Determining surface roughness and emissivity

Abstract

The system includes a radiation source configured to emit a radiation beam. The system further includes a first optical sensor configured to detect a first intensity of a first portion of the radiation beam reflected from a surface of the object. The system further includes a second optical sensor configured to detect a second intensity of a second portion of the radiation beam scattered by the surface of the object. The system further includes a processing device communicatively coupled to the first optical sensor and the second optical sensor. The processing device is configured to determine at least one of a roughness or an emissivity of the surface of the object based on a comparison of the first intensity and the second intensity.

Description

[Technical Field]

[0001] FIELD OF THE DISCLOSURE Embodiments of the present disclosure relate generally to determining the surface roughness and emissivity of an object, and more particularly to systems, methods, and devices for optically determining the surface roughness and emissivity of an object. [Background technology]

[0002] Emissivity is a fundamental property of materials. Particularly in semiconductor processing, accurately characterizing the surface emissivity and / or surface roughness for chamber components can directly affect the quality of processed substrates. Emissivity can be affected by various material parameters, including topography (e.g., surface roughness), reflectivity, etc. Summary of the Invention

[0003] The following is a simplified summary of the present disclosure to provide a basic understanding of some aspects of the disclosure. This summary is not an extensive overview of the disclosure. It is not intended to identify key or critical elements of the disclosure, nor to delineate the scope or claims of particular embodiments of the disclosure. Its sole purpose is to present some concepts of the disclosure in a simplified form as a prelude to the more detailed description that is presented later.

[0004] Some embodiments described herein involve a system including a radiation source configured to emit a radiation beam. The system further includes a first optical sensor configured to detect a first intensity of a first portion of the radiation beam reflected from the surface of the object. The system further includes a second optical sensor configured to detect a second intensity of a second portion of the radiation beam scattered by the surface of the object. The system further includes a processing device communicatively coupled to the first optical sensor and the second optical sensor. The processing device is configured to determine at least one of a roughness of the surface of the object or an emissivity of the surface of the object based on a comparison of the first intensity and the second intensity.

[0005] Additional or related embodiments described herein include a method that includes emitting a radiation beam from a radiation source. The method further includes detecting, with a first optical sensor, a first intensity of a first portion of the radiation beam that is reflected from a surface of a chamber component of a processing chamber. The method further includes detecting, with a second optical sensor, a second intensity of a second portion of the radiation beam that is scattered by the surface of the chamber component. The method further includes determining, via a processing device communicatively coupled to the first optical sensor and the second optical sensor, at least one of a surface roughness of the chamber component or an emissivity of the surface of the chamber component based on a comparison of the first intensity and the second intensity.

[0006] In a further embodiment, a non-transitory machine-readable storage medium includes instructions that, when executed by a processing device, cause the processing device to perform operations including receiving data associated with at least one of emissivity or roughness of a surface of a chamber component of a processing chamber. The operations further include inputting the data associated with at least one of emissivity or roughness of the surface of the chamber component into a trained machine learning model. The operations further include receiving output from the trained machine learning model including predicted substrate process results. The predicted substrate process results correspond to future substrates to be processed in a processing chamber using the chamber component.

[0007] In accordance with these and other aspects of the present disclosure, numerous other features are also provided. Other features and aspects of the present disclosure will become more fully apparent from the following detailed description, claims, and accompanying 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 references indicate similar elements. It should be noted that various references in this disclosure to "an embodiment" or "one embodiment" do not necessarily refer to the same embodiment, but rather that such references mean at least one. [Brief explanation of the drawings]

[0009] [Figure 1A] 1 is a simplified side view of a system for optically determining emissivity and / or surface roughness of an object, according to an embodiment of the present disclosure. FIG. [Figure 1B] 1 is a simplified side view of a system for optically determining emissivity and / or surface roughness of an object, according to an embodiment of the present disclosure. FIG. [Figure 2] 1 illustrates a cross-sectional view of one embodiment of a processing chamber. [Figure 3] FIG. 1 illustrates an exemplary computer system architecture according to aspects of the present disclosure. [Figure 4] FIG. 1 illustrates a model training and model application workflow for determining predicted processed substrate outcomes, according to aspects of the present disclosure. [Figure 5A] 1 is a flowchart of a method for generating a training dataset for training a machine learning model, according to an aspect of the present disclosure. [Figure 5B] 1 is a flowchart of a method for generating predicted processed substrate outcomes using a trained machine learning model, according to an aspect of the present disclosure. [Figure 6] 1 is a flowchart of a method for optically determining the emissivity and / or surface roughness of an object, according to an embodiment of the present disclosure. [Figure 7] 1 is a diagrammatic representation of a machine, an exemplary form of computing device, capable of executing a set of instructions to cause the machine to perform any one or more of the techniques discussed herein. DETAILED DESCRIPTION OF THE INVENTION

[0010] Embodiments of the present disclosure are directed to systems and methods for determining surface roughness and emissivity. Process results of a manufacturing process depend on many factors, including process recipes and chamber component conditions. For example, process results can vary across the surface of a substrate based on the emissivity and / or surface roughness of components of a processing chamber used to perform a process (e.g., a deposition process, an etch process, etc.) on the substrate. For example, process results can vary across the surface of a substrate based on showerhead conditions, lid conditions, nozzle conditions, substrate support conditions that support the substrate, chamber liner conditions, pump and / or valve conditions, etc. The emissivity and / or surface roughness of one or more of these components can directly affect the quality of a film deposited on a substrate. The emissivity of an object (e.g., a chamber component) is also affected by various factors, including topography (e.g., surface roughness). Therefore, it can be useful to classify the surface roughness along with the emissivity of an object.

[0011] Typically, the wavelength range in which the emissivity of chamber components has the greatest impact on the quality of processed substrates is the mid-infrared (mid-IR), specifically the 3-5 μm range. Conventional emissometers (e.g., tools for measuring emissivity) typically measure and report emissivity within this wavelength range. These conventional emissometers operate on the principle that, for a given sample, a direct relationship exists between emissivity and reflected radiation (e.g., reflected by the surface of the object being measured). Thus, conventional emissometers operate by illuminating the object with light from a line source and collecting the reflected light from the object's surface. The reflected light is detected and then reported.

[0012] Conventional systems and methods for detecting the emissivity of an object have several drawbacks. First, conventional systems offer little or no control over the size of the area illuminated by the light source (e.g., "spot size"). Therefore, conventional systems and methods are ineffective for analyzing small surface areas or geometries.

[0013] Second, and more relatedly, conventional systems utilize relatively weak radiation from an omnidirectional radiation source (e.g., through an aperture) to illuminate the surface of an object. The omnidirectional radiation of conventional systems contributes to limited collection of reflected light (e.g., reflected radiation). Therefore, conventional systems are inherently susceptible to noise and cannot provide the accuracy requirements for characterizing the geometries of small objects (e.g., less than 1,000 microns). To increase accuracy, conventional systems may slow the measurement process and utilize certain techniques to increase the signal-to-noise ratio. To increase the signal-to-noise ratio, some conventional systems use a larger aperture to pass radiation to the object, but as discussed above, this introduces system error and increases the spot size.

[0014] Aspects and embodiments of the present disclosure address these and other shortcomings of conventional systems by providing a system (e.g., an optical measurement tool) for detecting the emissivity and / or surface roughness of an object. In some embodiments, the system includes a radiation source, such as a supercontinuum laser operating in the mid-IR range, that emits a radiation beam (e.g., a laser beam). The radiation beam can be directed toward the surface of the object by one or more mirrors and / or lenses. In some embodiments, the lenses focus the radiation beam to a "spot" on the surface of the object. The surface of the object reflects and / or scatters a portion of the radiation beam. In some embodiments, a reflected portion having a first intensity is reflected back into the system and detected by a photodetector of the system. In some embodiments, a scattered portion having a second intensity is collected by the system (e.g., a reflective objective such as a Schwarzschild objective) and detected by another photodetector of the system. A processing device (e.g., a computing device, etc.) determines the surface roughness and / or emissivity of the object based on comparing the intensity of the reflected radiation (e.g., a first intensity) to the intensity of the scattered radiation (e.g., a second intensity).

[0015] Embodiments of the present disclosure offer advantages over the conventional systems described above. In particular, some embodiments described herein detect emissivity with greater accuracy by providing a radiation source that emits a radiation beam rather than the omnidirectional source of conventional systems. The radiation beam is stronger (e.g., has greater intensity) and more focused, thus providing a greater intensity of reflected and / or scattered radiation from the object's surface. This greater intensity makes the system less susceptible to signal noise and allows for greater accuracy. Additionally, some embodiments described herein can simultaneously detect and characterize both the emissivity and surface roughness of the measured object. By using two photodetectors, both reflected radiation (e.g., "bright field") and scattered radiation (e.g., "dark field") can be measured to provide data for characterizing the object's emissivity and surface roughness. This data can be used (e.g., via machine learning techniques described later herein) to predict substrate process results for a substrate to be processed in a processing chamber using the measured chamber part (e.g., the measured object). Additionally, the radiation beam used in the embodiments described herein allows for faster measurement of emissivity compared to conventional systems.

[0016] 1A shows a simplified side view of a system 100A for optically determining the emissivity and / or surface roughness of an object, in accordance with aspects of the present disclosure. In some embodiments, the system 100A is an optical measurement tool (e.g., an emissometer).

[0017] System 100A includes a radiation source 102 configured to emit a radiation beam 103, which may be a focused radiation beam. In embodiments, radiation source 102 is a laser, such as a semiconductor laser (e.g., using a laser diode). Other types of lasers that may be used include gas lasers, solid-state lasers, fiber lasers, and liquid lasers. In some embodiments, radiation source 102 is a supercontinuum laser. In an optical system, a supercontinuum is formed when a set of nonlinear processes act together on a pump beam, causing severe spectral broadening of the original pump beam. The result is a continuous spectrum. In some embodiments, radiation source 102 is a supercontinuum laser configured to operate in the mid-IR range (e.g., radiation source 102 is a mid-IR supercontinuum laser). In some embodiments, radiation source 102 emits electromagnetic radiation having a wavelength in the range of 1 to 6 μm. In further embodiments, radiation source 102 emits radiation having a wavelength in the range of 3 to 5 μm. In some embodiments, radiation beam 103 is a collimated beam (e.g., radiation source 102 is configured to emit a collimated beam). In some embodiments, radiation beam 103 has a diameter of about 1 millimeter to about 10 millimeters. In some embodiments, radiation beam 103 has a diameter of about 5 millimeters.

[0018] In some embodiments, the radiation beam 103 is directed through a polarizing filter 104 (also called a polarizer). The polarizing filter 104 can be positioned along the optical axis of the radiation beam 103 between the radiation source 102 and the beam splitter 106. In some embodiments, the polarizing filter 104 is configured to polarize the radiation beam 103 emitted from the radiation source 102. In some embodiments, the polarizing filter 104 linearly polarizes the radiation beam 103. In some embodiments, the polarizing filter 104 is omitted.

[0019] Beam splitters (such as beam splitter 106) are often polarization-dependent, meaning that the ratio of reflected to transmitted radiation depends on the polarization and wavelength of the incoming radiation. Although the radiation beam 103 emitted by the radiation source 102 is substantially unpolarized, there may be some residual and varying polarization preference between the horizontal and vertical directions. Under such conditions, there may be a slight modulation in the amount of radiation transmitted by the beam splitter 106 and / or the polarization of the radiation. This modulation may introduce errors into the normalization process associated with the optical sensor 108 described herein. Therefore, in some embodiments, the inclusion of a polarizing filter 104 converts any changes in the instantaneous polarization of the radiation beam 103 into amplitude variations that affect the radiation transmitted by the beam splitter 106 and the radiation reflected by the beam splitter 106 in a similar manner (e.g., the amplitude of both the transmitted and reflected radiation increases or decreases during a change in the polarization of the radiation beam 103). Further functionality of beam splitters is described later in this specification.

[0020] In some embodiments, the radiation beam 103 passes through a beam splitter 106 (optionally after passing through a polarizing filter 103). In some embodiments, a one-way mirror is used instead of a beam splitter.

[0021] In some embodiments, all or substantially all of the radiation beam 103 passes through the beam splitter 106. Alternatively, a portion of the radiation beam can be reflected by the beam splitter 106 and directed towards the light sensor 108, while another portion of the radiation beam is transmitted by the beam splitter (e.g., towards the lens 110). In some embodiments, a majority of the intensity of the radiation beam 103 is transmitted through the beam splitter 106, while a small portion (e.g., 2-10%) of the intensity of the radiation beam 103 is reflected towards the light sensor 108. In some embodiments, a substantially equal intensity of the radiation beam 103 is transmitted through the beam splitter 106 and reflected (e.g., by the beam splitter 106) towards the light sensor 108.

[0022] Optical sensor 108 can be configured to detect the intensity of the portion of the radiation beam reflected by beam splitter 106. Optical sensor 108 (as well as optical sensors 116, 130) can be or include a sensor having one or more (e.g., a matrix) sensing elements. In some embodiments, the sensing elements are charge-coupled device (CCD) sensors. In some embodiments, the sensing elements are complementary metal-oxide semiconductor (CMOS)-type image sensors. In some embodiments, the sensing elements are mercury cadmium telluride (HgCdTe) photoconductive detectors. Other types of image sensors known to those skilled in the art can also be used for optical sensors 108, 116, 130. In some embodiments, optical sensors 108, 116, and / or 130 each include or are coupled to a galvanometer for measuring a current induced by exposure to radiation.

[0023] As described later herein, the intensity detected by light sensor 108 can be used to normalize the intensity of the radiation detected by light sensor 116 and / or light sensor 130. For example, fluctuations in the intensity of the radiation detected by light sensor 108 can be used to attenuate fluctuations in the intensity of the radiation output by radiation source 102 and detected by light sensor 116 and / or light sensor 130. Specifically, in some embodiments, the intensity of the radiation detected by light sensor 108 is directly related to the intensity of radiation beam 103, and therefore the intensity of the radiation detected by light sensor 108 can be used as a relative benchmark for light sensor 116 and light sensor 130. In some examples, fluctuations in the power of radiation beam 103 output by source 102 can be detected by light sensor 108. In some embodiments, the signal output by light sensor 108 is used to stabilize system 100. In embodiments, fluctuations in the measurement system (e.g., fluctuations between measurements of the same radiation intensity) can be reduced based on the signal output by light sensor 108. In some embodiments, the signal output by the optical sensor 108 may reduce the variation in the measured value (e.g., emissivity and / or surface roughness) to less than 0.1%. Thus, in embodiments, the use of the beam splitter 106 and the optical sensor 108 may increase the stability of the system 100 such that the variation is less than 0.1%. In other embodiments, the variation may be less than 0.2%, less than 0.3%, less than 0.4%, less than 0.5%, less than 0.6%, less than 0.6%, less than 0.7%, less than 0.8%, less than 0.9%, or less than 1.0%.

[0024] The use of the polarizing filter 104 described above further improves the stability of the system 100. In particular, there may be slight variations in the polarization of the radiation output by the radiation source 102. The amount of the radiation beam 103 that passes through the beam splitter 106 and the amount of the radiation beam 103 that is reflected by the beam splitter 106 may depend to some extent on the polarization. Therefore, slight variations in polarization may be detected as variations in the intensity detected by one or more of the optical sensors 108, 116, 130, which may contribute to instability of the system. However, by introducing the polarizing filter 104, variations in the polarization of the radiation beam 103 are eliminated, resulting in increased system measurement stability (reduced measurement fluctuations).

[0025] In some embodiments, the beam splitter 106 transmits the radiation beam (e.g., a portion of the radiation beam, a majority of the radiation beam, all of the radiation beam except for the portion reflected toward the photosensor 108, etc.) toward one or more lenses 110, which may be located on the optical axis of the system. In some embodiments, the lens 110 is a doublet lens. In some embodiments, the lens 110 is an objective lens. The lens 110 may be configured to focus the radiation beam to expand and / or reduce the diameter of the radiation beam. The lens 110 may have a focal length of about 50 millimeters to about 100 millimeters. In some embodiments, the lens 110 may have a focal length of about 75 millimeters. In some embodiments, the lens 110 may focus the radiation beam to a spot size of less than about 200 microns in diameter on the surface of the object 114. In some embodiments, the lens 110 focuses the radiation beam 103 to a spot size of less than 300 microns. In some embodiments, the lens 110 focuses the radiation beam 103 to a spot size of less than 500 microns. In some embodiments, the spot size is approximately 50 microns to 90 microns. The spot size can depend on the focal length of the lens 110, the wavelength of the radiation beam 103, and the initial width of the radiation beam 103. In some embodiments, the spot size can be variable. For example, in some embodiments, the lens 110 is attached to an actuator or other translation mechanism that can move the position of the lens 110 along the optical axis of the system 100. Such movement of the position of the lens 110 can change the focus setting of the optical system. In some embodiments, an actuator coupled to the lens 110 can move the lens 110 along the optical axis to change the spot size on the surface of the object 114 being measured.

[0026] In some embodiments, object 114 is positioned on support 135. Support 135 may be a movable stage. In some embodiments, support 135 may be movable about one or more axes (e.g., one axis, two axes, three axes, etc.). For example, support 135 may be movable in an XY plane that is orthogonal (e.g., substantially orthogonal) to the direction of the incoming radiation beam. In some embodiments, support 135 is rotatable about one or more axes. In some embodiments, support 135 may have six or fewer degrees of freedom.

[0027] In some embodiments, the radiation beam is transmitted by lens 110 toward angled mirror 112, which reflects the focused radiation beam onto the surface of object 114. In some embodiments, the surface of object 114 is at least partially emissive and can have surface roughness. In some examples, the surface of object 114 can reflect radiation and / or scatter radiation. The amount of reflected and / or scattered radiation can depend on one or more properties of the object's surface, such as roughness, reflectivity, absorbance, or refractive index. The reflected and / or scattered radiation can be measured (e.g., via system 100). In some embodiments, object 114 is a chamber component of a substrate processing chamber, such as a component of processing chamber 200 in FIG. 2. In some embodiments, the surface of object 114 to be measured can be substantially orthogonal to the incoming radiation beam. Thus, if the object has a non-flat surface, the orientation of the object relative to system 100 can be changed when different portions of the object are measured, such that a normal to the point on the object's surface being measured is aligned with the rays of radiation beam 103.

[0028] In some embodiments, the mirror 112 is coupled to the bottom surface (e.g., as shown) of the convex mirror 124 of the reflective objective lens 120. The arrangement and / or size of the mirror 112 may be such that scattered radiation (e.g., from the surface of the object 114) is not blocked by the mirror 112. A first portion of the radiation beam may be reflected by the surface of the object 114 towards the mirror 112. The first portion of the radiation beam may be referred to as a reflected radiation beam. The reflected radiation beam may then be reflected from the mirror 112, return through the lens 110, be reflected from the beam splitter 106 and directed towards the photosensor 116.

[0029] In some embodiments, the beam splitter 106 reflects the reflected portion of the radiation beam towards the optical sensor 116. The optical sensor 116 can be configured to detect the intensity of the portion of the radiation beam that is reflected by the surface of the object 114 (i.e., the reflected radiation beam). In some embodiments, the intensity of the radiation detected by the optical sensor 116 (e.g., the intensity of the reflected radiation beam) is related to the emissivity and / or surface roughness of the surface of the object 114.

[0030] In some embodiments, radiation scattered by the surface of object 114 (e.g., indicated by dashed arrows in FIG. 1 and referred to as the scattered radiation beam) is collected by a reflective objective lens 120, referred to as a collector. The reflective objective lens 120 may include a concave mirror inner surface 122 and a convex mirror 124 positioned below or adjacent to the inner surface 122. The scattered radiation beam may be collected by the concave mirror inner surface 122 and reflected toward the convex mirror 124. In some embodiments, the convex mirror 124 forms a dark region in the center of the reflective objective lens 120. In some embodiments, the convex mirror 124 reflects the collected radiation from the scattered radiation beam through an opening 126 in the concave mirror inner surface 122 toward the optical sensor 130. In some embodiments, the reflective objective lens 120 is a Schwarzschild objective. However, one skilled in the art will appreciate that other reflective objective lenses may also be used. In some embodiments, the optical sensor 130 is configured to detect the intensity of radiation (e.g., the scattered radiation beam) scattered by the surface of the object 114. In some embodiments, the intensity of the radiation detected by the optical sensor 130 (e.g., the intensity of the radiation scattered by the surface of the object 114) is related to the emissivity and / or surface roughness of the surface of the object 114.

[0031] In some embodiments, a system controller 160 (e.g., a computing device, a processing device, etc.) may be communicatively coupled to light sensor 108, light sensor 116, and / or light sensor 130. System controller 160 may be and / or include a computing device such as a personal computer, a server computer, a programmable logic controller (PLC), a microcontroller, a system-on-a-chip (SoC), etc. System controller 132 may include 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 devices may be complex instruction set computing (CISC) microprocessors, reduced instruction set computing (RISC) microprocessors, very long instruction word (VLIW) microprocessors, or processors implementing other instruction sets or combinations of instruction sets. The processing devices 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. System controller 132 may include data storage devices (e.g., one or more disk drives and / or solid-state drives), main memory, static memory, network interfaces, and / or other components. System controller 132 may execute instructions to implement any one or more of the techniques and / or embodiments described herein. These instructions may be stored on a computer-readable storage medium, which may include main memory, static memory, secondary storage, and / or a processing device (during execution of the instructions). System controller 132 may also be configured to allow an operator to input and display data, operational commands, and the like.

[0032] The system controller 160 can receive output signals from each of the optical sensors. In some embodiments, the system controller 160 can determine (e.g., via processing logic) the roughness and / or emissivity of the surface of the object 114 based on a comparison of the intensity of radiation detected by the optical sensor 116 and the intensity of radiation detected by the optical sensor 130. In some embodiments, the emissivity is equal to 1 minus the reflectivity of the surface of the object 114 (e.g., 1 - reflectivity). In some embodiments, the intensity of the reflected radiation (e.g., detected by the optical sensor 116) is related to the emissivity. For example, the emissivity can be considered to be the complement to the reflectivity. The reflectivity can be calculated by the ratio of the intensity of the reflected radiation beam (e.g., represented by the intensity of the radiation detected by the optical sensor 116) to the intensity of the radiation detected by the optical sensor 108. The reflectivity can indicate the emissivity of the surface of the object 114 by the relationship emissivity = 1 - reflectivity. In some embodiments, the ratio of the intensity of the scattered radiation to the intensity of the reflected radiation indicates the surface roughness.

[0033] In some examples, a higher intensity of reflected radiation (e.g., detected by optical sensor 116) compared to the intensity of scattered radiation (e.g., detected by optical sensor 130) can indicate lower emissivity and / or lower surface roughness of the surface of object 114. In some examples, a lower intensity of reflected radiation compared to the intensity of scattered radiation can indicate higher emissivity and / or higher surface roughness. In some examples, a higher intensity of scattered radiation (e.g., detected by optical sensor 130) compared to the intensity of reflected radiation can indicate higher surface roughness, and a lower intensity of scattered radiation compared to the intensity of reflected radiation can indicate lower surface roughness.

[0034] In some embodiments, the system controller 160 may determine that the surface roughness of the object 114 is related to the ratio of the intensity of the scattered radiation to the intensity of the reflected radiation. Thus, the processing device may determine the surface roughness of the object 114 based on the ratio of the intensity of the radiation detected by the optical sensor 130 to the intensity of the radiation detected by the optical sensor 116.

[0035] In some embodiments, as described herein above, the system controller 160 can determine the surface roughness and / or emissivity further based on the sensor data from the optical sensor 108. Specifically, the system controller 160 can determine a normalization factor based on the sensor data from the optical sensor 108. The normalization factor can be used to normalize the sensor data from the optical sensor 116 and / or the optical sensor 130. For example, variations in the amplitude of the radiation beam 103 may cause corresponding variations in the reflected radiation detected by the optical sensor 116 and / or the scattered radiation detected by the optical sensor 130. These variations may cause variations in the surface roughness and / or emissivity calculated by the system controller 160. However, variations in the amplitude of the radiation beam 103 may also be detected by the optical sensor 108. By determining the normalization factor based on the sensor data from the optical sensor 108 (e.g., if the sensor data corresponds to variations in the amplitude of the radiation beam 103), variations in the sensor data from the optical sensors 116 and 130 can be normalized (e.g., based on the normalization factor). The normalized sensor data can be used by system controller 160 to determine surface roughness and / or emissivity. In some embodiments, the normalization factor is proportional to the product of the intensity detected by optical sensor 108 multiplied by the target intensity. The output signal of optical sensor 116 and / or optical sensor 130 can be multiplied by the normalization factor to determine a corrected signal. In some embodiments, the normalization factor can account for frequency and / or phase mismatch between sensors, nonlinearities in the sensor measurements, and / or other non-idealities in system 100A.

[0036] In some embodiments, a surface roughness and / or emissivity map of the object 114 can be generated by the system 100A. The surface roughness and / or emissivity map can be generated by moving the object 114 relative to the incoming radiation beam (e.g., via the movable support 135) and determining the surface roughness and / or emissivity at various discrete points on the surface of the object. In some embodiments, the generated surface roughness and / or emissivity map can be based on measurements of the surface roughness and / or emissivity at various known points across the surface of the object 114. This map can be used to determine various predicted factors, as described later herein.

[0037] In some embodiments, system 100 includes a camera instead of or in addition to one or more components of system 100 A. In some examples, a camera operating in the mid-IR range can image the surface of object 114 to determine emissivity and / or roughness information of the surface of object 114.

[0038] FIG. 1B shows a simplified side view of a system 100B for optically determining emissivity and / or surface roughness according to aspects of the present disclosure. Features of system 200 numbered similarly to features of system 100 can have similar structure and / or function as described above in this specification. In some embodiments, system 100B includes a rotatable mirror 152 configured to direct the radiation beam toward lens 110. In some examples, the optical axis of radiation source 102 can be set approximately perpendicular (e.g., 90 degrees) to the optical axis of lens 110. In some embodiments, rotatable mirror 152 is positioned substantially in the focal plane of lens 110. In some embodiments, rotatable mirror 152 can reflect the radiation beam from the radiation source toward lens 110 at an angle. In response to rotation of rotatable mirror 152 about an axis orthogonal to the optical axis of lens 110 (e.g., an axis extending above and below the plane of the paper or into and out of the plane of the paper), rotatable mirror 152 can move the radiation beam in a periodic motion across the surface of object 114. For example, the lens 110 can convert angular motion of the rotatable mirror 152 into lateral motion (e.g., periodic lateral motion) of the radiation beam. In some examples, rotation of the rotatable mirror 152 moves the radiation beam back and forth periodically (e.g., in a periodic motion) across the surface of the object 114. The back and forth motion of the radiation beam can allow the surface of the object 114 to be scanned.

[0039] In some embodiments, as the object 114 is slowly moved in the Y direction of the XY plane by the support 135, the radiation beam is rapidly moved back and forth in the X direction (e.g., of the XY plane) to scan the surface of the object 114. Data collected during the scan (e.g., reflected and / or scattered radiation intensity) can be used to determine (e.g., by the system controller 160) an emissivity surface profile map and / or a surface roughness profile map (e.g., one or more profile maps) of the object 114.

[0040] FIG. 2 is a cross-sectional view of a processing chamber 200 (e.g., a semiconductor processing chamber, a display processing chamber, etc.) having one or more chamber parts characterized using the system 100A of FIG. 1A or the system 100B of FIG. 1B according to an embodiment of the present disclosure. The processing chamber 200 can be used for processes in which a corrosive plasma environment having plasma processing conditions is provided. For example, the processing chamber 200 can be a chamber for a plasma etcher or plasma etch reactor, a plasma cleaner, etc. Other types of chambers can include deposition chambers, cleaning chambers, oxidation chambers, etc. Examples of chamber parts that can have characterized surface roughness and / or emissivity include the substrate support assembly 248, an electrostatic chuck (ESC), a ring (e.g., a process kit ring or a single ring), chamber walls, a base, a gas distribution plate, a showerhead 230, gas lines, a nozzle, a lid, a liner, a liner kit, a shield, a plasma screen, a flow equalizer, a cooling base, a chamber viewport, a chamber lid, etc. The chamber parts can be constructed from metals, metal alloys, ceramics, and any combination thereof. The chamber components can include coatings, such as plasma-resistant or corrosion-resistant coatings, and the surfaces of the coatings can be characterized using the system of Figures 1A-1B. The coatings can be deposited or grown via atomic layer deposition, plasma spray coating, chemical vapor deposition, ion-assisted deposition, sputtering, physical vapor deposition, electroplating, anodization, etc.

[0041] In one embodiment, the processing chamber 200 includes a chamber body 202 and a showerhead 230 that enclose an interior volume 206. The showerhead 230 may include a showerhead base and a showerhead gas distribution plate. Alternatively, in some embodiments, the showerhead 230 may be replaced by a lid and a nozzle. The chamber body 202 may be fabricated from aluminum, stainless steel, or other suitable materials. The chamber body 202 generally includes a sidewall 208 and a bottom 210. Any of the showerhead 230 (or the lid and / or nozzle), the sidewall 208, and / or the bottom 210 may include a characterized coating.

[0042] An outer liner 216 may be disposed adjacent the sidewall 208 to protect the chamber body 202. The outer liner 216 may be characterized. In one embodiment, the outer liner 216 is fabricated from aluminum oxide.

[0043] An exhaust port 226 can be defined in the chamber body 202, and the exhaust port 226 can couple the interior volume 206 to a pumping system 228. The pumping system 228 can include one or more pumps and a throttle valve utilized to evacuate and regulate the pressure of the interior volume 206 of the processing chamber 200.

[0044] The showerhead 230 can be supported on the sidewalls 208 and / or top of the chamber body 202. In some embodiments, the showerhead 230 (or lid) can be opened to allow access to the interior volume 206 of the processing chamber 200 and can provide a seal for the processing chamber 200 when closed. A gas panel 258 can be coupled to the processing chamber 200 to provide process gases and / or cleaning gases to the interior volume 206 through the showerhead 230 or lid and nozzles. The showerhead 230 is used for processing chambers used for dielectric etching (etching of dielectric materials). The showerhead 230 can include a gas distribution plate (GDP) having multiple gas delivery holes 232 throughout the GDP. The showerhead 230 can include an aluminum showerhead base or a GDP bonded to an anodized aluminum showerhead base. The GDP 233 can be made of Si or SiC, or can be a ceramic such as YO, AlO, or YAG. The showerhead 230 and delivery holes 232 can be characterized using system 100 or 150, in embodiments. For processing chambers used for conductor etching (etching conductive materials), a lid can be used rather than a showerhead. The lid can include a central nozzle that fits into the lid's central hole. The lid can be a ceramic, such as Al2O3, YO3, YAG, or a ceramic compound including Y4Al2O9, and a solid solution of YO3-ZrO2. The nozzle can also be a ceramic, such as YO3, YAG, or a ceramic compound including Y4Al2O9, and a solid solution of YO3-ZrO2. According to one embodiment, the lid, showerhead 230 (e.g., including the showerhead base, GDP, and / or gas delivery conduits / holes), and / or nozzle can be characterized using system 100 or 150.

[0045] A substrate support assembly 248 is disposed below the showerhead 230 or lid within the interior volume 206 of the processing chamber 200. The substrate support assembly 248 holds the substrate 244 during processing and may include an electrostatic chuck bonded to a cooling plate.

[0046] An inner liner may be located around the periphery of the substrate support assembly 248. The inner liner may be a material that is resistant to halogen-containing gases, such as those discussed with reference to the outer liner 216. In one embodiment, the inner liner 218 may be fabricated from the same material as the outer liner 216. Additionally, in an embodiment, the inner liner 218 may also be characterized using the system 100 or 150.

[0047] 3 illustrates an exemplary computer system architecture 300 according to aspects of the present disclosure. The computer system architecture 300 includes a client device 320, manufacturing equipment 322, an optical measurement tool 326, a prediction server 312 (e.g., for generating prediction data, providing model adaptation, using a knowledge base, etc.), and a data store 350. The prediction server 312 can be part of a prediction system 310. The prediction system 310 can further include server machines 370 and 380. In some embodiments, the computer system architecture 300 can include or be part of a manufacturing system for processing substrates or the optical measurement tool 326. Further details regarding the optical measurement tool 326 are provided with respect to FIGS. 1A-1B.

[0048] Components of client device 320, manufacturing equipment 322, optical measurement tool 326, prediction system 310, and / or data store 350 can be coupled to each other via network 340. In some embodiments, network 340 is a public network that provides client device 320 access to prediction server 312, data store 350, and other publicly available computing devices. In some embodiments, network 340 is a private network that provides client device 320 access to manufacturing equipment 322, optical measurement tool 326, data store 350, and / or other privately available computing devices. Network 340 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, cloud computing networks, and / or combinations thereof.

[0049] The client device 320 may include computing devices such as a personal computer (PC), a laptop, a mobile phone, a smartphone, a tablet computer, a netbook computer, a network-connected television ("smart TV"), a network-connected media player (e.g., a Blu-ray player), a set-top box, an over-the-top (OTT) streaming device, an operator box, etc.

[0050] The manufacturing equipment 322 can fabricate products according to a recipe. In some embodiments, the manufacturing equipment 322 can include or be part of a manufacturing system that includes one or more stations (e.g., process chambers, transfer chambers, load locks, factory interfaces, etc.) configured to perform various operations on substrates.

[0051] The optical measurement tool 326 may be a tool (e.g., a system) for determining the emissivity and / or roughness of a surface of an object being measured. The optical measurement tool 326 may be configured to generate data associated with the emissivity and / or surface roughness of the object being measured by the optical measurement tool 326. In some embodiments, the optical measurement tool corresponds to system 100A or system 100B. In some embodiments, such data (e.g., emissivity data, surface roughness data, etc.) may be stored in a data store 350, where the data may be accessed (e.g., via network 340). The optical measurement tool 326 may include one or more sensors (e.g., multiple optical sensors) configured to detect radiation and generate data associated with the object being measured. In some embodiments, the optical measurement tool 326 includes a radiation source that provides a radiation beam used to irradiate a surface of the object being measured (e.g., a chamber component of a substrate processing chamber of the manufacturing equipment 322, etc.). Radiation reflected and / or scattered by the surface of the object may be detected by an optical sensor of the optical measurement tool 326. In some embodiments, the optical measurement tool 326 can generate emissivity data and / or surface roughness data based on the intensity of reflected and / or scattered radiation detected by the optical sensor. In some embodiments, the optical measurement tool 326 can generate a surface roughness and / or emissivity profile map of the measured object surface by measuring the emissivity and / or surface roughness at multiple locations on the surface of the measured object. In some embodiments, the optical measurement tool 326 can be included in a system used to manufacture parts (e.g., process chamber parts) of the manufacturing equipment 322.

[0052] The data store 350 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 store 350 can include multiple storage components (e.g., multiple drives or multiple databases) that can span multiple computing devices (e.g., multiple server computers). The data store 350 can store emissivity data and surface roughness data (e.g., generated by the optical measurement tool 326).

[0053] One or more portions of data store 350 can be configured to store data that is not accessible to users of the manufacturing system. In some embodiments, all data stored in data store 350 can be inaccessible to manufacturing system users. In other or similar embodiments, a portion of the data stored in data store 350 is inaccessible to users, while another portion of the data stored in data store 350 is accessible to users. In some embodiments, the inaccessible data stored in data store 350 is encrypted using an encryption mechanism unknown to the users (e.g., the data is encrypted using a private encryption key). In other or similar embodiments, data store 350 can include multiple data stores, with data that is inaccessible to users stored in a first data store and data that is accessible to users stored in a second data store.

[0054] In some embodiments, prediction system 310 includes server machine 370 and server machine 380. Server machine 370 includes training set generator 372 capable of generating a training dataset (e.g., a set of data inputs and a set of target outputs) for training, validating, and / or testing a machine learning model 390 or a set of machine learning models 390. Some operations of training set generator 372 are described in more detail below with respect to Figures 4 and 5A. In some embodiments, training set generator 372 can partition the training data into a training set, a validation set, and a test set.

[0055] The server machine 380 may include a training engine 382. An engine may refer to hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, a processing device, etc.), software (e.g., instructions executed on a processing device, a general-purpose computer system, or a dedicated machine), firmware, microcode, or a combination thereof. The training engine 382 may be capable of training one machine learning model 390 or a set of machine learning models 390. The machine learning model 390 may refer to a model artifact resulting from the training engine 382's use of training data. The training data may include training inputs and corresponding target outputs (correct responses for each training input). The training engine 382 may discover patterns in the training data that map the training inputs to target outputs (predicted responses). The training engine 382 may then ultimately provide a machine learning model 390 that captures these patterns. The machine learning model 390 may include a linear regression model, a partial least squares regression model, a Gaussian regression model, a random forest model, a support vector machine model, a neural network, a ridge regression model, etc. In some embodiments, machine learning model 390 is a physics-based model instead of or in addition to being a machine learning model.

[0056] The training engine 382 may also be capable of validating the trained machine learning models 390 using a corresponding set of features of the validation set from the training set generator 372. In some embodiments, the training engine 382 may assign a performance grade to each of the set of trained machine learning models 390. The performance grade may correspond to the accuracy of each trained model, the speed of each model, and / or the efficiency of each model. The training engine 382 may select trained machine learning models 390 having a performance grade that satisfies performance criteria to be used by the prediction engine 314, according to some embodiments described herein. Further details regarding the training engine 382 are provided with respect to FIG. 5A .

[0057] The prediction server 312 includes a prediction engine 314 that can provide data from the optical metrology tools 326 (e.g., emissivity data and / or surface roughness data) as input to a trained machine learning model 390. The prediction engine can run the trained model 390 on the input to obtain one or more outputs. In embodiments, the trained model 390 is trained on training data that includes a surface profile map of roughness and / or emissivity of chamber parts and one or more quality metrics of one or more processed substrates. As described further with respect to FIG. 5B , in some embodiments, the prediction engine 314 processes the input data (e.g., the surface profile of roughness and / or emissivity of chamber parts) using the model 390 to predict substrate process results (e.g., one or more substrate quality metrics) for future substrates to be processed in the processing chamber using the chamber parts measured by the optical metrology tools 326.

[0058] It should be noted that in some other embodiments, the functionality of server machines 370 and 380 and prediction server 312 may be provided by more or fewer machines. For example, in some embodiments, server machines 370 and 380 may be combined into a single machine. In other embodiments, server machines 370 and 380 and / or prediction server 312 may be combined into a single machine. In general, functionality described in one embodiment as being performed by server machine 370, server machine 380, and / or prediction server 312 may also be performed on client device 320. Additionally, functionality attributed to particular components may also be performed by different or multiple components operating together.

[0059] 4 illustrates a model training workflow 405 and a model application workflow 417 for determining predicted processed substrate outcomes from surface profile maps of one or more chamber parts, according to one embodiment. The model training workflow 405 and the model application workflow 417 may be performed by processing logic executed by a processor of a computing device. One or more of these workflows 405, 417 may be performed, for example, by one or more machine learning models implemented on the processing device and / or other software and / or firmware executing on the processing device.

[0060] The model training workflow 405 is for training one or more machine learning models (e.g., deep learning models) to determine predicted substrate outcomes for substrates processed in a process chamber including one or more chamber parts with measured emissivity and / or roughness surface profiles. The model application workflow 417 is for applying the one or more trained machine learning models to perform substrate outcome assessments. Each of the part emissivity / roughness data 412 can include surface emissivity and / or roughness at multiple locations on a chamber part of a processing chamber. For example, each of the part emissivity / roughness data 412 can include an array of surface emissivity and / or surface roughness measurements for the corresponding chamber part. In some embodiments, the part emissivity / roughness data 412 includes one or more emissivity and / or roughness maps (e.g., profile maps) of the surface of the object (e.g., the surface of the chamber part). In some embodiments, the emissivity and / or roughness maps can be generated via system 100A or 100B as described hereinabove.

[0061] Various machine learning outputs are described herein. Specific numbers and arrangements of machine learning models are described and illustrated. However, it should be understood that the number and types of machine learning models used, as well as the arrangements of such machine learning models, can be modified to achieve the same or similar end results. Therefore, the arrangements of the machine learning models described and illustrated are merely examples and should not be construed as limiting.

[0062] In some embodiments, one or more machine learning models are trained to perform one or more substrate outcome estimation tasks. Each task may be performed by a separate machine learning model. Alternatively, a single machine learning model may perform each of the tasks or portions of the tasks. For example, a first machine learning model may be trained to determine substrate process results, and a second machine learning model may be trained to determine corresponding corrective actions. Additionally or alternatively, different machine learning models may be trained to perform different combinations of these tasks. In one example, one or several machine learning models may be trained. The trained machine learning (ML) model may be a single shared neural network with multiple shared layers and multiple separate higher-level output layers, each output layer outputting a different prediction, classification, identification, etc. For example, a first higher-level output layer may determine substrate process results based on input data corresponding to a first chamber part, and a second higher-level output layer may determine substrate process results based on input data corresponding to a second chamber part.

[0063] 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 recurrent layer that maps features to a target output space. A convolutional neural network (CNN), for example, hosts multiple layers of convolutional filters. Deep learning is a type of machine learning algorithm that uses 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 hierarchy of multiple layers, with different layers learning different levels of representation corresponding to different levels of abstraction. In deep learning, each level learns to transform its input data into slightly more abstract and complex representations. In particular, the deep learning process can learn which features naturally fit best into which levels. The "deep" in "deep learning" refers to the number of layers through which data is transformed. More precisely, deep learning systems have substantial Contribution Allocation Path (CAP) depth. A CAP is a chain of transformations from input to output. A CAP describes the potentially causal connections between input and output. For forward neural networks, the CAP depth can be the depth of the network, which can be the number of hidden layers plus one. For recurrent neural networks, where a signal can propagate through a layer more than once, the CAP depth is potentially unlimited.

[0064] Training a neural network can be accomplished in a supervised learning manner, which involves feeding a training data set of labeled inputs through the network, observing its outputs, defining an error (by measuring the difference between the output and the label value), and using techniques such as deep gradient descent and backpropagation to adjust the mass of the network across all of its layers and nodes to minimize the error. In many applications, repeating this process across many labeled inputs in the training data set results in a network that can provide the correct output when presented with inputs different from those present in the training data set.

[0065] For the model training workflow 405, a training dataset including hundreds, thousands, tens of thousands, hundreds of thousands, or more instances of part emissivity / roughness data 412 (e.g., surface emissivity / roughness maps) should be used to form the training dataset. The data may include, for example, chamber part emissivity measurements determined using a given number of measurements. In some embodiments, multiple measurements are performed to generate a surface emissivity map of the surface of the chamber part. This data may be processed to generate one or more training datasets 436 for training one or more machine learning models. The training data items in the training dataset 436 may include the part emissivity / roughness data 412, substrate results for substrates processed in a processing chamber using the measured chamber parts, and / or one or more images of the processed substrates.

[0066] To accomplish training, processing logic inputs a training data set 436 into one or more untrained machine learning models. Before inputting a first input to the machine learning models, the machine learning models can be initialized. Processing logic trains the untrained machine learning models based on the training data set to generate one or more trained machine learning models that perform the various operations described above. Training can be performed by inputting input data, such as part emissivity / roughness data 412, images, and / or processed substrate results, into the machine learning models one at a time.

[0067] A machine learning model processes this input to generate an output. An artificial neural network includes an input layer consisting of values ​​in the data points. The next layer is called the hidden layer, and each node in the hidden layer receives one or more of the input values. Each node includes parameters (e.g., masses) to apply to the input values. Thus, each node essentially inputs the input values ​​into a multivariate function (e.g., a nonlinear mathematical transformation) to produce an output value. The next layer can be another hidden layer or an output layer. In either case, the nodes in the next layer receive output values ​​from the nodes in the previous layer, and each node applies masses to those values ​​and then generates its own output value. This can be done at each layer. The final layer is the output layer, where there is one node for each class, prediction, and / or output that the machine learning model can produce.

[0068] Thus, the output may include one or more predictions or inferences (e.g., an estimate of processed substrate results for substrates processed in the process chamber in which the measured substrate was processed using a particular chamber part). Processing logic may compare the output estimated substrate results to past substrate results. Processing logic may determine an error (i.e., classification error) based on the difference between the estimated substrate results and the target substrate results. Processing logic may adjust the mass of one or more nodes in the machine learning model based on the error. An error term or delta may be determined for each node in the artificial neural network. Based on this error, the artificial neural network adjusts one or more of its parameters (masses for one or more inputs to the node) for one or more of its nodes. Parameters may be updated using a backpropagation method, such that nodes in the highest layer are updated first, followed by nodes in the next layer, and so on. The artificial neural network includes multiple layers of "neurons," each layer receiving as input values ​​from neurons in the previous layer. The parameters for each neuron include a mass associated with the values ​​received from each of the neurons in the previous layer. Accordingly, adjusting the parameters may include adjusting masses assigned to each of the inputs to one or more neurons in one or more layers within the artificial neural network.

[0069] After the model parameters are optimized, model validation can be performed to determine whether the model has improved and to determine the current accuracy of the deep learning model. After one or more training rounds, the processing logic can determine whether a stopping criterion has been met. The stopping criterion can be a target accuracy level, a target number of processed images from the training dataset, a target amount of change to the parameters relative to one or more previous data points, combinations thereof, and / or other criteria. In one embodiment, the stopping criterion is met when at least a minimum number of data points have been processed and at least a threshold accuracy has been achieved. The threshold accuracy can be, for example, 70%, 80%, or 90% accuracy. In one embodiment, the stopping criterion is met when the accuracy of the machine learning model stops improving. If the stopping criterion is not met, further training is performed. If the stopping criterion is met, training can be completed. After the machine learning model is trained, the model can be tested using a reserved portion of the training dataset. After one or more trained machine learning models 438 are generated, these machine learning models 438 can be stored in model storage 445 and added to the processed substrate results engine 430.

[0070] According to one embodiment, for the model application workflow 417, the input data 462 can be input into one or more processed substrate result determiners 467, each of which can include a trained neural network or other model. Additionally or alternatively, the one or more processed substrate result determiners 467 can apply image processing algorithms to determine the processed substrate result. The input data can include a chamber component surface emissivity and / or roughness profile map (e.g., measured / generated using an optical metrology tool described herein). The input data can additionally, optionally, include one or more images of the measured chamber component. Based on the input data 462, the processed substrate result determiner 467 can output one or more estimated processed substrate results 469. The processed substrate results 469 can include predicted qualities (e.g., thickness, uniformity, etc.) of one or more films to be deposited or etched on a substrate processed in a process chamber using the measured chamber component.

[0071] The action determiner 472 can determine one or more actions 470 to take based on the processed substrate results 469. In one embodiment, the action determiner 472 compares the processed substrate result estimates to one or more processed substrate result thresholds. If one or more of the processed substrate result estimates meet or exceed the processed substrate result thresholds, the action determiner 472 can determine that a chamber part replacement and / or a process parameter update is recommended for future substrate processing. In such cases, the action determiner 472 can output a recommendation or notification for a chamber part replacement and / or a process parameter update. In some embodiments, the action determiner 472 automatically updates the process parameters based on the processed substrate results 469 satisfying one or more criteria. In some examples, the processed substrate results 469 can include an estimated condition of a substrate after one or more processing operations. In some embodiments, the estimated condition can be used to determine one or more updates to the process parameters for future substrate processing in a processing chamber using the chamber part.

[0072] 5A is a flowchart of a method 500A for generating a training dataset for training a machine learning model to perform substrate outcome assessment, according to an aspect of the present disclosure. Method 500A is performed by processing logic, which may include hardware (circuitry, dedicated logic, etc.), software (such as running on a general-purpose computer system or a dedicated machine), firmware, or some combination thereof. In one embodiment, method 500A may be performed by a computer system, such as computer system architecture 300 of FIG. 3. In other or similar embodiments, one or more operations of method 500A may be performed by one or more other machines not shown.

[0073] At block 510, processing logic initializes the training set T to an empty set (e.g., {}).

[0074] At block 512, processing logic obtains substrate process result data associated with a substrate processed in a processing chamber of the manufacturing system (e.g., data associated with a surface of a film on the substrate, such as film thickness, uniformity, etc.). In some embodiments, processing logic obtains past substrate process result data corresponding to substrates processed in the processing chamber using one or more past chamber parts.

[0075] At block 514, processing logic acquires surface emissivity and / or surface roughness information for components contained within the processing chamber that processed the substrate. As described above, the surface emissivity and / or surface roughness information may be acquired by an optical measurement tool (e.g., optical measurement tool 326 of FIG. 3 ) or a system for optically determining emissivity and / or surface roughness (e.g., system 200 or system 200), as described herein. In some embodiments, the surface emissivity and / or surface roughness information may include a profile map of the surface of the chamber part being measured. In some embodiments, processing logic acquires historical chamber part surface roughness data and / or historical chamber part emissivity data corresponding to past measurements of past chamber parts.

[0076] At block 516, processing logic generates training inputs based on the data obtained from the chamber component surface emissivity and / or roughness at block 514. In some embodiments, the training inputs may include a normalized set of sensor data (e.g., normalized intensity of reflected and / or scattered radiation, normalized emissivity and / or surface roughness measurements, etc.).

[0077] At block 518, processing logic may generate target outputs based on the substrate process result data obtained at block 512. The target outputs may correspond to substrate result metrics (data indicative of the quality of the processed substrate) for substrates processed in the processing chamber.

[0078] At block 520, processing logic generates an input / output mapping. The input / output mapping refers to training inputs that include or are based on data for chamber parts and target outputs for the training inputs, where the target outputs identify substrate process results, and the training inputs are associated with (or mapped to) the target outputs. At block 522, processing logic adds the input / output mapping to a training set T.

[0079] At block 524, processing logic determines whether training set T includes a sufficient amount of training data for training the machine learning model. Note that in some embodiments, training set T may be determined to be sufficient based solely on the number of input / output mappings in the training set, while in some other embodiments, training set T may be determined to be sufficient based on one or more other criteria (e.g., the degree of diversity of the training examples) in addition to or instead of the number of input / output mappings. In response to determining that training set T includes a sufficient amount of training data for training the machine learning model, processing logic provides training set T for training the machine learning model. In response to determining that the training set does not include a sufficient amount of training data for training the machine learning model, method 500 returns to block 512.

[0080] At block 526, processing logic provides a training set T for training the machine learning model. In some embodiments, the training set T is provided to a training engine 382 of a server machine 380 (e.g., of FIG. 3 ) to perform training. In the case of a neural network, for example, input values ​​of a given input / output mapping (e.g., spectral data and / or chamber data for a previous substrate) are input to the neural network, and output values ​​of the input / output mapping are stored in output nodes of the neural network. The connection mass in the neural network is then adjusted according to a learning algorithm (e.g., backpropagation, etc.), and the procedure is repeated for other input / output mappings in the training set T. After block 526, the machine learning model (e.g., machine learning model 390 of FIG. 3 ) can be used to provide predicted substrate process results for substrates processed in a processing chamber using the measured chamber parts.

[0081] 5B is a flowchart of a method 500B for generating predicted processed substrate results using a trained machine learning model, according to an aspect of the present disclosure. Method 500B is performed by processing logic, which may include hardware (circuitry, dedicated logic, etc.), software (such as running on a general-purpose computer system or a dedicated machine), firmware, or some combination thereof. In one embodiment, method 500B may be performed by a computer system, such as computer system architecture 300 of FIG. 3. In other or similar embodiments, one or more operations of method 500B may be performed by one or more other machines not shown.

[0082] At block 552, processing logic receives data associated with the emissivity and / or roughness of a surface of a chamber component of the processing chamber. In some embodiments, the data is received from an optical measurement tool (e.g., optical measurement tool 326 of FIG. 3 ) or a system for optically determining emissivity and / or surface roughness (e.g., system 100A or system 100B) as described herein. The data may be raw sensor data or may be data that has been processed (e.g., by a processing device, a computing device, etc.) to determine the surface emissivity and / or roughness. In some embodiments, the data is in the form of one or more surface profile maps indicative of the surface emissivity and / or roughness.

[0083] At block 554, processing logic inputs the data received at block 552 into a trained machine learning model. In some embodiments, the trained machine learning model is trained using the techniques described herein with reference to Figures 3, 4, and / or 5A. The trained machine learning model can be trained with data inputs including historical surface roughness and / or surface emissivity data labeled with corresponding target output data including historical substrate process result data. The trained machine learning model can be trained to output one or more predicted substrate process results based on the data inputs associated with the surface emissivity and / or roughness of the chamber parts.

[0084] At block 556, processing logic receives output from the trained machine learning model including predicted substrate process results corresponding to future substrates to be processed in the processing chamber using the chamber part. In some embodiments, the surface emissivity and / or roughness of the chamber part may affect the results of substrates processed in the processing chamber. The predicted substrate process results may reflect such effects.

[0085] 6 is a flowchart of a method 600 for optically determining emissivity and / or surface roughness according to aspects of the present disclosure. Method 600 is performed by a system that may include hardware (such as circuitry described herein, dedicated logic, optical measurement tools, etc.), software (such as running on a general-purpose computer system or a dedicated machine), firmware, or some combination thereof. In one embodiment, method 600 may be performed by a computer system such as computer system architecture 300 of FIG. 3. In other or similar embodiments, one or more operations of method 600 may be performed by one or more other machines not shown.

[0086] At block 602, a radiation source of the system emits a radiation beam. In some embodiments, the radiation beam is a beam of infrared radiation in the mid-IR range (e.g., output by a laser). For example, the radiation beam can have a wavelength in the range of 1-6 μm. In another example, the radiation beam can have a wavelength in the range of 3-5 μm. In some embodiments, the radiation source is a mid-IR supercontinuum laser emitter configured to operate in the mid-IR range. Thus, in some embodiments, the radiation beam is a mid-IR infrared laser beam. In some embodiments, the radiation beam is directed toward a surface of an object via one or more mirrors, optical filters (e.g., polarizing filters), lenses, and / or beam splitters. The surface of the object can reflect a portion of the radiation beam and / or scatter a portion (e.g., another portion) of the radiation beam, at least in part due to the emissivity and / or roughness of the surface of the object. In some embodiments, the object is a chamber component of a substrate processing chamber.

[0087] At block 604, a first optical sensor of the system detects the intensity of a portion of the radiation beam reflected from a surface of the object (e.g., a chamber component). The intensity of the reflected radiation can be indicative of at least the emissivity and / or roughness of the object surface. In some embodiments, the reflected portion of the beam is directed to the first optical sensor via one or more mirrors, lenses, and / or beam splitters. In some examples, the reflected portion of the radiation beam retraces at least a portion of its path back toward the radiation source. The beam splitter can direct the reflected radiation from the path toward the optical sensor.

[0088] At block 606, a second optical sensor of the system detects the intensity of a portion of the radiation beam scattered by the surface of the object (e.g., a chamber component). The intensity of the scattered radiation can be indicative of at least the emissivity and / or roughness of the object surface. In some embodiments, the scattered radiation is collected by a reflective objective (e.g., a Schwarzschild objective) and directed (e.g., reflected and / or focused) toward the second optical sensor. In some embodiments, the reflective objective is positioned substantially above the object (e.g., as shown in FIGS. 1A and 1B). In some embodiments, one or more mirrors, optical filters, lenses, etc. can direct, process, manipulate, reflect, etc. the scattered radiation.

[0089] At block 608, a processing device communicatively coupled to the first and second optical sensors may determine (e.g., via processing logic) at least one of the surface roughness of the object (e.g., chamber part) or the emissivity of the surface of the object. In some embodiments, the processing device makes this determination based on a comparison of the intensity of the reflected radiation and the intensity of the scattered radiation, as described herein above. In some embodiments, manufacturing process parameters (e.g., manufacturing recipes, manufacturing operations, etc.) corresponding to the object are updated (e.g., adjusted) based on the measured roughness and / or measured emissivity. For example, a manufacturing process for the chamber part may be updated based on measured values ​​of the surface roughness and / or emissivity of the surface of the sample chamber part. In such an example, the measured values ​​may indicate that the sample chamber part does not meet target thresholds (e.g., target surface roughness threshold and / or target emissivity threshold). The update to the manufacturing process may be for manufacturing future chamber parts within the target thresholds according to the updated manufacturing process parameters.

[0090] In some embodiments, the processing device is communicatively coupled to a third optical sensor (e.g., a normalization sensor, such as optical sensor 108 of FIG. 1 ). The signal received from the third optical sensor can be used by the processing device to normalize the signals received from the first and second optical sensors (e.g., to normalize the intensity of reflected and / or scattered radiation). In some embodiments, a surface map of the object is generated by capturing multiple measurements at different locations on the object's surface. The surface map can indicate surface roughness and / or emissivity across the object's surface. In some embodiments, the surface map can be generated by multiple individual measurements on the object's surface. The map can alternatively be generated by a surface scanning operation (e.g., performed by system 100B of FIG. 1 ).

[0091] 7 shows a diagrammatic representation of a machine in the exemplary form of a computing device 700 capable of executing a set of instructions to cause the machine to perform any one or more of the techniques discussed herein. In alternative embodiments, the machine may be connected (e.g., networked) to other machines in a local area network (LAN), an intranet, an extranet, or the Internet. The machine may operate in the capacity of a server or a client machine in a client-server network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The machine may be a personal computer (PC), a tablet computer, a set-top box (STB), a personal digital assistant (PDA), a cellular phone, a web appliance, a server, a network router, switch, or bridge, or any machine capable of executing (sequentially or otherwise) a set of instructions that specify actions to be taken by the machine. Further, while only a single machine is shown, the term "machine" should also be taken to include any group of machines (e.g., computers) that individually or jointly execute a set (or sets) of instructions to perform any one or more of the techniques discussed herein. In an embodiment, computing device 700 may correspond to one or more of server machine 370, server machine 380, or prediction server 312, as described herein.

[0092] The exemplary computing device 700 includes a processing device 702, a main memory 704 (e.g., read-only memory (ROM), flash memory, dynamic random access memory (DRAM), e.g., synchronous DRAM (SDRAM), etc.), a static memory 706 (e.g., flash memory, static random access memory (SRAM), etc.), and a secondary memory (e.g., a data storage device 728), which communicate with each other via a bus 708.

[0093] The processing device 702 may represent one or more general-purpose processors, such as a microprocessor, a central processing unit, or the like. More specifically, the processing device 702 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 implementing other instruction sets, or a processor implementing a combination of instruction sets. The processing device 702 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, or the like. The processing device 702 may also be or include a system-on-chip (SoC), a programmable logic controller (PLC), or other type of processing device. The processing device 702 is configured to execute processing logic for performing the operations discussed herein.

[0094] Computing device 700 may further include a network interface device 722 for communicating with a network 764. Computing device 700 may also include a video display unit 710 (e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT)), an alphanumeric input device 712 (e.g., a keyboard), a cursor control device 714 (e.g., a mouse), and a signal generation device 720 (e.g., a speaker).

[0095] The data storage device 728 may include a machine-readable storage medium (or more specifically, a non-transitory computer-readable storage medium) 724 having stored thereon one or more sets of instructions 726 that implement any one or more of the techniques or functions described herein. A non-transitory storage medium refers to a storage medium other than a carrier wave. The instructions 726 may also reside, completely or at least partially, within the main memory 704 and / or within the processing device 702 during execution thereof by the computing device 700, the main memory 704, and the processing device 702, which also constitute computer-readable storage media.

[0096] While the exemplary embodiment depicts computer-readable storage medium 724 as a single medium, the term "computer-readable storage medium" should be interpreted to include a single medium or multiple media (e.g., centralized or distributed databases, and / or associated caches and servers) that store one or more sets of instructions. The term "computer-readable storage medium" should also be interpreted to include any medium capable of storing or encoding a set of instructions for execution by a machine that cause the machine to perform any one or more of the techniques of this disclosure. Thus, the term "computer-readable storage medium" should be interpreted to include, but is not limited to, solid-state memory and optical and magnetic media.

[0097] The above description sets forth numerous specific details, such as examples of specific systems, components, methods, etc., to provide a thorough understanding of some embodiments of the present disclosure. However, it will be apparent to those skilled in the art that at least some embodiments of the present disclosure can be practiced without these specific details. In other instances, well-known components or methods have not been described in detail or have been presented in simple block diagram form to avoid unnecessarily obscuring the present disclosure. Thus, the specific details described are merely exemplary. It is contemplated that particular embodiments may vary from these exemplary details and still be within the scope of the present disclosure.

[0098] Throughout this specification, a reference to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with that embodiment is included in at least one embodiment. Thus, the appearances of the phrase "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. In addition, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." When the term "about" or "approximately" is used herein, it is intended to mean that the stated nominal value is accurate to within ±10%.

[0099] Although the method operations herein are illustrated and described in a particular order, the order of the method operations may be changed, such that certain operations may be performed in reverse order, and certain operations may be performed at least partially concurrently with other operations. In alternative embodiments, instructions or sub-operations of separate operations may be performed intermittently and / or alternately.

[0100] It is understood that the above description is intended to be illustrative, and not limiting. Many other embodiments will be apparent to those skilled in the art upon reading and understanding the above description. Accordingly, the scope of the present disclosure should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.

Claims

1. a radiation source configured to emit a radiation beam; a first optical sensor configured to detect a first intensity of a first portion of the radiation beam reflected from a surface of the object; a second optical sensor configured to detect a second intensity of a second portion of the radiation beam scattered by the surface of the object; a processing device communicatively coupled to the first optical sensor and the second optical sensor, the processing device configured to determine at least one of a roughness of the surface of the object or an emissivity of the surface of the object based on a comparison of the first intensity and the second intensity. system.

2. The system of claim 1 , wherein the radiation source comprises a mid-infrared supercontinuum laser.

3. a mirror configured to direct the radiation beam towards the object; a reflective objective configured to receive the second portion of the radiation beam scattered by the surface of the object and to direct the second portion of the radiation beam scattered by the surface of the object to the second photosensor; The system of claim 1 further comprising:

4. The system of claim 3 , wherein the reflective objective lens comprises a Schwarzschild objective lens.

5. and a beam splitter disposed along the optical axis between the radiation source and the mirror, wherein the first portion of the radiation beam reflected from the surface of the object is reflected from the mirror, passes back through one or more lenses, and is directed by the beam splitter to the first photosensor. The system of claim 3.

6. further comprising a third optical sensor, wherein the beam splitter is configured to direct a portion of the radiation beam emitted by the radiation source towards the third optical sensor, the third optical sensor is configured to detect a third intensity of the portion of the radiation beam, and the processing device is configured to normalize the detected first intensity and the detected second intensity based on the detected third intensity. The system of claim 5.

7. and further comprising a polarizing filter disposed along the optical axis between the radiation source and the beam splitter, the polarizing filter configured to polarize the radiation beam emitted from the radiation source. The system of claim 6.

8. further comprising one or more lenses configured to focus the radiation beam, wherein the radiation beam is focused to a spot size of less than about 200 microns in diameter on the surface of the object. The system of claim 1 .

9. further comprising a rotatable mirror configured to direct the radiation beam emitted by the radiation source towards the one or more lenses, the rotatable mirror configured to move the radiation beam periodically across the surface of the object in response to rotation of the rotatable mirror. The system of claim 8.

10. 10. The system of claim 9, wherein the system detects at least one of emissivity or roughness with a measurement system variation of less than 0.1%.

11. emitting a radiation beam from a radiation source; detecting, with a first optical sensor, a first intensity of a first portion of the radiation beam reflected from a surface of a chamber component of the processing chamber; detecting, with a second optical sensor, a second intensity of a second portion of the radiation beam scattered by the surface of the chamber part; determining, via a processing device communicatively coupled to the first optical sensor and the second optical sensor, at least one of a roughness of the surface of the chamber part or an emissivity of the surface of the chamber part based on a comparison of the first intensity and the second intensity; A method comprising:

12. The method of claim 11 , wherein the radiation source comprises a mid-infrared supercontinuum laser.

13. detecting via a third optical sensor a third intensity of a portion of the radiation beam emitted by the radiation source that is directed towards the third optical sensor by a beam splitter arranged along an optical axis between the radiation source and a mirror, the mirror being configured to direct the radiation beam towards the chamber part; normalizing the detected first intensity and the detected second intensity based on the detected third intensity; The method of claim 11 further comprising:

14. inputting data associated with at least one of the emissivity or the roughness of the surface of the chamber component into a model; and receiving output from the model including predicted substrate process results, the predicted substrate process results corresponding to future substrates to be processed using the chamber component. The method of claim 11.

15. The method of claim 14 , wherein the model comprises a trained machine learning model.

16. training a machine learning model to create a trained machine learning model, wherein the machine learning model is trained with data inputs including one or more of historical chamber part surface roughness data, historical chamber part emissivity data, data corresponding to the roughness of the surface of the chamber part, and data corresponding to the emissivity of the surface of the chamber part, and the data inputs are labeled with corresponding target output data including historical substrate process result data corresponding to substrates processed by one or more historical chamber parts; The method of claim 11.

17. scanning the surface of the part with the radiation beam by periodically moving the radiation beam across the surface of the part in response to rotation of a rotatable second mirror. The method of claim 11.

18. A non-transitory machine-readable storage medium containing instructions that, when executed by a processing device, cause the processing device to perform operations, the operations including: receiving data associated with at least one of emissivity or roughness of a surface of a chamber component of a processing chamber; inputting the data associated with at least one of the emissivity or the roughness of the surface of the chamber component into a trained machine learning model; and receiving output from the trained machine learning model including predicted substrate process results, the predicted substrate process results corresponding to future substrates to be processed in the processing chamber using the chamber part.

19. 20. The non-transitory machine-readable storage medium of claim 18, wherein the trained machine learning model is trained with data inputs comprising one or more of historical chamber part surface roughness data, historical chamber part emissivity data, data corresponding to the roughness of the surface of the chamber part, and data corresponding to the emissivity of the surface of the chamber part, and the data inputs are labeled with corresponding target output data comprising historical substrate process result data corresponding to substrates processed by one or more historical chamber parts.

20. receiving data associated with at least one of the emissivity or the roughness of the surface of the chamber component; receiving first sensor data from a first optical sensor indicative of a first intensity of a first portion of the radiation beam reflected from the surface of the chamber component; receiving second sensor data from a second optical sensor indicative of a second intensity of a second portion of the radiation beam scattered by the surface of the chamber component; 20. The non-transitory machine-readable storage medium of claim 18, wherein at least one of the emissivity or the roughness of the surface is based on a comparison of the first intensity and the second intensity.

Images