a processing device, first data generated by a first sensor of a substrate processing system. The first data is generated in response to the first sensor receiving electromagnetic radiation from a substrate held by a robotic arm of a transfer chamber in the substrate processing system. The method further includes processing the first data to obtain second data. The second data includes a first indication of a performance of the substrate processing system. The method further includes causing execution of a corrective action associated with the substrate processing system in view of the second data.

[0005] A substrate processing system includes a processing chamber, a transfer chamber, a robot arm for the transfer chamber, a sensor, and a processing device. The transfer chamber is coupled to the processing chamber. The robot arm is configured to transfer a substrate between the processing chamber and the transfer chamber. The sensor has a field of view. When the substrate is transferred to and from the processing chamber by the robot arm, at least a portion of the field of view includes at least a portion of the substrate. The sensor is used to receive electromagnetic radiation that has interacted with the substrate. The processing device is used to process data. The data is generated in response to the sensor receiving the electromagnetic radiation. The processing device is used to determine at least one of the following: (i) one or more indications of the performance of the substrate processing system or (ii) one or more properties of the substrate.

[0006] A non-transitory machine-readable storage medium stores instructions. The instructions, when executed, cause a processing device to perform operations. The operations include receiving first data generated by a first sensor of a substrate processing system. The first data is generated in response to the first sensor receiving electromagnetic radiation from a substrate held by a robot arm of a transfer chamber of the substrate processing system. The operations further include processing the first data to obtain second data. The second data includes first one or more property values ​​of the substrate. The operations further include causing execution of a corrective action associated with the substrate processing system in view of the second data.

[0007] Numerous other features are provided according to these and other aspects of the disclosure. Other features and aspects of the disclosure will become more apparent from the following detailed description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The present disclosure is illustrated by way of example and not by way of limitation in the figures of the accompanying drawings, in which like reference numerals represent similar elements. It should be noted that different references to "one" or "an" embodiment in the present disclosure do not necessarily refer to the same embodiment, and such references mean at least one.

[0009] Figure 1 is a schematic top view of an exemplary processing system according to some embodiments.

[0010] Figure 2 is a simplified side view of a substrate processing system including an electromagnetic radiation probe according to some embodiments.

[0011] Figure 3A is a schematic representation of a metrology system including a probe array according to some embodiments.

[0012] Figure 3B is a schematic bottom view of a blade of a substrate processing system according to some embodiments.

[0013] Figure 3C is a schematic representation of a metrology system including a probe array and an acquisition trajectory according to some embodiments.

[0014] Figure 3D is a schematic representation of a metrology system including a probe array and an acquisition trajectory according to some embodiments.

[0015] Figure 4 is a block diagram illustrating an exemplary system architecture 400 according to some implementations.

[0016] Figure 5 is a block diagram of an exemplary dataset generator for generating datasets for one or more models according to some embodiments.

[0017] Figure 6 is a block diagram of a system for generating output data for performing corrective action, according to some implementations.

[0018] Fig. 7A is a flow chart of a method for generating a data set for a model for generating output data, according to some embodiments.

[0019] Figure 7B is a flow chart of a method for generating and utilizing data based on radiation received by a probe while a substrate is within a processing system, according to some embodiments.

[0020] Figure 7C is a flow chart of a method 700C for predicting a characteristic of a substrate based on probe data collected from within a processing system, according to some embodiments.

[0021] Figure 8 Depicted is a block diagram of an exemplary computing device in accordance with some implementations. DETAILED DESCRIPTION

[0022] Methods, systems, apparatus, etc. related to performing substrate measurements in a controlled environment are described herein. For example, the methods, systems, and apparatus of the present disclosure may relate to performing metrology measurements of substrates in a vacuum; may relate to metrology measurements that are transparent to the throughput of substrates in processing; may relate to measurements of substrates in an environmentally controlled chamber that are indicative of processing conditions associated with the substrates, and the like.

[0023] In some systems, substrates are processed and / or manufactured in one or more processing chambers. The processing chamber can distinguish the processing environment (e.g., the spatial region where the substrate is processed) from the surrounding conditions. For example, substrate processing can be performed under controlled gas pressure, under controlled gas mixture, under vacuum, etc.

[0024] In some systems, multiple processing chambers may be coupled to a single processing system, for example, multiple processing chambers may each be coupled to a central transfer chamber. The environment within the processing chamber, within the transfer chamber, various other chambers (e.g., a loading chamber), etc. may be a controlled environment.

[0025] In some systems, the substrate processing system can be configured to manufacture multi-layer substrates. One or more operations can be performed to produce one layer of the substrate, a second one or more operations can be performed to produce another layer of the substrate, and so on. In some systems, the substrate can be transferred between processing chambers during processing, for example, a first processing chamber coupled to a transfer chamber can be configured to perform a first operation for processing the substrate, a second processing chamber coupled to the transfer chamber can be configured to perform a second operation for processing the substrate, and so on. The substrate can be processed in multiple stages in multiple processing chambers without interacting with ambient atmospheric conditions, without leaving the controlled environment of the processing system, and so on.

[0026] In some systems, the substrate may be sensitive to atmospheric conditions. The substrate (e.g., the material of the substrate, the film of the substrate, the shape or size of the substrate, etc.) may be damaged, altered, or changed when atmospheric conditions, uncontrolled atmospheres, etc. are introduced. In some systems, the substrate may be protected (e.g., may have a final layer of atmospheric contaminant resistance deposited) prior to removal from the processing system.

[0027] In some systems, substrate measurements (e.g., metrology measurements) will be performed on the manufactured substrates. Metrology of the substrates can provide an indication of substrate performance (e.g., a prediction of whether substrate performance is satisfactory / unsatisfactory), an indication of substrate processing performance (e.g., the quality of the substrate processing procedure). Metrology can be performed in a stand-alone metrology system (e.g., a room, facility, area, etc. separate from the substrate processing system) or an inline metrology system (e.g., a metrology system coupled to the substrate processing system), etc.

[0028] In some systems, the metrology operations may be performed external to the processing system, e.g., the substrate may leave the controlled environment before it is measured, the substrate may be exposed to atmospheric / ambient conditions before it is measured, the substrate may have metrology operations performed under ambient conditions, etc. In some systems, the metrology operations may be separated in time from the processing operations. An in-line metrology system may receive a substrate, perform measurements on the substrate, etc., minutes after the final processing operation is performed. Any information from the substrate (e.g., to be used to control or adjust future processing) may be temporarily unavailable (e.g., due to such delay). An independent metrology system may receive a substrate hours after the final substrate processing operation is performed. Many other substrates may be processed between processing the substrate and generating metrology data from the independent metrology system.

[0029] In some systems, metrology operations may be performed on a subset of substrates produced by a substrate processing system. For example, randomly selected substrates may be marked for further metrology, substrates may be periodically marked for further metrology (e.g., one out of every n substrates produced), selected substrates may be marked for metrology based on a performance metric (e.g., sensor data associated with processing of those substrates), etc. In some embodiments, a subset of substrates may be marked for metrology operations, metrology operations may be performed on them, etc. due to the time cost associated with performing metrology operations. Including more substrates in the metrology operations may reduce the processing throughput of the substrate processing system.

[0030] The present disclosure may address one or more of the shortcomings of known substrate processing and / or metrology systems. In some embodiments, a metrology system that generates measurements based on receiving electromagnetic (e.g., optical) radiation from a substrate is included as part of a processing system. The metrology system may be configured to receive radiation emitted by a substrate, radiation transmitted through a substrate, radiation reflected by a substrate, and the like. The metrology system may include a probe, such as a device for collecting electromagnetic radiation from a substrate. The probe may be disposed within a processing system, for example, the probe may be located within a processing chamber, within a transfer chamber, within a load lock, within a host or chamber body, within a factory interface, may be located within a controlled environment, and the like. The probe may receive electromagnetic radiation from a substrate while the substrate is in a controlled environment (e.g., a processing environment, a vacuum, an inert environment, and the like).

[0031] A probe for receiving electromagnetic radiation from a substrate can be arranged along a path that a substrate travels during or between processing operations. For example, a probe can be arranged above an area of ​​a chamber or component configured to accommodate one or more substrates (e.g., the probe can be suspended on a cover or top wall of a transfer chamber, a processing chamber, a load lock, a slit valve assembly, a factory interface, etc.). The probe can have a field of view from which the probe can receive electromagnetic radiation. The field of view of the probe can be positioned to include one or more areas of the chamber configured to accommodate substrates. For example, a probe near the top of the chamber can have a field of view pointing below the probe. The field of view of the probe can intersect with an area through which a substrate passes when being transferred (e.g., from one chamber to another). For example, a probe can be arranged near an interface between a processing chamber and a transfer chamber. When a robotic arm (e.g., associated with a transfer chamber, configured to transfer one or more substrates within a processing system, etc.) transfers a substrate into and / or out of a processing chamber, a portion of the substrate can pass through the field of view of the probe. In some embodiments, the probe can be positioned in different ways. For example, the probe may be located within a transfer chamber but not associated with a particular processing chamber coupled to the transfer chamber. In another example, the probe may be disposed in a slit valve assembly that separates a processing chamber from a transfer chamber. In some embodiments, a first processing chamber may be used for a first set of operations associated with processing a substrate, and the substrate may be moved to a second chamber for a second set of operations. The probe may be disposed such that a substrate passing from a first processing chamber through a transfer chamber to a second processing chamber may intersect a field of view of the probe.

[0032] In some embodiments, one or more measurements are taken when the substrate passes through the field of view of the probe. In some embodiments, the probe can provide radiation received from the substrate (e.g., via one or more optical elements, via fiber optic cables, etc.) to a spectrometer, to one or more detectors, to one or more cameras or imagers, etc. In some embodiments, one or more measurements can be taken while the substrate is being transferred between locations, for example, the substrate can be continuously moved while the probe is collecting radiation. In some embodiments, the probe can be placed so that the substrate naturally passes through the field of view of the probe, for example, receiving electromagnetic radiation from the substrate may not increase the processing time, completion time, manufacturing time, etc. of the substrate. In some embodiments, multiple data points are acquired while the substrate is transferred through the field of view of the probe. For example, multiple data points along the diameter of the substrate can be collected. In some embodiments, an electromagnetic source can be provided, and radiation reflected by or transmitted through the substrate by the substrate can be collected by the probe. In some embodiments, the probe may include a pyrometer, and emitted radiation can be collected from the substrate.

[0033] In some embodiments, multiple probes may be employed (e.g., to map a larger portion of a substrate). In some embodiments, additional detection systems may be used, for example, an object detection system may be used to synchronize data acquisition with the presence of a substrate in the field of view, synchronize robot operation with spectrometer operation, and the like. In some embodiments, a robot used to transport a substrate may be instructed to adjust the path of the substrate through the processing system to facilitate measurements made by the probe. In some embodiments, the robot may pass a substrate through the field of view of a probe multiple times, may keep a substrate within the field of view of a probe for a longer period of time, may transport a substrate along a path such that a larger portion of the substrate passes through the field of view of the probe than if the substrate were directly transferred from one chamber to another, and the like. In some embodiments, one or more portions of a substrate may pass through the field of view of one or more probes multiple times during processing. For example, a substrate may be transported into a processing chamber to deposit a film. When the substrate is transported to the processing chamber, the substrate may pass through the field of view of the probe, radiation may be provided to the probe, and the like. After processing, the substrate may be transported to another chamber and may pass through the field of view of the probe again.

[0034] A processing device (e.g., a computer processor) may be provided with data from a spectrometer or other sensor. The processing device may infer one or more metrics associated with the measured substrate. In some embodiments, the processing device may generate an indication of one or more properties of the substrate. The processing device may use data based on electromagnetic radiation received from the substrate to determine and / or predict one or more properties of the substrate. The thickness, film composition, etc. of a film (e.g., a film deposited on a substrate) may be determined by the processing device. In some embodiments, data from a spectrometer may be provided to a physics-based model to determine one or more properties of the substrate. In some embodiments, data from a spectrometer and / or other sensor may be provided to a machine learning model that is trained to receive spectrometer data and generate an indication of substrate properties as an output.

[0035] In some embodiments, the processing device may generate an indication of the performance (e.g., performance quality) of one or more processing operations associated with the substrate. The processing device may receive spectral data from a spectrometer. The processing device may provide the spectral data to a trained machine learning model, which is configured to generate as an output a prediction of the processing conditions under which a previously processed substrate was subjected. In some embodiments, the processing device may provide the spectral data to the machine learning model, which is configured to cause the performance of a corrective action (e.g., planning maintenance, updating a processing recipe, providing an alert to a user, etc.).

[0036] Aspects of the present disclosure provide one or more technical advantages over known systems. The present disclosure enables measurements indicative of substrate processing to be performed in a controlled environment (e.g., within a processing system, in a transfer chamber, in a process chamber, etc.). In known in-line or stand-alone metrology systems, it may not be possible to measure substrates that are sensitive to atmosphere. For example, a protective layer may be applied to a substrate prior to removing the substrate from the controlled environment, which may prevent measurement of other layers of the substrate.

[0037] Aspects of the present disclosure enable multiple measurements of a substrate throughout a process. For example, as a substrate is moved in and out of a process chamber, measurements may be taken by a probe, which may indicate one or more properties of the substrate, one or more processing conditions of the substrate, and the like. In some embodiments, multiple measurements may be taken of a substrate throughout a process, such as between a series of processing operations. In this manner, layers that may be obscured by performing metrology on an entire stack of substrate layers may be more accurately measured.

[0038] Various aspects of the present disclosure enable measurement of a substrate quickly (e.g., seconds after processing, minutes after processing, etc.) after one or more processing operations are performed on the substrate. In some systems, metrology of one or more produced substrates may be used to perform corrective actions, such as updating a process recipe, planning maintenance, providing an alert to a user, etc. In some known systems, there may be a significant delay between processing a substrate and performing a metrology operation associated with the substrate (e.g., in terms of time, in terms of additional substrates being processed before changes may be made, etc.). According to the present disclosure, a substrate may be measured immediately after processing (e.g., electromagnetic radiation may be received from the substrate by a probe). Updates to process conditions, process recipes, etc. may be quickly initiated and / or performed, thereby reducing wasted material, energy, time, etc., operating a substrate processing system under suboptimal process conditions.

[0039] Aspects of the present disclosure enable metrology measurements of substrates to be performed while the substrates are being transported through a processing system. For example, a transport robot may operate normally, and while the transport robot is operating normally (e.g., as the robot operates without the probe included in the processing system), the electromagnetic probe may receive radiation from the substrate, the processing device may determine one or more properties of the substrate, and the like. Aspects of the present disclosure may enable metrology to be performed without impacting the throughput of the substrate processing system (e.g., the metrology system may be throughput transparent), without significantly impacting the throughput (e.g., metrology operations according to the present disclosure may increase the throughput by an amount of time less than a threshold), and the like. Aspects of the present disclosure may enable measurement of more substrates of a substrate processing system, for example, each substrate processed by the processing system may be measured by the metrology system, a portion of the substrates processed by the processing system (e.g., each substrate processed in a first processing chamber of the substrate processing system) may be measured by the metrology system, and the like. In some embodiments, feedback control, recipe updates, planned maintenance, and the like may be based on metrology of substrates. Enabling measurement of a larger portion of a substrate may increase the certainty of prediction of a corrective action (e.g., additional data may increase the statistical likelihood of an accurate corrective action). Measuring a greater portion of substrates processed by a substrate processing system may facilitate the processing system to avoid making erroneous changes to one or more process recipes, may facilitate the processing system to take appropriate (e.g., increase the likelihood that produced substrates meet target performance metrics) corrective actions (e.g., by increasing the certainty of detected differences from ideal conditions in a processing chamber), etc. This may provide technical advantages to substrate processing systems by reducing energy, time, and materials used to perform suboptimal processing operations, may reduce energy, time, material, and defective product disposal costs associated with an increased likelihood of producing defective products, etc.

[0040] In one aspect of the present disclosure, a method includes receiving, by a processing device, first data generated by a first sensor of a substrate processing system. The first data is generated in response to the first sensor receiving electromagnetic radiation from a substrate held by a robotic arm of a transfer chamber in the substrate processing system. The method further includes processing the first data to obtain second data. The second data includes a first indication of a performance of the substrate processing system. The method further includes causing execution of a corrective action associated with the substrate processing system in view of the second data.

[0041] In another aspect of the present disclosure, a substrate processing system includes a processing chamber, a transfer chamber, a robot arm for the transfer chamber, a sensor, and a processing device. The transfer chamber is coupled to the processing chamber. The robot arm is configured to transfer a substrate between the processing chamber and the transfer chamber. The sensor has a field of view. When the substrate is transferred to and from the processing chamber by the robot arm, at least a portion of the field of view includes at least a portion of the substrate. The sensor is used to receive electromagnetic radiation that has interacted with the substrate. The processing device is used to process data. The data is generated in response to the sensor receiving the electromagnetic radiation. The processing device is used to determine at least one of the following: (i) one or more indications of the performance of the substrate processing system or (ii) one or more properties of the substrate.

[0042] In another aspect of the present disclosure, a non-transitory machine-readable storage medium stores instructions. The instructions, when executed, cause a processing device to perform operations. The operations include receiving first data generated by a first sensor of a substrate processing system. The first data is generated in response to the first sensor receiving electromagnetic radiation from a substrate held by a robot arm of a transfer chamber of the substrate processing system. The operations further include processing the first data to obtain second data. The second data includes first one or more property values ​​of the substrate. The operations further include causing execution of a corrective action associated with the substrate processing system in view of the second data.

[0043] Figure 1 1 is a schematic top view of an exemplary processing system 100 according to some embodiments. The processing system 100 may be a substrate processing system. The processing system 100 includes a transfer chamber robot 101 and a factory interface robot 121, each of which is suitable for transferring a substrate from an electronic device processing system (such as a Figure 1 The robot 100 of the present invention picks up a substrate 110 (sometimes referred to as a "wafer" or "semiconductor wafer") from a destination in the processing system 100 shown in FIG. 1 , or places the substrate 110 at the destination. However, any type of electronic device substrate, mask, or other silicon dioxide-containing substrate (generally referred to herein as a "substrate") can be transported and transferred by the disclosed robot. For example, the destination of the substrate 110 can be one or more processing chambers 103, and / or one or more of the load lock devices 107A, 107B that can be distributed around and coupled to the transfer chamber 114. As shown, for example, the substrate transfer can pass through a slit valve 111.

[0044] The processing system 100 may further include a host 102 including a transfer chamber 114 and a plurality of processing chambers 103. The housing of the host 102 includes the transfer chamber 114. The transfer chamber 114 may include a top wall (not shown), a bottom wall (floor) 139, and side walls, and may include a controlled environment. The controlled environment may include vacuum conditions, controlled pressure (e.g., different from the surrounding atmospheric pressure), a controlled gas environment (e.g., an inert gas such as argon or nitrogen or a gas mixture), etc. In the depicted embodiment, the transfer chamber robot 101 is mounted to the bottom wall (floor) 139. However, the transfer chamber robot 101 may be mounted elsewhere, such as to the top wall.

[0045] In various embodiments, the processing chamber 103 can be adapted to perform any number of processes on the substrate 110. These processes can include deposition, oxidation, nitration, etching, polishing, cleaning, photolithography, metrology (e.g., integrated metrology), etc. Other processes can also be performed. The load lock devices 107A, 107B can be adapted to dock with the factory interface 117 or other system components, which can receive the substrate 110 from, for example, a substrate carrier 119 (e.g., a Front Opening Unified Pod, FOUP) that can be docked at the load port of the factory interface 117. The factory interface robot 121 (illustrated in dashed lines) can be used to transfer the substrate 110 between the substrate carrier 119 and each load lock device 107A, 107B. The transfer of the substrate 110 can be performed in any order or direction. In some embodiments, the factory interface robot 121 can be the same (or similar) as the transfer chamber robot 101, but can further include a mechanism that allows the factory interface robot to move in any lateral direction and as indicated by arrow 123. Any other suitable robot may be used as the factory interface robot 121. In some embodiments, the system 100 may be coupled to (eg, interfaced with) a metrology system, such as an integrated metrology system, an in-line metrology system, or the like.

[0046] In an embodiment, and by way of exemplary explanation of any robot, the transfer chamber robot 101 includes at least one arm 113 (e.g., a robot arm) and at least one end effector 115 coupled to the arm 113. The end effector 115 may be controlled by the transfer chamber robot 101 to pick up a substrate 110 from a load lock device 107A or 107B, guide the substrate 110 through one of the slit valves 111 of the process chamber 103, and accurately place the substrate 110 on a substrate support of the process chamber 103. In some embodiments, the end effector 115 may include a blade for supporting the substrate 110. In some embodiments, the end effector 115 may support a first portion of the substrate 110, for example, may be annular so that some portion of the substrate 110 can be visible from the bottom when the substrate 110 is supported by the end effector 115.

[0047] In various embodiments, one or more of the processing chambers 103 may include a probe 120 (e.g., a device for collecting electromagnetic radiation), at least a portion of which is within the chamber of the processing system 100. In some embodiments, the probe 120 may be within the processing chamber 103 (as shown). In some embodiments, the probe 120 may be within the transfer chamber 114. In some embodiments, the probe 120 may be within a slit valve assembly including a slit valve 111. In some embodiments, the probe 120 may be within a load lock 107A-107B. In some embodiments, the probe 120 may be within a factory interface 117. In some embodiments, the probe 120 may include an optical component designed to couple radiation collected from within the chamber of the processing system 100 and couple the radiation into one or more fiber optic cables / cores. In some embodiments, the probe 120 may be disposed above the path of the substrate (e.g., may be suspended from or embedded in the top wall of the processing system 100). In some embodiments, the probe 120 may be disposed below the path of the substrate. In some embodiments, multiple probes may be included in the processing system 100, the processing chamber 103, the transfer chamber 114, etc.

[0048] In some embodiments, the field of view of the probe (e.g., the spatial region from which the probe is configured to receive electromagnetic radiation) can intersect the path of the substrate 110, the path of the end effector 115, can be near a coupling between chambers (e.g., near the slit valve 111), etc. In some embodiments, the probe 120 can be configured to receive radiation reflected from the surface of the substrate. In some embodiments, the probe 120 is configured to receive radiation transmitted through the substrate. In some embodiments, the probe 120 is configured to receive radiation emitted by the substrate. In some embodiments, the probe 120 can include an array of devices, such as devices with different (overlapping, non-overlapping, etc.) fields of view, devices with different functions (e.g., devices that receive radiation in different parts of the electromagnetic spectrum), devices configured to receive reflected, emitted, or transmitted light, etc.

[0049] In some embodiments, the probe 120 can be configured to receive radiation from the substrate 110 while the substrate 110 is being transferred from a first portion of the processing system 100 to a second portion of the processing system 100. For example, the probe 120 can be positioned so that the field of view of the probe 120 can intersect a path through which the transfer arm 113 can transfer the substrate 110. The probe 120 can receive radiation from the substrate 110 while the substrate 110 is being transferred from the transfer chamber 114 to the processing chamber 103. The probe 120 can receive radiation from the substrate 110 while the substrate 110 is being transferred from the processing chamber 103 to the transfer chamber 114.

[0050] In some embodiments, the light received by the probe 120 can be directed to the spectrometer 125 for analysis. The light received by the probe 120 can be focused into a fiber optic cable coupled to the spectrometer 125 for analysis (e.g., spectral analysis). The spectrometer 125 can perform operations (e.g., the spectrometer 125 can include or be coupled to a processing device) to determine one or more spectra of light that can be used to determine at least one optical property of the substrate. In some embodiments, light from the substrate will be received before the substrate is processed. In some embodiments, light from the substrate will be received after the substrate is processed. In some embodiments, light from the substrate will be received between processing operations. The probe 120 and the spectrometer 125 can include an optical sensor associated with the processing chamber 103, with the transfer chamber 114, with the processing system 100, etc. The probe 120 and the spectrometer 125 can include a metrology system to be operated in a controlled environment. The probe 120 and the spectrometer 125 can include an in-vacuum metrology system. The optical sensor can detect at least one property of the material of the substrate 110. In some embodiments, an optical sensor can provide sensor data indicative of the thickness of a material of substrate 110 by thin film optical calculations performed by a processing device (e.g., processing device 130). For example, an optical sensor can be used to determine the thickness of a film most recently applied to substrate 110, a film most recently exposed by substrate 110 (e.g., after an etching operation), and the like. An optical sensor can be used to determine the overall thickness of a substrate. An optical sensor can be used to determine additional characteristics of a substrate. An optical sensor can be used to determine the geometry of a substrate (e.g., a measurement of one or more dimensions of a substrate). An optical sensor can be used to determine the chemical or physical composition of a substrate or a portion of a substrate. An optical sensor can be used to classify, analyze, and / or characterize a pattern of a patterned substrate.

[0051] In some embodiments, the processing system 100 can further include an electromagnetic radiation source, such as optically coupled to the probe 120 (e.g., the probe 120 is configured to receive radiation generated by the source). In some embodiments, light received by the probe 120 can be reflected from the substrate 110. In some embodiments, radiation can be provided to the substrate 110 from a location proximate to the probe 120, from a core bundled with an optical fiber line of the probe 120, from the same side of the substrate 110 as the probe 120 (e.g., top side, bottom side, etc.), etc. The radiation can be provided to the substrate 110 by a radiation coupling device that is embedded in a wall of the chamber, supported by a bottom wall of the chamber (e.g., bottom wall 139), suspended from a top wall of the chamber, etc. The light received by the probe 120 can be transmitted through the substrate 110. The radiation can be provided to the substrate 110 from a location disposed opposite to the probe 120 (e.g., relative to the substrate 110). For example, the probe 120 can be suspended from and / or near a top wall of the processing system 100, and radiation can be provided from near the bottom wall 139. In some embodiments, the system can include multiple probes, can include one or more arrays of probes, can include probes disposed above and / or below a substrate, etc.

[0052] The controller 109 (e.g., a tool and equipment controller) can control various aspects of the processing system 100, such as the gas pressure in the processing chamber 103, the individual gas flows, the spatial flow ratio, the temperature of various chamber components, and the radio frequency (RF) or electrical state of the processing chamber 103. The controller 109 can receive signals from the factory interface robot 121, the transfer chamber robot 101, one or more sensors, and / or other processing components of the processing system 100, and send commands to them. The controller 109 can thus control the start and stop of processing, can adjust the deposition rate, the type or mix of deposition composition, etc. The controller 109 can further receive and process sensory data from various sensors (e.g., sensors associated with the processing system 100).

[0053] In various embodiments, the controller 109 includes (or is coupled to) a processing device 130 and is coupled to the spectrometer 125. The processing device 130 can be configured to receive and process sensor data, including the results of the spectral analysis performed by the spectrometer 125. The processing device 130 can be configured to accept multiple measurements and perform signal processing, for example, configured to isolate the effects of the thin film (e.g., from the optical effects of plasma generation) by receiving data collected with and without an external light source. The processing device 130 can calculate a spectral signal (e.g., indicating one or more characteristics of the substrate 110) by subtracting the second measurement result from the first measurement result (e.g., subtracting the second spectrum from the first spectrum). The processing device 130 can then fit the reflectance measurement signal to a thin film optical model to determine information including one or more optical thin film properties of the treated film layer. Based on the thin film optical model, the processing device 130 can determine one or more characteristics of the treated product included in the substrate 110. The characteristics can be calculated by the processing device 130, including thickness, reflectivity, chemical characteristics, etc. Depending on the results of analyzing the one or more optical film properties, the processing device 130 (e.g., the controller 109) can perform one or more actions. For example, the processing device 130 can direct the processing chamber 103 to make processing changes or adjustments. For example, the controller 109 can adjust processing parameters or settings such as deposition rate, type or mix of deposition compositions, timing of performing cleaning processes within the processing chamber, and reference 7A to 7C Other actions discussed in more detail. Additionally, in some embodiments, the controller 109 can cause calibration of one or more sensors of the processing chamber 103 based on the results of analyzing one or more optical film properties, can perform chamber matching based on the results of analyzing one or more optical film properties, identify chamber drift based on the results of analyzing one or more optical film properties, and the like.

[0054] In some embodiments, the processing device 130 may perform an analysis that is not intended to determine one or more properties of the substrate 110. The processing device 130 may receive spectral data from the spectrometer 125 and utilize the spectral data to determine one or more indications of the performance of the processing system 100 (e.g., the quality of the performance, the quality of the processing, etc.). In some embodiments, the processing device 130 may provide data from the spectrometer 125 (e.g., spectral data, processed spectral data, input vectors based on the spectral data, etc.) to a trained machine learning model. The trained machine learning model may be configured to generate as output one or more indications of processing conditions associated with the substrate (e.g., processing conditions under which the substrate is processed). The trained machine learning model may be configured to generate as output one or more corrective actions associated with the processing system 100 (e.g., indications of corrective actions, causing the performance of corrective actions, etc.). Corrective actions may include updating process recipes, updating non-process recipes (e.g., updating cleaning recipes, updating seasoning recipes, updating calibration recipes, updating identification recipes, etc.), updating equipment constants, planning preventive maintenance (e.g., cleaning, calibration, parts replacement, etc.), planning corrective maintenance, providing alerts to users, etc.

[0055] The controller 109 and / or the processing device 130 may be and / or include a computing device, such as a personal computer, a server computer, a programmable logic controller (PLC), a microcontroller, etc. The controller 109 and / or the processing device 130 may include (or be) one or more processing devices, which may be general-purpose processing devices, such as a microprocessor, a central processing unit, etc. More specifically, the processing device may 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 processor that implements a combination of instruction sets. The processing device may 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 controller 109 and / or the processing device 130 may include a data storage device (e.g., one or more disks and / or solid-state drives), a main memory, a static memory, a network interface, and / or other components. The processing device 130 may execute instructions to perform any one or more of the methods and / or embodiments described herein. The instructions may be stored on a computer-readable storage medium, which may include a main memory, a static memory, an auxiliary storage device, and / or a processing device (during the execution of the instructions).

[0056] Figure 2 2 shows a simplified side view of a substrate processing system 200 including an electromagnetic radiation probe 202 according to some embodiments. The substrate processing system includes a transfer chamber 204 and a processing chamber 206 (eg, Figure 1 The transfer chamber 114 and the processing chamber 103 are shown in FIG. 2 . The transfer chamber 114 may include a transfer robot 208. The transfer robot 208 may be configured to transfer one or more substrates within the transfer chamber 204, between the transfer chamber 204 and the processing chamber 206, between the processing chamber 206 and another chamber (not shown) of the processing system 200, etc.

[0057] The transfer robot 208 may be coupled to or include a robotic arm 212. The robotic arm 212 may be configured to support the substrate 210, transfer the substrate 210 between portions of the substrate processing system 200, etc. The robotic arm 212 may include a support and / or an end effector, as will be described in more detail in conjunction with FIG.

[0058] The transfer robot 208 may be configured to extend (eg Figure 2 204) to transport the substrate 210 from the transfer chamber 204 to the processing chamber 206. One or more portions of the substrate 210 may pass through the field of view 214 of the probe 202. In some embodiments, the probe 202 may be disposed near an interface between chambers of the substrate processing system 200, for example, near a slit valve 216 (e.g., Figure 1 In some embodiments (e.g., embodiments including those in which the probe 202 is disposed near an interface between chambers of the substrate processing system 200), a portion of the substrate 210 may be within the field of view 214 (e.g., Figure 2 ). In some embodiments, the probe 202 is disposed at a height higher than the height of the slit valve, and the field of view 214 of the probe 202 is directed downward. Alternatively, the probe 202 can be disposed at a height below the height of the slit valve, and the field of view 214 of the probe 202 can be directed upward. In some embodiments, the probe 202 can be placed in different ways, for example, it can be configured so that a portion of the substrate 210 is in the field of view 214 while the substrate 210 is in the transfer chamber 204; so that a portion of the substrate 210 is in the field of view 214 while the substrate 210 is in the processing chamber 206, and so on.

[0059] In some embodiments, the probe 202 can be coupled to other components associated with performing metrology, taking measurements of a substrate, etc. In some embodiments, the probe 202 can include a detector (e.g., an electromagnetic radiation detector). In some embodiments, the probe 202 can include a radiation collection device. In some embodiments, the probe 202 can be coupled to a spectrometer, for example, the probe 202 can be coupled to a fiber optic cable that can direct radiation received by the probe 202 from the substrate 210 to the spectrometer. In some embodiments, the probe 202 can be coupled to a detector. In some embodiments, one or more detectors associated with the probe 202 can be communicatively coupled to a processing device.

[0060] In some embodiments, the probe 202 can receive radiation emitted by the substrate 210. For example, the probe 202 can receive infrared radiation emitted by the substrate 210. A processing device associated with the probe 202 can determine one or more properties of the substrate 210 based on the radiation emitted by the substrate 210. The processing device can determine the temperature of the substrate 210 based on the emitted radiation, the chemical composition of the substrate 210, etc. In some embodiments, the probe 202 can include part of a pyrometer system.

[0061] In some embodiments, the probe 202 may be configured to receive light reflected by the substrate 210. The substrate processing system 200 may include an electromagnetic radiation source configured to illuminate at least a portion of the substrate 210. In some embodiments, the illumination of the substrate 210 may be performed from above, for example, so that the reflected radiation can be collected by the probe 202. In some embodiments, the illumination may be broadband, for example, it may be provided by a white light source. In some embodiments, the illumination may be narrowband, for example, a limited wavelength range may be provided to the substrate 210. In some embodiments, the illumination may be pulsed. A spectrometer associated with the probe 202 may operate in a pulsed mode, which may correspond to the pulsed mode of the illumination source (e.g., it may be synchronized in time). The illumination source may be a pulsed flash lamp, such as a xenon flash lamp. In some embodiments, the illumination may be provided via a component of the probe 202, for example, the probe 202 may include two optical fiber cores, one for providing radiation from the radiation source to the substrate 210, and another for receiving radiation reflected from the substrate 210 and providing the reflected radiation to an associated spectrometer.

[0062] In some embodiments, the radiation used to illuminate the substrate 210 can be collimated or substantially collimated. Collimated illumination can be substantially insensitive to the distance of the substrate from the probe. In some embodiments, the radiation used to illuminate the substrate 210 can be focused (e.g., converging). Converging illumination can cause the metrology system to be substantially insensitive to substrate angle (e.g., the angle of the surface of the substrate relative to the optical axis of the metrology system). In some embodiments, the radiation used to illuminate the substrate 210 can be divergent. In some embodiments, the collected radiation (e.g., spectral data) can be compared to a reference (e.g., a known silicon substrate reference). The comparison with the reference substrate can be used for background removal, calibration, etc.

[0063] In some embodiments, differences in substrate placement can be compensated. For example, additional equipment can be included to perform measurements of the surface angle of substrate 210. Data indicating the angle at which the substrate is placed, the angle of a portion of the substrate (e.g., due to bending or warping), etc. can be provided to the processing device for use in correcting conclusions drawn from the in-chamber metrology system.

[0064] In some embodiments, the probe 202 can be configured to receive light transmitted by the substrate 210. The electromagnetic radiation source can be disposed on an opposite side of the probe 202 (relative to the substrate 210), e.g., below a path taken by the substrate 210. The radiation can pass through the substrate 210 (e.g., through one or more openings in the bottom of the robotic arm 212) to be collected by the probe 202.

[0065] In some embodiments, the probe 202 can be one of a probe array for collecting electromagnetic radiation from the substrate 210. In some embodiments, multiple similar probes can be provided in the substrate processing system 200. For example, multiple probes can be arranged so that different portions of the substrate 210 are captured by the field of view of the probe. This can produce a more complete map of substrate properties, can improve noise reduction and / or reduce errors in conclusions or analyses based on data from the probe, etc. In some embodiments, probes that measure different quantities can be utilized. For example, a probe configured to operate in a combination of emission, reflection, and transmission modes can be included in the substrate processing system 200. In some embodiments, multiple probes operating in different wavelength regions (e.g., for different portions of the electromagnetic spectrum) can be included.

[0066] In some embodiments, the substrate processing system 200 may further include a component configured to detect the presence and / or position of the substrate 210. For example, the radiation source may be activated when the substrate enters the field of view 214 (e.g., the object detection system may provide an indication that the substrate has entered the field of view 214, for example, by overlapping the field of view with the field of view of the field of view 214, by causing the substrate 210 to enter the field of view 214 earlier and providing a delayed signal indicating the activation of the radiation source, etc.), the spectrometer may be activated when the substrate enters the field of view 214, etc. In some embodiments, the object detection component may facilitate synchronization of the operation of the spectrometer and the operation of the robot, for example, the pulsed light source may be synchronized (e.g., using the object detection system to cooperate with the control system of the robot 208 to determine the movement speed of the substrate 210) to enable data to be collected from a target portion of the substrate 210 (e.g., a portion near the outer edge, a portion at a given distance from the outer edge, etc.). In some embodiments, data points may be acquired at several intervals as the substrate 210 passes through the field of view 214. In some embodiments, pulses of the pulsed radiation source may correspond to the data points. In some embodiments, the integration time of a system utilizing a continuous radiation source (along with the robot speed) can define the size of the region of the substrate 210 that corresponds to a data point.

[0067] In some embodiments, the robotic arm 212 may deviate from a straight path as the robotic arm 212 is extended. For example, as the robotic arm 212 is extended from a position where the first portion (e.g., leading edge) of the substrate 210 enters the field of view 214 to a position where the last portion (e.g., trailing edge) of the substrate 210 leaves the field of view 214, the placement and / or orientation of the substrate 210 relative to the probe 202 may change. In some embodiments, the distance between the substrate 210 and the probe 202 may change as the robotic arm 212 is extended and / or retracted. In some embodiments, the angle between the substrate 210 (e.g., the angle of a ray perpendicular to the surface of the substrate 210) and the field of view 214 (e.g., a ray passing through the center of the field of view 214, the optical axis of the probe, etc.) may change as the robotic arm 212 is extended and / or retracted. In some embodiments, the distortion values ​​(e.g., angular droop of the robotic arm 212, vertical droop of the robotic arm 212) may be different during the extension and retraction operations. In some embodiments, the behavior of the robotic arm 212 during the extension / retraction operation may be repeatable, may be predictable, may be interpretable by one or more processing devices associated with performing measurements of a substrate in a controlled environment, and the like.

[0068] Figure 3A 3 is a schematic representation of a metrology system 300A including a probe array 304 according to some embodiments. The probe 302 is configured to receive a signal from a substrate 310 (e.g., Figure 1 In some embodiments, the probe array 304 receives electromagnetic radiation emitted by the substrate 310. In some embodiments, the probe array 304 receives radiation transmitted through the substrate 310. In some embodiments, the probe array 304 receives radiation reflected from the substrate 310. In some embodiments, the probe array 304 receives radiation reflected from the substrate 310. In some embodiments, the probes 302, 306, and 308 may constitute a probe array. Each probe may have an associated field of view (e.g., depicted by a dashed cone).

[0069] In some embodiments, each probe in probe array 304 can be substantially similar, e.g., can be configured to perform similar operations, can be configured to receive electromagnetic radiation within similar wavelength ranges, etc. In some embodiments, one or more probes can perform different functions. For example, probe 302 can be configured to receive radiation emitted within a first frequency range (e.g., receive infrared radiation to perform temperature measurements of a substrate, act as a pyrometer, etc.), probe 306 can be configured to receive radiation reflected within a second frequency range (e.g., receive radiation within a visible wavelength range provided by a source and reflected from one or more surfaces of substrate 310), and probe 308 can be configured to receive radiation transmitted within a third frequency range (e.g., receive radiation with a wavelength of approximately 1 μm provided by a source from an opposite side of substrate 310).

[0070] The substrate 310 may be provided by a support 312 (eg, including Figure 1 The support 312 may be coupled to a robotic arm, a transfer robot, or any mechanism configured to transfer the substrate 310 from one location (e.g., a first portion of a substrate processing system) to a second location (e.g., a second portion of a substrate processing system). The probe array 304 may be fixed (e.g., may be fastened to a wall of a substrate processing system) and may take measurements of the substrate 310 as the substrate 310 is being transferred (e.g., passing through a field of view of one or more probes of the probe array 304).

[0071] In some embodiments, a probe (e.g., probe 302) can receive radiation continuously. For example, a radiation source optically coupled to probe 302 can be a continuous source. In some embodiments, a detector, sensor, spectrometer, etc. associated with the probe can be configured to process radiation in a non-continuous manner. For example, the spectrometer can integrate data received over a period of time (e.g., when substrate 310 is moved by support 312), pause (e.g., separate a first area of ​​substrate 310 in the field of view of probe 302 from a second area of ​​substrate 310 during data integration), and then integrate over a period of time. In some embodiments, the processing system can include a pulsed source. For example, the processing system can include a pulsed flash lamp source. The probe (e.g., probe 302) can receive radiation from the source depending on the source that generates the radiation, for example, when substrate 310 moves through the field of view of probe 302, alternating areas of substrate 310 along a path across substrate 310 can be measured and not measured. In some embodiments, radiation received by the probe 302 when the source is not providing radiation can be used for correction, calibration, baseline operations, etc. associated with analysis of the received radiation.

[0072] Figure 3AAn exemplary data acquisition path / trajectory 314 is further depicted. In some embodiments, the transfer robot is configured to move the substrate 310 along one or more trajectories (e.g., straight trajectory segments, curved trajectory segments, etc.) to intersect one or more fields of view of the probe array 304. The path 314 depicts an area of ​​the substrate 310 from which the probe array 304 can receive radiation. The path 314 can, for example, be associated with transferring the substrate 310 from one location to another (e.g., between a transfer chamber and a processing chamber). The trajectory of the substrate 310 that results in measurements along the path 314 can be a normal part of the operation of the processing system, for example, data along the path 314 can be collected without affecting substrate processing time, without affecting system throughput, etc. Performing in-vacuum metrology can be throughput transparent. For example, data can be acquired along the path 314 while a robot arm supporting the substrate 310 is being extended or retracted. Data can be acquired along a path similar to the path 314 using a single probe, a probe array, multiple probe arrays (e.g., probes above and below the substrate 310), etc. Data related to radiation received from substrate 310 (e.g., spectral data, processing data, substrate property data, etc.) can be synchronized with the movement of support 312 (e.g., to generate a data map over a portion of the surface of substrate 310, to generate a property map over a portion of the surface of substrate 310, to extrapolate a property map over a larger portion of substrate 310 based on data associated with path 314, etc.). Additional components (e.g., object detection systems, object detection equipment, etc.) can be used to synchronize the movement of support 312 with the collection / analysis of data associated with probe 308 receiving radiation from substrate 310.

[0073] In some embodiments, the substrate 310 may be patterned, for example, a patterned wafer. The processing of data received from the patterned wafer may include additional operations. For example, the spectral data received from the patterned wafer may be compared with a database of such data. Data substantially similar to the data received from the wafer (e.g., spectra) may be used to characterize the substrate, characterize the pattern, etc. Binning of similar spectra, comparison of spectra, extraction of property values, etc. may be performed by a model (e.g., a physics-based model, a machine learning model, a statistical model, etc.).

[0074] Figure 3B326. FIG. 327 is a schematic bottom view (viewed from the bottom side) of a support 320 of a processing system 300B according to some embodiments. The support 320 can support a substrate 322. The support 320 can be coupled to a robot arm of a transfer robot of the processing system. The metrology system 300B can include metrology components 324 and 326. In some embodiments, one or more of the metrology components 324 and 326 can be a probe. One or more of the metrology components 324 and 326 can be a source, for example, can be configured to direct radiation to the substrate 322.

[0075] In some embodiments, when the substrate 322 is located on the support 320, a portion of the bottom of the substrate 322 (eg, the bottom surface of the substrate 322 supported by the support 320) may be optically accessible. Figure 3B As shown, the support 320 may allow a portion of the substrate 322 to be visible from the bottom (e.g., the support 320 may be configured to contact the substrate 322 along an outer edge of the substrate 322). The metrology system 300B may include components above and below a path that the substrate 322 travels (e.g., when transferred between chambers of the processing system). In some embodiments, one or both of the components 326 and 324 may represent arrays, such as a probe array and a radiation source array. In an exemplary embodiment, the component 324 may be configured to transmit light to the substrate 322, and the component 326 may be a probe configured to receive light transmitted through the substrate 322. In another exemplary embodiment, the component 324 may perform operations including supplying electromagnetic radiation to the substrate 322 and receiving radiation reflected from the substrate 322, and the component 326 may receive radiation emitted from the substrate 322 (e.g., to generate an indication of the temperature of the substrate 322).

[0076] In some embodiments, additional data can be collected from additional probes. For example, probes located above or below the plane of travel of the substrate can be used to detect the geometry of the substrate, such as the shape of the substrate, distortion of the substrate, etc. The data received from these probes can be used to correct or adjust the data received by other probes. For example, the probes can be used to measure the angle of the upper surface of the substrate, such as the angle relative to the illumination system used to perform the reflection measurement. The data generated by receiving the reflected light can be corrected corresponding to the measured angle of a portion of the upper surface of the substrate. Wafer shape, distortion, warping, bending, etc. can be corrected in a similar manner.

[0077] Figure 3C is a schematic representation of a metrology system 300C including a probe array 304 and a path 318 (eg, an acquisition trajectory) according to some embodiments. The metrology system 300C may be used with Figure 3AThe metrology system 300A of FIG. 300B shares one or more features, for example, the metrology system 300C includes an array of probes (e.g., probes 302 and 308) having associated fields of view, a substrate 310, a support 312, etc. In some embodiments, the transfer robot is configured to move the substrate 310 along one or more trajectories (e.g., straight trajectory segments, curved trajectory segments, etc.) to intersect one or more fields of view of the probe array 304.

[0078] Path 318 includes multiple trajectories. The trajectory of path 318 can be straight (as shown), curved, have various or uniform lengths, etc. The robotic arm can be configured to move substrate 310 along a path that is not limited to bringing substrate 310 closer to a destination, for example, the robotic arm can be extended and retracted multiple times, repeatedly extended and retracted along the same path, or extended and retracted along two or more different (e.g., parallel) paths. In some embodiments, the robotic arm moves laterally between extensions / retractions, for example, to provide a larger area of ​​substrate 310 to one or more fields of view of the probes of probe array 304. In some embodiments, the robotic arm does not move laterally between extensions / retractions, for example, to provide more data (e.g., repeated measurements) of a first area of ​​substrate 310, to provide more statistical certainty, to fill gaps (e.g., gaps caused by integration windows, pulse sources, etc.), etc.

[0079] Figure 3D is a schematic representation of a metrology system 300D including a probe array 304 and an acquisition track 316 according to some embodiments. The metrology system 300D can be used with Figure 3A The metrology system 300A shares one or more features with the metrology system 300D, for example, including the probes 302 and 306 , the substrate 310 , the support 312 , etc. The transfer robot may be configured to move the substrate 310 along a trajectory, illustrated as the acquisition trajectory 316 .

[0080] The acquisition trajectory 316 includes multiple trajectories, such as multiple segments of a path along which a robotic arm moves a substrate, multiple segments of a path traced by a field of view on the surface of the substrate 310, and the like. The trajectory can be straight (as shown), curved, have varying or uniform lengths, and the like. In some embodiments, an indirect path (e.g., a path that does not efficiently move the substrate 310 to a destination) can be used. If the field of view of the probe array 304 is arranged in a pattern similar to the acquisition trajectory 316 (e.g., different from a straight path (e.g., Figure 3A314) intersects substrate 310, then a probe (e.g., a probe of probe array 304) may receive radiation from a greater portion of substrate 310. Radiation may be received by a probe, a probe array, multiple probe arrays, etc. along one or more acquisition trajectories (e.g., trajectories including paths / trajectories 314, 316, 318, etc.).

[0081] Figure 4 is a block diagram illustrating an exemplary system architecture 400 in which embodiments of the present disclosure may operate. Figure 4 As shown, system architecture 400 includes manufacturing system 402, metrology system 410, client device 450, data storage device 440, server 420, and modeling system 470. Metrology system 410 may include in-system tools 415 (e.g., metrology tools disposed in an area where one or more chambers of the manufacturing system provide a controlled environment, a vacuum environment, etc.). In some embodiments, metrology system 410 may include metrology tools 414, which may include components, probes, spectrometers, radiation sources, etc., such as in combination Figure 1 3. Modeling system 470 may be part of server 420. In some embodiments, one or more components of modeling system 470 may be fully or partially integrated into client device 450. Manufacturing system 402, metrology system 410, client device 450, data storage device 440, server 420, and modeling system 470 may each be hosted by one or more computing devices, including a server computer, a desktop computer, a laptop computer, a tablet computer, a notebook computer, a personal digital assistant (PDA), a mobile communication device, a cellular phone, a handheld computer, or a similar computing device.

[0082] The manufacturing system 402, the metrology system 410, the client device 450, the data storage device 440, the server 420, and the modeling system 470 can be coupled to each other via a network 460 (e.g., for performing the methods described herein). In some embodiments, the network 460 is a dedicated network that provides each element of the system architecture 400 with access to each other and other dedicated computing devices. The network 460 may 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, and / or any combination thereof. In some embodiments, processing and / or data storage operations may be performed by remote cloud-based devices, virtual devices, etc., and the network 460 may enable access to and communication with these devices. Alternatively or additionally, any of the elements of system architecture 400 may be integrated together or otherwise coupled without the use of network 460 .

[0083] The client device 450 may be or include any personal computer (PC), laptop computer, mobile phone, tablet computer, netbook computer, networked television (“Smart TV”), networked media player (e.g., Blu-ray player), set-top box, over-the-top (OOT) streaming device, operator box, etc. The client device 450 may include a browser 452, an application 454, and / or other tools described and executed by other systems of the system architecture 400. In some embodiments, the client device 450 can be able to access the manufacturing system 402, the metrology system 410, the data storage device 440, the server 420 and / or the modeling system 470, and transmit (e.g., send and / or receive) sensor data, processed data, data classification, processing result data, processing update data and / or indications of inputs and outputs of various processing tools (e.g., the metrology tool 414, the data preparation tool 416, the chamber matching tool 422, the sensor matching tool 424, the recipe development tool 426, the process control tool 428 and / or the prediction component 494) at various stages of processing of the system architecture 400, as described herein.

[0084] like Figure 4As shown, the manufacturing system 402 includes a processing tool 404, a process flow 406, and a process controller 408. The process controller 408 can coordinate the operation of the processing tool 404 to perform one or more process flows 406. For example, the various processing tools 404 can include dedicated chambers, such as etching chambers, deposition chambers (including chambers for atomic layer deposition, chemical vapor deposition, or plasma-enhanced versions thereof), annealing chambers, etc. In another example, the machine can incorporate a sample transport system (e.g., a selective compliance assembly robot arm (SCARA) robot, a transfer chamber, a front opening pod (FOUP), a side storage pod (SSP), etc.) to transport samples between the machine and the processing operation.

[0085] In some embodiments, one or more of the metrology tools 414 can be utilized when a substrate is transported between machines, between processing operations, into or out of the manufacturing system 402, etc. For example, a radiation source of the metrology tool 414 can provide electromagnetic radiation to be directed to a substrate being transferred from a transfer chamber to a processing chamber of the manufacturing system 402. The radiation source can be coupled to a component of the in-system tool 415 that directs the radiation to the substrate. A probe of the in-system tool 415 can receive radiation reflected from the substrate and provide the radiation to a spectrometer of the metrology system 410 for further analysis.

[0086] The process flow 406, or sometimes referred to as a process recipe, process operation, or process operation, can include various specifications for operations performed by the process tool 404. For example, the process flow 406 can include process specifications such as the start duration of the process operation, the process tool used for the operation, the temperature, flow rate, pressure, etc. of the machine (e.g., chamber), the order of deposition, etc. In another example, the process flow can include transport instructions for transporting a sample to another process operation or transporting a sample measured by the metrology system 410. One or more process flows 406 include preventive maintenance processes and cleaning processes.

[0087] The process controller 408 may include a device designed to manage and / or coordinate the actions of the process tool 404. In some embodiments, the process controller 408 is associated with a process recipe or a series of process flow instructions that, when applied in a designed manner, produces a desired process result for substrate processing. For example, a process recipe may be associated with processing a substrate to produce a target process result (e.g., critical dimension, thickness, uniformity standard, etc.). The process controller 408 may coordinate the execution of preventive maintenance processes (e.g., chamber cleaning), chamber recovery processes (e.g., chamber aging), etc. to return a chamber to a production state, and / or update process operations associated with the process chamber. In addition, the process controller 408 may cause updates to the calibration of sensors associated with the process tool 404 or the metrology system 410.

[0088] like Figure 4 As shown, metrology system 410 includes metrology tool 414 and data preparation tool 416. Metrology tool 414 can include various sensors to measure process results (e.g., critical dimensions, thickness, uniformity, etc.) and detect parameters within manufacturing system 402. In some embodiments, metrology tool 414 includes one or more components for generating, directing and / or receiving electromagnetic radiation, such as Figure 2As described in FIG. 3 . In some embodiments, the metrology tool 414 includes sensors to measure one or more properties of a substrate in a processing system (e.g., a manufacturing system). The metrology tool 414 may include tools for performing online metrology, integrated metrology, independent metrology, vacuum metrology, etc. The metrology tool 414 may include multiple sensors to detect environmental conditions of a processing chamber. For example, sensors disposed in one or more processing chambers may be used to measure conditions within the processing chambers, such as temperature, pressure, vacuum conditions, deposited layer thickness, etc. In another example, a metrology tool disposed in a processing chamber (e.g., a probe that may be coupled to one or more spectrometers) may be used to measure one or more properties of a substrate of the manufacturing system 402. In some embodiments, one or more sensors of the system 400 (e.g., sensors of the in-system tool 415) may be used to collect measurements from a substrate (e.g., spectral data, data from reflected, transmitted, or emitted radiation, etc.) while the substrate is being transported by a robot of the manufacturing system. In some embodiments, one or more sensors of the system 400 may be used to determine chemical properties (e.g., chemical composition) of a substrate, a layer of a substrate, etc. In some embodiments, one or more sensors of the system 400 may be used to determine processing conditions associated with a substrate for recommending corrective actions associated with the metrology system 410 and / or the manufacturing system 402, etc. In some embodiments, the sensors of the system 400 may be used to determine the thickness of a substrate. In some embodiments, a metrology tool may be used to measure the thickness of a process product deposited on a surface of a substrate. The metrology tool 414 may also include a device for measuring a process result of a substrate processed using the manufacturing system. For example, a process result of a processed substrate, such as a critical dimension, a thickness measurement result (e.g., a film layer from etching, deposition, etc.), may be evaluated based on a process recipe and / or actions performed by the process controller 408. In another example, various sensors may measure the conditions of a chamber during a processing operation.

[0089] The data preparation tool 416 may include a process for extracting features and / or generating synthetic / engineered data associated with the data measured by the metrology tool 414. In some embodiments, the data preparation tool 416 may identify correlations, patterns, and / or anomalies in metrology and / or process performance data. For example, the data preparation tool 416 may perform feature extraction, wherein the data preparation tool 416 uses a combination of measurement data to determine whether a criterion is met. For example, the data preparation tool 416 may analyze multiple data points of associated parameters (e.g., temperature, pressure, deposited layer thickness, vacuum conditions, plasma conditions, process product thickness, spectral data of various radiation wavelengths, etc.) to determine whether rapid changes occur during iterations of processing operations. In some embodiments, the data preparation tool 416 performs normalization on various sensor data associated with various processing chamber conditions. Normalization may include processing incoming sensor data so that it appears similar between the various chambers and sensors used to acquire the data. The data preparation tool 415 may prepare data to be supplied to another component (e.g., model 490) for further processing.

[0090] In some embodiments, the data preparation tool 416 can perform one or more of a process control analysis, a univariate limit violation analysis, or a multivariate limit violation analysis on the metrology data (e.g., metrology data obtained by the metrology tool 414). For example, the data preparation tool 416 can perform statistical process control (SPC) by employing statistical-based methods to monitor and control the process controller 408. For example, SPC can improve the efficiency and accuracy of process operations (e.g., by identifying data points that fall within and / or exceed control limits).

[0091] In some embodiments, the performance (e.g., performance quality) of one or more processing chambers can be measured throughout a process flow (e.g., a recipe for processing a substrate). For example, a characteristic (e.g., thickness) of a process product deposited on a substrate in a processing chamber during a process operation (e.g., during a process recipe operation, during a cleaning operation, etc.) can be measured. For example, a substrate can be processed in multiple chambers. A substrate can enter a processing chamber and be measured by one or more probes as it is transferred into the processing chamber (e.g., by an in-system tool 415, by a Figure 1Spectrometer 125, etc.). The substrate may undergo processing in the chamber, such as a deposition process, an etching process, etc. The substrate may then be removed from the processing chamber and measured again by one or more probes while the substrate is being transferred out of the processing chamber. In some embodiments, an incremental amount of metrology data is acquired during / between predetermined processing operations. For example, additional sensors may be activated immediately after processing a wafer and / or currently activated sensors may acquire additional data. In some embodiments, the process controller 408 may trigger measurements performed by the metrology tool 414 based on operations to be performed by the process tool 404. For example, the process controller 408 may trigger activation of one or more sensors and / or one or more radiation sources (e.g., of the metrology tool 414) in response to updates associated with the process (e.g., completion of a processing operation, transfer of a substrate from one location in the processing system to another, etc.).

[0092] In some embodiments, the extracted features, the generated synthetic / engineered data, and the statistical analysis can be used in association with the modeling system 470 (e.g., to train, validate, and / or test the model 490). Additionally and / or alternatively, the data preparation tool 416 can output the data to the server 420 for use by any of the chamber matching tool 422, the sensor matching tool 424, the recipe development tool 426, and / or the process control tool 428.

[0093] The data storage device 440 can be a memory (e.g., random access memory), a drive (e.g., a hard drive, a flash drive), a database system, or another type of component or device capable of storing data. The data storage device 440 can store one or more historical data 442, including historical sensor data 444, historical metrology data 446, and / or historical chamber parameter data 447 of previous chamber conditions, and processing results of substrates processed under associated chamber conditions. In some embodiments, the historical data 442 can be provided to train the model 490. The sensor data can be provided to the trained model 490 to obtain an output. In some embodiments, the historical sensor data 444 includes historical data from the metrology system 410, for example, spectral data generated based on radiation received by the probe from the substrate. The historical sensor data 444 can include spectral data indicating the thickness of a layer deposited on the substrate. The historical sensor data 444 can indicate another characteristic of the substrate, processing conditions of the substrate, etc.

[0094] In some embodiments, the historical chamber parameter data 447 may include historical updates to one or more processing operations associated with the processing chamber. For example, the historical chamber update data 447 may include historical updates to one or more processing operations associated with the processing chamber (e.g., cleaning recipe updates, etching recipe updates, deposition recipe updates, etc.) made based on the historical sensor data 444. In some embodiments, the historical chamber parameter data 447 may be mapped to the historical sensor data 444, the historical metrology data 446, etc. In some embodiments, the historical data 442 may be used to train, validate, and / or test the model 490 of the modeling system 470 (see, e.g., Figure 6 for exemplary methods).

[0095] The server 420 may include one or more computing devices, such as a rack server, a router computer, a server computer, a personal computer, a mainframe computer, a laptop computer, a tablet computer, a desktop computer, etc. The server 420 may include a chamber matching tool 422 , a sensor matching tool 424 , a recipe development tool 426 , and a process control tool 428 .

[0096] Each of the chamber match tool 422, the sensor match tool 424, the recipe development tool 426, and the process control tool 428 can receive data from the data preparation tool 416. Each of the chamber match tool 422, the sensor match tool 424, the recipe development tool 426, and the process control tool 428 can receive data from the model 490. Each component of the server 420 can receive data from the prediction component 494.

[0097] In some embodiments, each of the chamber match tool 422, the sensor match tool 424, the recipe development tool 426, and the process control tool 428 receives chamber data from the process tool 404 and / or processed data output from the data preparation tool 416. In some embodiments, the data preparation tool 416 receives raw sensor data from the metrology tool 414. The raw sensor data can be combined with synthetic data designed from the data preparation tool 416. Each of the chamber match tool 422, the sensor match tool 424, the recipe development tool 426, and the process control tool 428 can generate updates to one or more process flows 406 and / or can generate reports / notifications indicating chamber matching, chamber drift, anomalies, etc.

[0098] In an example, the chamber match tool 422 may determine updates to the process operations of the first process chamber based on the received data so that the process operations performed on the first process chamber more closely match corresponding process operations performed on the second process chamber.

[0099] In another example, the sensor matching tool 424 can determine a calibration of one or more sensors associated with the process chamber based on the received numerical data. Additionally, the sensor matching tool 424 can determine a sensor calibration that accounts for sensor drift based on the received numerical data.

[0100] In another example, the recipe development tool 426 can determine updates to the process recipe based on the received data. In particular, the recipe development tool 426 can determine updates to one or more process parameters (e.g., run time, cleaning time, process knobs, etc.) to optimize the process recipe (e.g., process operation) based on the received data. In one embodiment, the recipe development tool 426 determines updates to a cleaning recipe that is periodically executed to clean the process chamber based on the received data.

[0101] As an additional example, the process control tool 428 may determine an update to an endpoint of a process operation (eg, an endpoint of a chamber cleaning operation) based on the received data.

[0102] Updates to the process flow may change the manner in which the process tool 404 implements the process flow 406. For example, the updates may include increasing or decreasing the processing time of one or more process operations of the process flow 406. For example, the updates may increase or decrease the duration of a chamber cleaning operation. In some embodiments, each of the chamber matching tool 422, the sensor matching tool 424, the recipe development tool 426, and the process control tool 428 may use a model (e.g., a model of the modeling system 470) that receives input data (such as chamber data from the process tool 404, the metrology tool 414 including the in-system tool 415, and / or processed data output from the data preparation tool 416) and outputs one or more updates to the process flow 406. The model 490 may be a machine learning model and may include a bootstrap aggregation model, a random forest decision tree model, a partial least squares regression (PLS) model, a least absolute shrinkage and selection operator (LASSO) regression model, and / or a ridge regression model, among other models. The model may include modeling that combines multiple models (e.g., stacked modeling) and utilizes a higher confidence model to finally classify the received data. The model may be an unsupervised model, a semi-supervised model, or a supervised model. In addition, the model may include a linear model, a dynamic model, a digital model, a mechanical model, a statistical model, a physics-based model, a digital twin model, and the like.

[0103] In some embodiments, one or more of the chamber match tool 422, the sensor match tool 424, the recipe development tool 426, and / or the process control tool 428 can use a machine learning model to perform their described methods. In some embodiments, one or more of the chamber match tool 422, the sensor match tool 424, the recipe development tool 426, and / or the process control tool 428 can use a traditional model and / or a physics-based model (e.g., a digital twin) to perform their described methods. A modeling system 470 can be used to generate (e.g., train, validate, and / or test) the associated models.

[0104] In some embodiments, modeling system 470 may include server machine 472 and server machine 480. Server machine 472 includes a dataset generator 474 that can generate one or more datasets (e.g., data input sets and target output sets) to train, validate, and / or test model 190. Some operations of dataset generator 474 are combined with Figure 5 and Fig. 7A Detailed description. In some embodiments, the data set generator 172 can divide the historical data (e.g., historical sensor data 444, historical metrology data 446, chamber parameter data 447, etc.) into a training set (e.g., sixty percent of the data), a validation set (e.g., twenty percent of the data), and a test set (e.g., twenty percent of the data). In some embodiments, the modeling system 470 (e.g., via the prediction component 494) generates multiple attribute sets (e.g., feature vectors, vectors, etc.). For example, a first attribute set can correspond to a first group of sensor data (e.g., from a first group of sensors, a first combination of values ​​from the first group of sensors, a first pattern in the values ​​from the first group of sensors), the first group of sensor data corresponding to each data set in the data set (e.g., a training set, a validation set, and a test set), and a second attribute set can correspond to a second group of sensor data (e.g., from a second group of sensors different from the first group of sensors, a second combination of values ​​different from the first combination, a second pattern different from the first pattern), the second group of sensor data corresponding to each data set in the data set.

[0105] In some embodiments, the server machine 480 includes a training engine 482, a verification engine 484, a selection engine, and / or a test engine 486. An engine (e.g., a training engine 482, a verification engine 484, a test engine 486) may refer to hardware (e.g., a circuit system, a dedicated logic, a programmable logic, a microcode, a processing device, etc.), software (such as instructions running on a processing device, a general-purpose computer system, or a dedicated machine), firmware, microcode, or a combination thereof. The training engine 482 may generate a plurality of trained models 490. Each of the plurality of trained models may correspond to a different set of attributes of a training set (e.g., sensor data from a different sensor group). For example, a first trained machine learning model may have been trained using all attributes (e.g., X1 to X5), a second trained machine learning model may have been trained using a first subset of attributes (e.g., X1, X2, X4), and a third trained machine learning model may have been trained using a second subset of attributes (e.g., X1, X3, X4, and X5) that may partially overlap with the first subset of attributes. The data set generator 474 can receive the output of the trained model (e.g., 490) and collect the data into a training data set, a validation data set, and a test data set, and use these data sets to train a second model. Some or all of the operations of the server machine 480 can be used to train various types of models, including physics-based models, supervised machine learning models, unsupervised machine learning models, etc.

[0106] The validation engine 484 may be capable of validating the trained models 490 using the corresponding feature set of the validation set from the dataset generator 474. For example, the first attribute set of the validation set may be used to validate the first trained model 490 trained using the first attribute set of the training set. The validation engine 484 may determine the accuracy of each of the trained models 490 based on the corresponding feature set of the validation set. The validation engine 484 may discard the trained models 490 having an accuracy that does not meet the threshold accuracy. In some embodiments, the selection engine (not shown) may be capable of selecting one or more trained models 490 having an accuracy that meets the threshold accuracy. In some embodiments, the selection engine may be capable of selecting the trained model 490 having the highest accuracy among the trained models 490.

[0107] The testing engine 486 may be able to test the trained model 490 using a corresponding attribute set of the test set from the data set generator 474. For example, a first trained model 490 trained using a first attribute set of the training set may be tested using a first attribute set of the test set. The testing engine 486 may determine the trained model 490 having the highest accuracy among all trained models based on the test set.

[0108] Model 490 can refer to a machine learning model, which can be a model artifact generated by training engine 482 using a training set including data inputs and corresponding target outputs (correct answers for the corresponding training inputs). Model 490 can additionally or alternatively refer to a statistical model or a physics-based model. Patterns in the data set that map the data inputs to the target outputs (correct answers) can be found, and a mapping that captures these patterns is provided to model 490. In some embodiments, model 490 can predict properties of a substrate. In some embodiments, model 490 can predict failure modes of manufacturing chamber components.

[0109] 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 with a classifier or regression layer that maps features to a desired output space. Convolutional neural networks (CNNs) are such as multi-layer convolution filters. Pooling is performed at lower layers and nonlinear problems can be solved, and multi-layer perceptrons are usually attached to the top of these lower layers, so that the top features extracted by the convolutional layers are mapped to decisions (e.g., classification outputs).

[0110] Recurrent neural network (RNN) is another type of machine learning model. Recurrent neural network models are designed to interpret a series of inputs, where these inputs are inherently related to each other, such as time trajectory data, sequential data, etc. The output of the perceptron of the RNN is fed back into the perceptron as input to produce the next output.

[0111] Deep learning describes a class of machine learning algorithms that use a cascade of multiple layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. Deep neural networks can learn in a supervised (e.g., classification) and / or unsupervised (e.g., pattern analysis) manner. Deep neural networks include a hierarchical structure in which 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. For example, in an image recognition application, the original input may be a matrix of pixels; the first representation layer may abstract the pixels and encode the edges; the second layer may combine and encode the arrangement of the edges; the third layer may encode a higher-level shape (e.g., identifying the structure of the substrate, such as a gate, mask, etc.); and the fourth layer may produce a classification output. Notably, the deep learning process can learn by itself which features are best placed at which level. The "depth" in "deep learning" refers to the number of layers through which the data is transformed. More precisely, deep learning systems have a considerable credit assignment path (CAP) depth. CAP is a chain of transformations from input to output. CAP describes the potential causal relationship between input and output. For a feed-forward neural network, the depth of the CAP may be the depth of the network and may be the number of hidden layers plus 1. For a recurrent neural network where a signal may propagate through the layers more than once, the CAP depth may be unlimited.

[0112] Training of neural networks can be accomplished in a supervised learning manner that involves feeding a training dataset 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 tuning the network weights at all layers and nodes of the network to minimize the error using techniques such as deep gradient descent and backpropagation. In many applications, repeating this process for many labeled inputs in the training dataset produces a network that can produce correct outputs when presented with inputs that differ from those present in the training dataset.

[0113] Model 490 may refer to a trained physics-based model. A trained physics-based model may be configured to find solutions to one or more equations describing physical quantities of a processing chamber, such as mass flow (e.g., gas flow) equations, heat transfer equations, fluid dynamics equations, etc. In some embodiments, the assumptions used to generate the physics-based model may not be completely accurate (e.g., due to inaccurate measurements, manufacturing or material defects, mismatches in manufacturing tolerances of components, component aging, drift, or different behavior than predicted, etc.). Training the physics-based model may correct one or more of these assumptions that introduce errors into the physics-based model, such as by allowing one or more parameters of the model to be changed to better fit the training data.

[0114] Prediction component 494 may provide input data to trained model 490 and may run trained model 490 on the input to obtain one or more outputs. Prediction component 494 may be capable of determining (e.g., extracting) prediction data 468 from the output of model 490 and may determine (e.g., extracting) confidence data from the output indicating a confidence level that prediction data 468 is an accurate predictor of a process associated with the input data of a product produced or to be produced, or an accurate predictor of a component of manufacturing system 402. Prediction component 494 may be capable of determining prediction data 468 based on the output of model 490, including predictions of properties of a finished substrate and predictions of the effective life of a component of manufacturing system 402, sensor, or metrology system 410. Prediction component 494 or a corrective action component associated with client device 450 (e.g., a component of application 454) may use the confidence data to determine whether to cause a corrective action associated with manufacturing system 402 based on prediction data 468.

[0115] The confidence data may include or indicate a confidence level. As an example, the prediction data 468 may indicate a predicted manufacturing condition (e.g., a condition within a processing chamber when the substrate is being processed) based on in-vacuum metrology of the substrate. The confidence data may indicate that the prediction data 468 is an accurate prediction of a product associated with at least a portion of the input data. In one example, the confidence level is a real number between 0 and 1 (including 0 and 1), where 0 indicates that there is no confidence that the prediction data 468 is an accurate prediction of a product processed according to the input data, and 1 indicates that there is absolute confidence that the prediction data 468 accurately predicts the properties of the product processed according to the input data. In response to the confidence data indicating that the confidence level of a predetermined number of examples (e.g., a percentage of examples, a frequency of examples, a total number of examples, etc.) is below a threshold level, the prediction component 494 may cause the model 490 to be retrained (e.g., by updating the training set, the validation set, and / or the test set to include additional, recent, or different data, etc.).

[0116] For purposes of illustration and not limitation, aspects of the present disclosure describe training models and using models using information related to historical data 442. In other implementations, heuristic models or rule-based models may be used to determine processing operation updates.

[0117] In some embodiments, the functionality of client device 450, server 420, data storage device 440, and modeling system 470 may be provided by a plurality of Figure 4 For example, in some embodiments, server machines 472 and 480 may be integrated into a single machine, while in some other embodiments, server machines 472, 480, and 492 may be integrated into a single machine. In some embodiments, modeling system 470 may be provided in whole or in part by server 420. In some embodiments, the functionality of client device 450, server 420, data storage device 440, and modeling system 470 may be provided by more than one machine. Figure 4 Larger machines available in quantities shown.

[0118] In general, functions described in one embodiment as being performed by client device 450, data storage device 440, metrology system 410, manufacturing system 402, and modeling system 470 may also be performed on server 420 in other embodiments, if appropriate. In addition, functions attributed to a particular component may be performed by different or multiple components operating together.

[0119] In some embodiments, a "user" may be represented as a single individual. However, other embodiments of the present disclosure encompass a "user" that is an entity controlled by multiple users and / or automation sources. For example, a group of individual users united as a group of administrators may be considered a "user."

[0120] Figure 5 is an exemplary dataset generator 572 (eg, Figure 4 The data set generator 572 may be Figure 4 In some embodiments, Figure 4The modeling system 470 may include multiple models. Each model may have a separate data set generator, or the models may share one or more data set generators. For example, different models may be utilized to accept different inputs (e.g., manufacturing parameters, sensor data, metrology data, spectral data), to generate different outputs (e.g., predicted metrology, predicted manufacturing conditions, recommended corrective actions), to participate in different types of analysis (e.g., machine learning, physics-based, statistical), etc.

[0121] In some embodiments, the model may be configured to accept as input data (e.g., spectral data) associated with electromagnetic radiation received by the probe from the substrate and to generate as output one or more indications of substrate properties (e.g., thickness; geometry such as critical dimension, etch depth, or sidewall angle; pattern uniformity; optical properties; chemical properties, etc.). Such models may include machine learning operations, physics-based operations, etc. In some embodiments, the model is configured to receive one or more indications of properties of the substrate (e.g., indications of one or more properties of the substrate at one or more locations of the substrate that coincide with the field of view of one or more probes) and to generate as output a prediction map of properties in other areas of the substrate (e.g., for a system with one probe, properties of locations that are not directly on the path of the probe as the substrate passes through the field of view of the probe from one part of the processing system to another). In some embodiments, the model is configured to receive as input one or more indications of substrate properties and to generate as output an indication of a processing condition of the substrate (e.g., an indication of the processing condition that caused the property of the substrate). In some embodiments, the model is configured to receive as input data (e.g., spectral data) associated with radiation received from the substrate and to generate as output a prediction of a processing condition of the substrate. In some embodiments, a model is used to receive data (e.g., spectral data, property data, etc.) and generate one or more indications of properties of a top layer of a substrate (e.g., the model may receive data collected from a substrate before and after a processing operation). In some embodiments, a model is used to receive input data (e.g., spectral data, property data, etc.) and generate one or more recommended corrective actions as output, and / or to cause performance of one or more corrective actions.

[0122] Figures 5 and 6The discussion will focus on systems and operations associated with a machine learning model that is configured to receive spectral data (e.g., spectral data collected by a probe from a substrate being transported by a transport robot from one location in a processing system to a second location in the processing system) and generate as output an indication of a processing condition associated with processing the substrate. Similar methods and systems can be used for different machine learning models (e.g., models that receive different data as input and / or generate different data as output), different types of models (e.g., physics-based models, statistical models), etc., and they are within the scope of the present disclosure.

[0123] The system 500 including the data set generator 572 is a model (e.g., Figure 4 The data set generator 572 may generate a data set using historical data. The data set generator 572 may generate a data set using data generated by a metrology tool (e.g., data generated by receiving electromagnetic radiation from a substrate in a processing system through one or more probes). The data set generator 572 may generate a data set using data indicating a processing condition of the substrate (e.g., data from a device configured to measure a condition at or near a location on the substrate, sensor data from a processing chamber, etc.).

[0124] The data set generator 572 generates data input 510. The data set generator 572 may also generate target output 520. In some embodiments, for example, to train an unsupervised machine learning model, the data set generator may not generate target output 520. The data set generator 572 may generate data input 510 using substrate radiation data. The substrate radiation data may be associated with radiation emitted by a substrate. The substrate radiation data may be associated with radiation reflected by one or more substrates. The substrate radiation data may be associated with radiation transmitted through a substrate. The substrate radiation data may be associated with radiation received by one or more probes of a processing system (e.g., a substrate processing system) when one or more substrates are moving within the processing system (e.g., data collected when one or more substrates are transferred between parts of the processing system). The substrate radiation data may be spectral data. The substrate radiation data may include a combination of data (e.g., data collected by multiple probes, data associated with multiple radiation sources (e.g., reflected and emitted light), etc.). The target output 520 may include processing condition data. The processing condition data may be generated by an instrument (e.g., designed to be located at or near a processing location). The process condition data may be generated by sensors associated with a processing system (eg, a substrate processing system).

[0125] The data set may include pre-processed data, such as data that is smoothed, cleaned (removing outliers, etc.), combined, collected into feature vectors or attributes, etc.

[0126] The data set generator 572 may generate a data set (e.g., a training set, a validation set, a test set) that includes one or more data inputs 510 (e.g., a training input, a validation input, a test input) and may include one or more target outputs 520 corresponding to the data inputs 510. The data set may also include mapping data that maps the data inputs 510 to the target outputs 520. The data inputs 510 may also be referred to as “features,” “attributes,” or “information.” In some embodiments, the data set generator 572 generates a data set (e.g., a training set, a validation set, a test set) that includes one or more data inputs 510 (e.g., a training input, a validation input, a test input) and may include one or more target outputs 520 corresponding to the data inputs 510. The data set may also include mapping data that maps the data inputs 510 to the target outputs 520. The data inputs 510 may also be referred to as “features,” “attributes,” or “information.” Figure 4 Provide one or more data sets to the training engine, validation engine, and / or test engine of the system. The data can be used by the engine to train, validate, or test the system. Figure 4 Model 490. Can be combined with Fig. 7A Some embodiments of generating a training set, a validation set, or a test set are further described.

[0127] The dataset generator 474 may generate a first data input corresponding to the first substrate radiation dataset 544A to train, validate or test the first model. The dataset generator 572 may generate a second data input corresponding to the second sensor dataset 544B to train, validate or test the second model.

[0128] In some embodiments, the data set generator 474 performs operations on one or more of the data input 510 and the target output 520. The data set generator 572 may extract patterns from the data (slope, curvature, etc.), may combine the data (average, feature generation, etc.), or may separate the data into groups (e.g., train a model on a subset of the substrate radiation data) and use the groups to train separate models.

[0129] The data input 510 and target output 520 for training, validating, or testing the model may include information for a specific substrate processing recipe (e.g., a specific substrate design). The data input 510 and target output 520 may include information for a specific substrate processing system (e.g., for a specific set of manufacturing equipment). The data input 510 and target output 520 may include information for a specific process type, target substrate properties, type of processing equipment, processing facility, or may be grouped together in another manner.

[0130] In some embodiments, the data set generator 572 generates a set of target outputs 520, including a processing condition data set 530. The target outputs 520 can be divided into sets corresponding to the input data sets. Different sets of target outputs 520 can be used in conjunction with sets of similarly defined data inputs 510, including training different models, using different sets for training, validation, and testing, etc.

[0131] In some embodiments, a model (e.g., an unsupervised or semi-supervised model) is trained without a target output 520. A trained model that is not provided with a target output can, for example, be trained to identify significant (e.g., outside of an error threshold) differences between predicted and measured data (e.g., between a process condition set point and a process condition implied by in-vacuum metrology of a substrate being transferred by a robotic arm of a processing system).

[0132] In some embodiments, the information used to train the model can come from a specific type of manufacturing equipment, such as manufacturing equipment of a manufacturing facility. The types of manufacturing equipment that contribute to the data set of the data set generator 572 can share one or more characteristics, such as the brand and / or model of the equipment. The trained model can be capable of generating outputs related to a group of manufacturing equipment tools based on the data input 510 and the target output 520 used to train the model. In some embodiments, the data used to train the model can originate from two or more manufacturing facilities.

[0133] In some embodiments, after a data set is generated and used to train, validate, or test a model, the model can be further trained, validated, or tested or adjusted. For example, after the model is trained, validated, and tested, additional data can be provided to the model from the processed substrate as retraining data, revalidation data, retest data, etc.

[0134] The data set generator 572 can generate a data set to train, validate and / or test a model. Training a model can include generating a model mapping that the model uses to connect input data to output data.

[0135] A dataset generator that performs similar functions to the dataset generator 572 may be used to train a physics-based model. A physics-based model may be configured to generate outputs based on a physical understanding of the system, based on physical assumptions about the operation of the system, based on one or more numerical solutions to one or more physical equations (e.g., heat transfer equations, mass balance equations, fluid dynamics equations, etc.), etc. A physics-based model may be trained in a manner similar to a machine learning model. A physics-based model may have training inputs and target outputs, and one or more parameters, weights, biases, etc. may be adjusted to better align the model output with the target output.

[0136] In some embodiments, a physics-based model receives a set of inputs (e.g., an indication of radiation received by a probe from a substrate). The physics-based model may generate an output (e.g., a predicted processing condition of a substrate) based on the inputs. The physics-based model may have a target output (e.g., a measured processing condition of a substrate). The physics-based model may adjust one or more parameters of the model to generate an output that is more similar to the target output than before the adjustment was made.

[0137] Figure 6 6 is a block diagram illustrating a system 600 for generating output data for performing corrective actions according to some embodiments. System 600 may be used to train a model (e.g., a machine learning model) and utilize the output of the model. Some or all operations of system 600 may be used to generate output data of a machine learning model. Some or all operations of system 600 may be used to generate output data of a physics-based model, a statistical model, etc.

[0138] At block 610, the system 600 (e.g., Figure 4 Components of the modeling system 470) perform data partitioning of the historical data 664 (e.g., via Figure 4 The historical data may be divided by the data set generator 474 of the training set 602 to generate a training set 602, a validation set 604, and a test set 606. The historical data may include data for training input (e.g., spectral data generated in a vacuum according to radiation received from one or more substrates), data for training target output (e.g., data indicating processing conditions of one or more substrates), etc. For example, the training set may be 60% of the historical data, the validation set may be 20% of the historical data, and the test set may be 20% of the historical data.

[0139] At block 612, system 600 performs model training using training set 602 (e.g., via Figure 4 484). The system 600 can train a model using multiple sets of features (e.g., attributes, feature vectors) of the training set 602 (e.g., a first attribute set including a subset of historical data of the training set 602, a second attribute set including a different subset of historical data of the training set 602, and so on). For example, the system 300 can train a machine learning model to produce a first trained machine learning model using a first attribute set in the training set and to produce a second trained machine learning model using a second attribute set in the training set (e.g., data different from the data used to train the first machine learning model). In some embodiments, the first trained machine learning model and the second trained machine learning model can be combined to produce a third trained machine learning model (e.g., which can be a better predictor than the first or second trained machine learning model itself). In some embodiments, the attribute sets used in the comparison models can overlap (e.g., one model can be trained with performance data indicative of film thickness, while another model can be trained with performance data indicative of both film thickness and film stress, different models can be trained with data from different locations of the substrate, models can be trained using inputs including different sets from sensors or manufacturing parameters, and so on). In some embodiments, hundreds of models can be generated, including models with various permutations of properties and combinations of models.

[0140] At block 614, system 600 performs model validation using validation set 604 (e.g., via Figure 4 484). The system 600 may validate each of the trained models using a corresponding feature set of the validation set 604. For example, the validation set 604 may use the same subset of historical data types for the model in the training set 602 (e.g., associated with the same substrate characteristics, the same sensors, the same input parameters, etc.), but with different input data values. The system 600 may validate hundreds of models generated at block 612 (e.g., models with various arrangements of features or attributes, combinations of models, etc.). At block 614, the system 600 may determine the accuracy of each of the one or more trained models (e.g., via model validation), and may determine whether one or more of the trained models have an accuracy that satisfies a threshold accuracy. In response to determining that none of the trained models have an accuracy that satisfies the threshold accuracy, the process may return to block 612, where the system 600 performs model training using a different attribute set of the training set. In response to determining that one or more of the trained models have an accuracy that satisfies a threshold accuracy, flow can continue to block 616. The system 600 can discard trained machine learning models having an accuracy below a threshold accuracy (e.g., based on a validation set).

[0141] At block 616, the system 600 may perform model selection (e.g., via a selection engine) to determine which of the one or more trained models that meet the threshold accuracy has the highest accuracy (e.g., the model 608 selected based on the validation of block 614). If only a single model has been trained (e.g., the accuracy is above the accuracy threshold in the validation), the operation of block 616 may be skipped. In response to determining that two or more of the trained models that meet the threshold accuracy have the same accuracy (e.g., within the threshold), the process may return to block 612, where the system 600 performs model training using a further refined training set (e.g., corresponding to a further refined set of attributes) to determine the trained model with the highest accuracy.

[0142] At block 618, system 600 performs model testing using test set 606 (eg, via Figure 4The system 600 may test the first model (e.g., a trained machine learning model) using the first feature set in the test set to determine that the first trained model meets the threshold accuracy (e.g., based on the first feature set of the test set 606). In response to the accuracy of the selected model 608 not meeting the threshold accuracy (e.g., the selected model 608 overfits the training set 602 and / or the validation set 604 and is not applicable to other data sets such as the test set 606), the process may continue to block 612, where the system 600 performs model training (e.g., retraining) using a different training set that may correspond to a different set of features or attributes or a reorganization of the data sets partitioned into a training set, a validation set, and a test set. In response to determining that the selected model 608 has an accuracy that meets the threshold accuracy based on the test set 606, the process continues to block 620. At least in block 612 , the model can learn patterns in the input data to make predictions, and in block 618 , the system 600 can apply the model to the remaining data (eg, the test set 606 ) to test the predictions.

[0143] At block 620, the system 600 uses a trained model (e.g., the selected model 608) to receive current radiation data 654 (e.g., data based on radiation received from a substrate being processed) and determines (e.g., predicts) via the trained model a process condition for processing the current substrate (e.g., process condition data 669). The process condition data 669 can be used to perform corrective actions, such as to improve the process conditions of the processing chamber by updating a recipe, scheduling maintenance, providing an alert to a user, etc.

[0144] In some embodiments, retraining of the model is performed by supplying additional data to further train the model. Current radiation data 654 may be provided for further model training (e.g., it may be provided to a training engine for use as a training input). Current condition data 646 (e.g., measurements of processing conditions of a substrate) may be provided to a model training engine, for example, for use as a target output. The selected model 608 may be retrained based on this data. One or more of actions 610 to 620 may occur in various orders and / or with other actions not presented and described herein. In some embodiments, one or more of actions 610 to 620 may not be performed. For example, in some embodiments, one or more of the data partitioning of block 610, the model validation of block 614, the model selection of block 616, or the model testing of block 618 may not be performed. When training a physics-based model, a subset of the described operations may be performed.

[0145] 7A to 7Cis a flow chart of methods 700A to 700C associated with utilizing electromagnetic radiation-based metrology within a chamber according to some embodiments. Methods 700A to 700C may be performed by processing logic that may include hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, processing device, etc.), software (such as instructions running on a processing device, a general purpose computer system, or a dedicated machine), firmware, microcode, or a combination thereof. In some embodiments, methods 700A to 700C may be performed in part by Figure 4 The method 700A may be performed in part by Figure 4 Modeling system 470 (e.g., Figure 4 According to an embodiment of the present disclosure, the modeling system 470 may use method 700A to generate a data set for at least one of training, validating, or testing a model. The model may be a physics-based model, a machine learning model, a statistical model, or another model trained to receive inputs and generate outputs related to substrate manufacturing or processing. Methods 700B to 700C may be performed by Figure 1 The processing device 130, Figure 4 In some embodiments, the non-transitory storage medium stores instructions that, when executed by a processing device (e.g., modeling system 470, system 400, server machine 480, etc.), cause the processing device to perform one or more of methods 700A to 700C.

[0146] For simplicity of explanation, methods 700A to 700C are depicted and described as a series of operations. However, operations according to the present disclosure may occur in various orders and / or simultaneously with other operations not presented and described herein. In addition, implementation of methods 700A to 700C according to the disclosed subject matter does not require execution of all illustrated operations. In addition, those skilled in the art will understand and appreciate that methods 700A to 700C may alternatively be represented as a series of interrelated states via a state diagram of events.

[0147] Fig. 7A is a flow chart of a method 700A for generating a data set for a model that generates output data according to some embodiments. At block 701, processing logic implementing the method 700A initializes a training set T to an empty set.

[0148] At block 702, processing logic generates a first data input (e.g., a first training input, a first validation input), which may include sensor data, manufacturing parameter data, measured substrate property data, substrate metrology data (e.g., film properties such as thickness, material composition, optical properties, roughness, etc.), etc. In some embodiments, the first data input may include a first set of attributes for certain data types, and the second data input may include a second set of attributes for certain data types (e.g., such as regarding Figure 6 described).

[0149] At block 703, processing logic generates a first target output for one or more of the data inputs (e.g., a first data input). In some embodiments, the first target output is performance data of the substrate. In some embodiments, the first target output is data indicating a corrective action. In some embodiments, no target output is generated (e.g., for training an unsupervised machine learning model).

[0150] At block 704, the processing logic optionally generates mapping data indicating an input / output mapping. The input / output mapping (or mapping data) may refer to a data input (e.g., one or more of the data inputs described herein), a target output for the data input, and an association between the data input and the target output. In some embodiments (e.g., those embodiments without target output data), these operations may not be performed.

[0151] In some implementations, at block 705 , processing logic adds the mapping data generated at block 404 to data set T.

[0152] At block 706, processing logic determines whether the dataset T is sufficient for training, validating, and / or testing the model (e.g., Figure 4 If T is sufficient, execution proceeds to block 707, otherwise, execution continues back to block 702. It should be noted that in some embodiments, the sufficiency of the dataset T can be determined simply based on the number of inputs (which are mapped to outputs in some embodiments) in the dataset, while in some other embodiments, in addition to or instead of the number of inputs, the sufficiency of the dataset T can be determined based on one or more other criteria (e.g., a measure of the diversity of data examples, accuracy, the range of the input and / or output space, etc.).

[0153] At block 707, processing logic provides a data set T (e.g., Figure 4In some embodiments, the dataset T is a training set and is provided to a training engine 482 of the server machine 480 to perform training. In some embodiments, the dataset T is a validation set and is provided to a validation engine 484 of the server machine 480 to perform validation. In some embodiments, the dataset T is a test set and is provided to a test engine 486 of the server machine 480 to perform testing.

[0154] Figure 7B 1 is a flow chart of a method 700B for generating and utilizing data based on radiation received by a probe while a substrate is within a processing system according to some embodiments. The method 700B may include receiving radiation from a substrate while the substrate is in a controlled environment (e.g., a vacuum). The method 700B may include receiving radiation from a substrate while the substrate is moving (e.g., while a robot is transporting the substrate from one location to another in a substrate processing system).

[0155] At block 710, processing logic receives first data. The first data is generated by a sensor of a substrate processing system (e.g., via a probe, a spectrometer, and a processing device / processor of the substrate processing system). The first data may include spectral data. The first data is generated in response to the sensor receiving electromagnetic radiation. The electromagnetic radiation is received from a substrate. The substrate is held by a robot arm of a transfer chamber in a substrate processing system. The first data may be generated in response to electromagnetic radiation received when the robot arm is transferring a substrate from a first area of ​​the substrate processing system to a second area of ​​the substrate processing system (e.g., by a probe, by a sensor, by a spectrometer, etc.). In some embodiments, when the substrate is being transferred, the radiation may be directed to / received by one or more sensors (e.g., in a yield-transparent manner). In some embodiments, the robot arm may be configured to change / adjust the path of the substrate to increase, change, or improve the data generated by the sensor. In some embodiments, the robot may transfer the substrate via multiple trajectories, such as to increase the portion of the substrate that intersects the field of view of one or more probes.

[0156] In some embodiments, data for a substrate may be recorded multiple times. For example, when a portion of a substrate passes through the field of view of a sensor, electromagnetic radiation received from the substrate may be separated into multiple data points, for example, each data point corresponding to a different spatial position of the substrate. One or more of these regions (e.g., regions associated with first data, other positions associated with other data, etc.) may have associated data analyzed. A map or partial map of measured properties, processing conditions, etc. may be generated by receiving electromagnetic radiation from multiple positions of the substrate. In some embodiments, spatially different (e.g., separated) data may be used to generate a distribution of the substrate (e.g., thickness distribution, temperature distribution, etc.).

[0157] In some embodiments, one or more operations of a sensor can be triggered. For example, an object detection system (e.g., a laser object detection system, an object detection device, etc.) can detect the presence of a substrate at a certain position of a substrate processing system. In response to detecting the substrate, one or more operations of the sensor can be started, changed, etc. In some embodiments, the speed of a robot arm supporting a substrate can be used to determine the timing of the operation of the sensor. In some embodiments, a detection device can be started at a target time in response to object detection. In some embodiments, an irradiation device (e.g., an electromagnetic radiation source) can be started in response to object detection. In some embodiments, the irradiation device can operate in a pulsed mode and can change the timing in response to object detection, such as to aim at a specific area of ​​the substrate (e.g., an edge, a distance from an edge, a center, etc.) for irradiation.

[0158] In some embodiments, additional data is generated by additional sensors (e.g., additional probes). For example, an array of probes can generate data associated with additional locations of the substrate (e.g., to increase statistical certainty, to increase understanding of the complete substrate distribution, etc.). Multiple probes can report different properties (e.g., substrate thickness and substrate temperature), radiation at different wavelength ranges, different illumination conditions (e.g., reflection, transmission, emission, etc.), etc. The data can be processed into different forms, such as temperature data, thickness data, corrective action data, process condition data, etc. The data from additional probes and / or sensors can be used similarly to the first.

[0159] In some embodiments, the collected data (e.g., data provided by sensors) may be corrected, for example, to account for the operation of the substrate processing system. For example, the behavior of the robot arm in terms of position, speed, direction of movement, extension percentage, etc. may differ from the ideal behavior. In some embodiments, the robot arm may hold the substrate at different angles depending on the position and movement of the robot arm. The data may be corrected for such effects. In some embodiments, the robot arm may hold the substrate at different heights depending on the position and movement of the robot arm. The data may be corrected for such effects.

[0160] At block 712, the processing logic processes the first data to obtain second data. The second data includes an indication of the performance (e.g., performance quality) of the substrate processing system. The second data may include one or more indications of the properties of the substrate. The second data may include one or more characteristics of the substrate, such as thickness, chemical composition, optical properties, surface pattern, etc. The second data may include optical data, such as absorption spectrum, reflection spectrum, etc. The second data may include the geometry of the substrate, such as etching depth, sidewall angle, critical dimension, etc. The second data may include substrate shape, substrate distortion, bending, etc. The second data may include one or more indications of the state of the substrate processing system or the performance quality of the substrate processing system. The second data may include one or more indications of the conditions under which the substrate processing system processes the substrate. The second data may include potential problems with the processing system, such as unexpected processing conditions, incorrect or insufficient calibration, etc.

[0161] In some embodiments, processing the first data may include providing the first data to a model. The first data may be provided to a machine learning model, a physics-based model, a statistical model, etc. The model may perform one or more of a number of different functions. The model may receive data generated by one or more sensors and generate data indicating a property of the substrate (e.g., thickness, chemical properties, temperature, etc.). The model may receive data indicating properties associated with one or more spatial regions of the substrate (e.g., regions arranged in a straight line on the substrate, based on radiation collected when the substrate is moving through the field of view of the probe) and generate a property map of the substrate, for example, including one or more regions where no radiation is collected. The model may receive data indicating one or more substrate properties and generate one or more indications of processing conditions of the substrate. The model may receive data indicating one or more substrate properties and generate recommended corrective actions and / or perform recommended corrective actions. The model may receive data associated with radiation received from the substrate (e.g., spectral data) and generate one or more indications of processing conditions of the substrate. The model may receive data associated with radiation received from the substrate and generate and / or perform one or more recommended corrective actions. The model can receive data and generate an indication of a property of a single layer of the substrate (e.g., radiation from the substrate can be collected before and after performing a processing operation, such as by a probe disposed near a coupling between a processing chamber and a transfer chamber of a substrate processing system). In some embodiments, multiple models can be utilized. In some embodiments, the models can be utilized sequentially (e.g., spectral data can be provided to a model to generate property data, and the property data can be provided to the model to generate a recommendation for corrective action). In some embodiments, a combined model can be utilized (e.g., a model that performs the operations of multiple models).

[0162] A model (e.g., a machine learning model) can be trained by providing historical data. In some embodiments, the historical data can be associated with the substrates that were generated to train the model. For example, many substrates can be generated with specialized and / or intentionally varied processing conditions to establish data for the input space and / or output space of the model.

[0163] At block 714, processing logic causes execution of a corrective action associated with the substrate processing system in view of the second data. The corrective action may include, for example, updating a process recipe, scheduling maintenance, providing an alert to a user, and the like.

[0164] Figure 7C is a flow chart of a method 700C for performing a corrective action in view of one or more characteristics of a substrate according to some embodiments. At block 720, processing logic receives first data. The first data may be Figure 7BThe first data share one or more characteristics. The first data is generated by a sensor of the substrate processing system. The sensor can be a spectrometer. The first data is generated in response to the sensor receiving electromagnetic radiation from the substrate. The substrate is held by a robotic arm (e.g., supported by a robotic arm, supported on a robotic arm, etc.). The robotic arm is in a substrate processing system (e.g., coupled to a transfer chamber of the substrate processing system). The radiation can be received by the sensor while the robotic arm is moving the substrate, for example, the measurement can be performed while the substrate is being transferred. The measurement can be performed while the substrate is being transferred from one chamber (e.g., a transfer chamber, a processing chamber, a loading lock, etc.) to another chamber. The sensor can include a probe (e.g., for receiving radiation). The probe can be at least partially disposed within the processing system (e.g., embedded in a wall of the system). The processing system can include one or more probes, one or more probe arrays, one or more sensors, etc.

[0165] At block 722, the first data is provided to a model by processing logic. The model may be a physics-based model, a machine learning model, etc. The model may be configured to receive optical data, radiation data, spectral data, etc. as input and generate output based on the input data.

[0166] At block 724, the processing logic obtains second data from the model. The second data indicates one or more properties of the substrate. These properties may include one or more of physical properties, optical properties, electrical properties, current conditions (e.g., temperature), etc. These properties may include a selected layer or group of layers of the substrate. These properties may include thickness, refractive index, extinction coefficient, temperature, etc. Probes and / or sensors may be used to determine target properties, for example, a pyrometer probe may be used to determine temperature, a broadband (e.g., white light sensitive) reflectometer may be used to determine film thickness, etc. In some embodiments, the model may receive historical measurements (e.g., measurements from one or more previous processing operations) as additional inputs (e.g., to separate properties of deposited or etched layers or substrates).

[0167] At block 726, processing logic causes execution of corrective actions. Corrective actions may include process / feedback control (e.g., updating one or more process recipes in view of the characteristics determined by the model). Corrective actions may include planning metrology (e.g., metrology of substrates that may exceed target specifications). Corrective actions may include planning maintenance (e.g., corrective or preventive maintenance). Corrective actions may include initiating maintenance (e.g., chamber cleaning or chamber conditioning processes).

[0168] Figure 8 A block diagram of an exemplary computing device that operates in accordance with one or more aspects of the present disclosure is depicted. In various illustrative examples, various components of computing device 800 may represent Figure 44. The various components of client device 450, metering system 410, server 420, data storage device 140, and modeling system 470 are shown in FIG.

[0169] The exemplary computing device 800 can be connected to other computer devices in a LAN, an internal network, an external network and / or an Internet. The computing device 800 can operate as a server in a client-server network environment. The computing device 800 can be provided by any device of a personal computer (PC), a set-top box (STB), a server, a network router, a switch or a bridge or a group of instructions (sequential or otherwise) that specify the action to be taken by the device. In addition, although only a single exemplary computing device is shown, the term "computer" should also be understood to include any collection of computers that execute a group (or multiple groups) of instructions to execute any one or more methods in the method discussed herein, either individually or jointly.

[0170] The exemplary computing device 800 may include a processing device 802 (also referred to as a processor or CPU), a main memory 804 (e.g., read-only memory (ROM), flash memory, dynamic random access memory (DRAM) such as synchronous DRAM (SDRAM), etc.), a static memory 806 (e.g., flash memory, static random access memory (SRAM), etc.), and an auxiliary memory (e.g., a data storage device 818), which may communicate with each other via a bus 830.

[0171] The processing device 802 represents one or more general-purpose processing devices, such as a microprocessor, a central processing unit, etc. More specifically, the processing device 802 may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor that implements other instruction sets, or a processor that implements a combination of instruction sets. The processing device 802 may 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. According to one or more aspects of the present disclosure, the processing device 802 may be configured to execute an implementation 7A to 7C The methods 700A to 700C and / or Figure 6 Instructions for the process shown in .

[0172] The exemplary computing device 800 may further include a network interface device 808, which may be communicatively coupled to a network 820. The exemplary computing device 800 may further include a video display 810 (e.g., a liquid crystal display (LCD), a touch screen, or a cathode ray tube (CRT)), an alphanumeric input device 812 (e.g., a keyboard), a cursor control device 814 (e.g., a mouse), and a sound signal generating device 816 (e.g., a speaker).

[0173] The data storage device 818 may include a computer-readable storage medium (or more particularly, a non-transitory machine-readable storage medium) 828 having stored thereon one or more sets of executable instructions 822. According to one or more aspects of the present disclosure, the executable instructions 822 may include executable instructions associated with any of the methods disclosed herein, such as instructions for performing any of the methods disclosed herein. The executable instructions 822 may be associated with an executable instruction. Figure 6 The methods shown in and / or Fig. 7A 7C is associated with methods 700A to 700C shown in FIG. 7C.

[0174] The executable instructions 822 may also reside completely or at least partially within the main memory 804 and / or within the processing device 802 during execution by the exemplary computing device 800, the memory 804 and the processing device 802 also constituting computer-readable storage media. The executable instructions 822 may further be sent or received over a network via the network interface device 808.

[0175] Although the computer-readable storage medium 828 is illustrated in FIG. 9 as a single medium, the term "computer-readable storage medium" should be considered a single medium or multiple media (e.g., a centralized or distributed database, and / or associated caches and servers) that store one or more sets of operating instructions. The term "computer-readable storage medium" should also be understood to include any medium capable of storing or encoding a set of instructions for execution by a machine to cause the machine to perform any one or more of the methods described herein. Therefore, the term "computer-readable storage medium" should be understood to include, but is not limited to, solid-state memories and optical and magnetic media.

[0176] Some portions of the above detailed description are presented in terms of algorithms and symbolic representations of operations on data bits within a computer memory. These algorithmic descriptions and representations are the means by which those skilled in the art most effectively convey the substance of their work to others skilled in the art. An algorithm is herein and generally considered to be a self-consistent sequence of steps leading to a desired result. These steps are those operations requiring physical manipulation of physical quantities. Typically, but not necessarily, these quantities take the form of electrical or magnetic signals capable of being stored, transmitted, combined, compared, and otherwise manipulated. Mainly for general reasons, it has proven convenient at times to refer to these signals as bits, values, elements, symbols, characters, terms, numbers, etc.

[0177] It should be remembered, however, that all of these and similar terms are associated with the appropriate physical quantities and are merely convenient labels applied to these quantities. Unless otherwise specifically stated, as will be apparent from the following discussion, it should be understood that throughout the specification, terms such as "identify," "determine," "store," "adjust," "cause," "return," "compare," "generate," "stop," "load," "copy," "throw," "replace," "execute," "receive," "process," "generate," "trigger," "train," and the like are used to refer to the actions and processes of a computer system or similar electronic computing device that manipulate and transform data represented as physical (electronic) quantities within the computer system's scratchpad and memory into other data similarly represented as physical quantities within the computer system's memory or scratchpad or other such information storage, transmission, or display devices.

[0178] Examples of the present disclosure also relate to devices for performing the methods described herein. Such devices may be specially constructed for the desired purpose, or they may be general-purpose computer systems selectively programmed by computer programs stored in a computer system. Such computer programs may be stored in a computer-readable storage medium, such as but not limited to any type of disk, including optical disks, compact disc read only memory (CD-ROM) and magneto-optical disks, read-only memory (ROM), random access memory (RAM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), magnetic disk storage media, optical storage media, flash memory devices, other types of machine-accessible storage media, or any type of medium suitable for storing electronic instructions, each medium coupled to a computer system bus.

[0179] The foregoing description sets forth many specific details, such as examples of specific systems, components, methods, etc., in order to provide a good understanding of several 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 may be practiced without these specific details. In other cases, well-known components or methods are not described in detail or presented in the form of simple block diagrams to avoid unnecessarily obscuring the present disclosure. Therefore, the specific details set forth are merely exemplary. Specific embodiments may differ from these exemplary details and are still considered to be within the scope of the present disclosure.

[0180] Throughout the specification, references to "one embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic described in conjunction with the embodiment is included in at least one embodiment. Therefore, the phrases "in one embodiment" or "in an embodiment" appearing in various places throughout the specification do not necessarily refer to the same embodiment. In addition, the term "or" is intended to represent an inclusive "or" rather than an exclusive "or". When the term "about" or "approximately" is used herein, this is intended to mean that the nominal value presented is accurate within a range of ±10%.

[0181] Although the operations of the methods herein are illustrated and described in a particular order, the order of operations of each method can be changed so that certain operations can be performed in a reverse order, thereby performing certain operations at least partially simultaneously with other operations. In another embodiment, the instructions or sub-operations of different operations can be intermittent and / or alternating.

[0182] It should be understood that the above description is intended to be illustrative, not restrictive. After reading and understanding the above description, many other embodiments will be apparent to those skilled in the art. Therefore, the scope of the present disclosure should be determined with reference to the full scope of the appended claims and the equivalent technical solutions of these claims.

Claims

1. A method comprising the following steps: receiving, by a processing device, first data generated by a first sensor of a substrate processing system, the first data having been generated in response to the first sensor receiving electromagnetic radiation from a substrate held by a robotic arm of a transfer chamber in the substrate processing system; processing the first data to obtain second data, wherein the second data comprises a first indication of performance of the substrate processing system; and In view of the second data, execution of a corrective action associated with the substrate processing system is caused. 2 . The method of claim 1 , wherein the first data comprises spectral data, and wherein the second data comprises an indication of a thickness of the substrate.

3. The method of claim 1, wherein the second data comprises an indication of conditions under which the substrate processing system processed the substrate.

4. The method of claim 1, wherein the first sensor receives the electromagnetic radiation from the substrate while the robotic arm is transferring the substrate from a first area of ​​the substrate processing system to a second area of ​​the substrate processing system.

5. The method according to claim 1, further comprising the steps of: receiving third data from the first sensor, wherein the first data is associated with a first portion of the substrate, and wherein the third data is associated with a second portion of the substrate; processing the third data to obtain fourth data, wherein the fourth data includes a second indication of performance of the substrate processing system; as well as The distribution of the substrate is generated in view of the third data and the fourth data.

6. The method according to claim 1, further comprising the steps of: receiving a signal from an object detection device, the signal indicating the presence of the substrate at a first location of the substrate processing system; as well as In response to receiving the signal from the object detection device, triggering operation of the first sensor, wherein the step of triggering operation of the first sensor includes the steps of causing the first sensor to detect electromagnetic radiation from the substrate at a target time, the target time being based on (i) the time when the object detection device indicates that the substrate is present at the first position and (ii) the speed at which the robot arm conveys the substrate.

7. The method according to claim 1, further comprising the steps of: receiving third data generated by one or more additional sensors of the substrate processing system, wherein the first sensor and the one or more additional sensors form a sensor array, the third data being generated in response to the one or more additional sensors receiving electromagnetic radiation from one or more regions of the substrate different from the region of the substrate from which the first sensor received electromagnetic radiation; as well as The third data is processed to obtain fourth data, wherein the fourth data includes a second indication of performance of the substrate processing system.

8. The method according to claim 1, further comprising the steps of: receiving third data generated by a second sensor of the substrate processing system; and The third data is processed to obtain fourth data, wherein the fourth data comprises a second indication of performance of the substrate processing system, and wherein the first sensor is used to receive electromagnetic radiation in a first wavelength range, and wherein the second sensor is used to receive electromagnetic radiation in a second wavelength range. 9 . The method of claim 8 , wherein the fourth data comprises temperature data of the substrate, and wherein the first sensor is configured to receive radiation reflected from the substrate.

10. The method according to claim 1, further comprising the steps of: receiving a plurality of sensor data associated with a first plurality of substrates after the first plurality of substrates have been processed by an etching process or a deposition process; receiving a plurality of data indicative of processing conditions for the first plurality of substrates; as well as The machine learning model is trained by providing the plurality of sensor data as training inputs to the machine learning model and providing the plurality of data indicating processing conditions as target outputs to the machine learning model.

11. The method according to claim 1, wherein the step of processing the first data to obtain the second data comprises the following steps: The first data is provided to a trained machine learning model, wherein the trained machine learning model is configured to receive sensor data as input and to generate an indication of a processing condition of the substrate as output.

12. A substrate processing system, comprising: a processing chamber; a transfer chamber coupled to the processing chamber; a robot arm of the transfer chamber, the robot arm being configured to transfer a substrate between the processing chamber and the transfer chamber; as well as a sensor having a first field of view, wherein at least a portion of the first field of view includes at least a portion of the substrate as the substrate is transferred to and from the processing chamber by the robotic arm, wherein the sensor is configured to receive electromagnetic radiation that has interacted with the substrate; as well as A processing device is configured to process data generated in response to the sensor receiving electromagnetic radiation for determining at least one of: (i) one or more indications of performance of the substrate processing system, or (ii) one or more properties of the substrate.

13. The substrate processing system of claim 12, further comprising an electromagnetic radiation source, wherein the sensor comprises an electromagnetic probe, and wherein the electromagnetic probe is arranged to receive electromagnetic radiation generated by the source that has interacted with the substrate.

14. The substrate processing system of claim 13, wherein the electromagnetic radiation that has interacted with the substrate comprises electromagnetic radiation reflected from a surface of the substrate.

15. The substrate processing system of claim 13, wherein the electromagnetic radiation that has interacted with the substrate comprises electromagnetic radiation that is transmitted through the substrate.

16. The substrate processing system of claim 12, wherein the sensor is configured to receive infrared radiation emitted by the substrate.

17. The substrate processing system of claim 12, further comprising one or more additional sensors, the sensor and the one or more additional sensors comprising a sensor array, a second sensor in the sensor array having a second field of view, wherein the second field of view comprises a second portion of the substrate, the second portion being different from the at least a portion of the substrate included in the first field of view.

18. The substrate processing system according to claim 12, wherein the processing device is used to process data, and the data comprises: first data associated with electromagnetic radiation received by the sensor from a first area of ​​the substrate at a first time; as well as Second data associated with electromagnetic radiation received by the sensor from a second region of the substrate at a second time, wherein the first region is different from the second region.

19. The substrate processing system of claim 12, further comprising a pyrometer, wherein the sensor is configured to receive electromagnetic radiation reflected from the substrate, and the pyrometer is configured to receive electromagnetic radiation emitted from the substrate.

20. A non-transitory machine-readable storage medium storing instructions that, when executed, cause a processing device to perform operations comprising: receiving first data generated by a first sensor of a substrate processing system, the first data having been generated in response to the first sensor receiving electromagnetic radiation from a substrate held by a robotic arm of a transfer chamber in the substrate processing system; processing the first data to obtain second data, wherein the second data includes first one or more property values ​​of the substrate; and In view of the second data, execution of a corrective action associated with the substrate processing system is caused.

21. The non-transitory machine-readable storage medium of claim 20, wherein the operations further comprise: receiving third data generated by the first sensor of the substrate processing system; processing the third data to obtain second one or more property values ​​of the substrate; receiving fourth data generated by the first sensor of the substrate processing system; as well as processing the fourth data to obtain third one or more property values ​​of the substrate, wherein: The first data, the second data, and the third data are each generated in response to the first sensor receiving electromagnetic radiation from the substrate while the substrate is being transferred by the robot arm; The first data corresponds to a first spatial region of the substrate, the third data corresponds to a second spatial region of the substrate, and the fourth data corresponds to a third spatial region of the substrate; and The first spatial region is different from the second spatial region, and the third spatial region is different from the first spatial region and the second spatial region.

22. The non-transitory machine-readable storage medium of claim 21, wherein the robot arm is configured to transfer the substrate according to a first trajectory and a second trajectory, wherein: The first trajectory causes a first portion of the substrate to intersect a field of view of the first sensor; the second trajectory causes a second portion of the substrate to intersect the field of view of the first sensor; The first portion includes the first spatial region; and The second portion includes the second spatial region.

23. The non-transitory machine-readable storage medium of claim 20, wherein processing the first data to obtain the second data is performed in view of at least one of: An angle of the surface of the substrate relative to the optical axis of the first sensor; or A distance between the surface of the substrate and one or more components of the first sensor.

24. The non-transitory machine-readable storage medium of claim 20, wherein the operations further comprise: receiving third data generated by a second sensor of the substrate processing system, the third data generated in response to the second sensor receiving electromagnetic radiation from the substrate; as well as The third data is processed to obtain fourth data, wherein the fourth data comprises an indication of a temperature of the substrate, and wherein the first sensor is for receiving electromagnetic radiation of a first wavelength range and the second sensor is for receiving electromagnetic radiation of a second wavelength range.

Images