Surface roughness and emissivity determination

Abstract

A system includes a radiation source configured to emit a beam of radiation. The system further includes a first optical sensor configured to detect a first intensity of a first portion of the beam of radiation reflected from a surface of an object. The system further includes a second optical sensor configured to detect a second intensity of a second portion of the beam of radiation scattered by the surface of the object. The system further includes a processing device communicatively coupled with 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] The embodiments of this disclosure generally relate to the determination of the surface roughness and emissivity of an object, and more specifically, to systems, methods, and apparatus for optically determining the surface roughness and emissivity of an object. Background Technology

[0002] Emissivity is a fundamental property of materials. In particular, in semiconductor processing, accurately characterizing the emissivity and / or surface roughness of chamber components can directly impact the quality of the processed substrate. Emissivity can be affected by various material parameters, including topography (such as surface roughness), reflectivity, etc. Summary of the Invention

[0003] The following is a simplified summary of this disclosure to provide a basic understanding of some aspects of it. This summary is not a comprehensive overview of this disclosure. It is not intended to identify key or essential elements of this disclosure, nor is it intended to define any scope of any particular implementation of this disclosure or any scope of the claims. Its sole purpose is to present some concepts of this disclosure in a simplified form as a prelude to the more detailed description that follows.

[0004] Some embodiments described herein cover a system comprising: a radiation source configured to emit a radiation beam. The system further comprises: a first optical sensor configured to detect a first intensity of a first portion of the radiation beam reflected from a surface of an object. The system further comprises: 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 comprises: 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 the roughness of the surface of the object or the 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 cover a method comprising: emitting a radiation beam from a radiation source. The method further comprises: detecting, by a first optical sensor, a first intensity of a first portion of the radiation beam reflected from a surface of a chamber component of a processing chamber. The method further comprises: detecting, by a second optical sensor, a second intensity of a second portion of the radiation beam scattered by the surface of the chamber component. The method further comprises: determining, via a processing device communicatively coupled to the first and second optical sensors, at least one of the roughness of the surface of the chamber component or the emissivity of the surface of the chamber component based on a comparison of the first and second intensities.

[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 the emissivity or roughness of a surface of a chamber component of a processing chamber. The operation further includes: inputting the data associated with at least one of the emissivity or roughness of the surface of the chamber component into a trained machine learning model. The operation further includes: receiving an output from the trained machine learning model, the output including predicted substrate process results. The predicted substrate process results correspond to a future substrate to be processed using the chamber component in the processing chamber.

[0007] Many other features are provided based on these and other aspects of this disclosure. These other features and aspects will become clearer from the following detailed description, claims, and drawings. Attached Figure Description

[0008] This disclosure is illustrated in the accompanying drawings by way of example rather than limitation, in which similar reference numerals indicate similar elements. It should be noted that different designations for “a / one” embodiments in this disclosure do not necessarily refer to the same embodiment, and such designation refers to at least one.

[0009] Figure 1A A simplified side view of a system for optically determining the emissivity and / or surface roughness of an object, according to an aspect of this disclosure, is shown.

[0010] Figure 1B A simplified side view of a system for optically determining the emissivity and / or surface roughness of an object, according to an aspect of this disclosure, is shown.

[0011] Figure 2 A cross-sectional view of one embodiment of the processing chamber is described.

[0012] Figure 3 An illustrative computer system architecture is described based on aspects of this disclosure.

[0013] Figure 4 The present disclosure illustrates a model training workflow and a model application workflow for determining the predicted results of the processed substrate.

[0014] Figure 5A This is a flowchart of a method for generating a training dataset for training a machine learning model, based on aspects of this disclosure.

[0015] Figure 5BThis is a flowchart of a method for generating predicted processed substrate results using a trained machine learning model, based on aspects of this disclosure.

[0016] Figure 6 This is a flowchart of a method for optically determining the emissivity and / or surface roughness of an object, according to an aspect of this disclosure.

[0017] Figure 7 A diagrammatic representation of a machine in the form of an example computing device is described, within which a set of instructions can be executed to cause the machine to perform any one or more of the methods discussed herein. Detailed Implementation

[0018] Embodiments of this disclosure relate to systems and methods for determining surface roughness and emissivity. The process outcome of a manufacturing process depends on many factors, including process formulation and chamber component conditions. For example, process outcomes across the entire substrate surface may vary based on the emissivity and / or surface roughness of the components of the processing chamber used to perform processes (such as deposition, etching, etc.) on the substrate. For example, process outcomes across the entire substrate surface may vary based on the conditions of the nozzle, the cap, the nozzle itself, the substrate support supporting the substrate, the chamber liner, the pump and / or valves, etc. The emissivity and / or surface roughness of one or more of these components can directly affect the quality of the thin film deposited on the substrate. The emissivity of an object (such as a chamber component) is also affected by various factors, including topography (such as surface roughness). Therefore, it may be useful to classify the surface roughness of an object together with its emissivity.

[0019] Typically, the wavelength range in which the emissivity of chamber components has the greatest impact on the quality of the processed substrate is the mid-infrared (mid-IR), particularly in the 3-5 micrometer range. Conventional emissometers (tools used to measure emissivity) typically measure and report emissivity within this wavelength range. These conventional emissometers operate on the principle that, for a given sample, there is a direct relationship between emissivity and reflected radiation (such as radiation reflected from the surface of the object under test). Therefore, a conventional emissometer operates by illuminating the object with light from a single source and collecting the reflected light from the object's surface. The reflected light is then detected and reported.

[0020] Traditional systems and methods for detecting the emissivity of objects have several drawbacks. First, traditional systems have virtually no control over the size of the area illuminated by the light source (e.g., the "spot size"). Therefore, traditional systems and methods cannot effectively analyze small surface areas or geometries.

[0021] Secondly, and relatedly, conventional systems utilize relatively weak radiation from an omnidirectional radiation source (e.g., via an aperture) to illuminate the object surface. The omnidirectional radiation of conventional systems results in limited collection of reflected light (such as reflected radiation). Therefore, conventional systems are inherently sensitive to noise and cannot provide the accuracy required to characterize small object geometries (e.g., less than 1,000 micrometers). To improve accuracy, conventional systems can slow down the measurement process and utilize certain techniques to improve the signal-to-noise ratio. To improve the signal-to-noise ratio, some conventional systems use larger apertures to transmit radiation to the object, but as mentioned above, this leads to system inaccuracies and an increased spot size.

[0022] The aspects and embodiments of this disclosure address the aforementioned and other drawbacks 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-infrared range, which emits a radiation beam (e.g., a laser beam). The radiation beam can be directed to the object surface by one or more mirrors and / or lenses. In some embodiments, the lens focuses the radiation beam onto a "point" on the object surface. The object surface reflects and / or scatters a portion of the radiation beam. In some embodiments, the reflected portion with a first intensity is reflected back to the system and detected by the system's optical detector. In some embodiments, the scattered portion with a second intensity is collected by the system (e.g., by a reflecting objective (e.g., a Schwarzschild objective)) and detected by another optical detector of the system. A processing device (e.g., a computing device) determines the surface roughness and / or emissivity of the object based on a comparison of the intensity of the reflected radiation (e.g., the first intensity) with the intensity of the scattered radiation (e.g., the second intensity).

[0023] Compared to the conventional systems described above, the embodiments of this disclosure offer significant advantages. In particular, some embodiments described herein detect emissivity with greater accuracy by providing a radiation source that emits a radiation beam, rather than an omnidirectional radiation source as in conventional systems. The radiation beam is stronger (e.g., more intense) and more focused, resulting in greater intensity of reflected and / or scattered radiation from the object's surface. This greater intensity reduces the system's sensitivity to signal noise, thereby achieving higher accuracy. Furthermore, some embodiments described herein can simultaneously detect and characterize both the emissivity and surface roughness of the object under test. By using two optical detectors, both reflected radiation (e.g., "bright field") and scattered radiation (e.g., "dark field") can be measured to provide data characterizing the object's emissivity and surface roughness. This data can be used (e.g., via machine learning techniques described below) to predict substrate process results for a substrate to be processed in a processing chamber using a component of the chamber under test (e.g., the object under test). Moreover, the radiation beam used in the embodiments described herein allows for faster emissivity measurement compared to conventional systems.

[0024] Figure 1A A simplified side view of a system 100A for optically determining the emissivity and / or surface roughness of an object, according to aspects of this disclosure, is shown. In some embodiments, system 100A is an optical measuring tool (such as an emissivity meter).

[0025] System 100A includes a radiation source 102 configured to emit a radiation beam 103, which may be a focused radiation beam. In embodiments, the radiation source 102 is a laser, such as a semiconductor laser (e.g., a laser using a laser diode). Other types of layers that may be used include gas lasers, solid-state lasers, fiber lasers, and liquid lasers. In some embodiments, the radiation source 102 is a supercontinuum laser. In optics, a supercontinuum is formed when a series of nonlinear processes act together on a pump laser beam, causing a significant broadening of the spectrum of the original pump laser beam. The result is a continuous spectrum. In some embodiments, the radiation source 102 is a supercontinuum laser configured to operate in the mid-infrared range (e.g., the radiation source 102 is a mid-infrared supercontinuum laser). In some embodiments, the wavelength of the electromagnetic radiation emitted by the radiation source 102 is in the range of 1-6 micrometers. In a further embodiment, the wavelength of the radiation emitted by the radiation source 102 is in the range of 3-5 micrometers. In some embodiments, the radiation beam 103 is a collimated beam (e.g., the radiation source 102 is configured to emit a collimated beam). In some embodiments, the diameter of the radiation beam 103 is between about 1 mm and about 10 mm. In some embodiments, the diameter of the radiation beam 103 is about 5 mm.

[0026] In some embodiments, the radiation beam 103 is guided through a polarizing filter 104 (also referred to as a polarizer). The polarizing filter 104 may be positioned between the radiation source 102 and the beam splitter 106 along the optical axis of the radiation beam 103. 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.

[0027] Typically, beamsplitters (such as beamsplitter 106) are polarization-dependent, meaning the ratio of reflected to transmitted radiation is a function of the polarization and wavelength of the incident radiation. While the radiation beam 103 emitted by radiation source 102 may be substantially unpolarized, some residual and varying polarization bias may exist between the horizontal and vertical directions. Under these conditions, the amount of radiation transmitted by beamsplitter 106 and / or the polarization of the radiated beam may exhibit slight modulation. This modulation may introduce errors during the normalization process associated with the optical sensor 108 described herein. Therefore, by including a polarizing filter 104 in some embodiments, any shift in the instantaneous polarization of the radiation beam 103 will be translated into amplitude fluctuations that will affect both the radiation transmitted by beamsplitter 106 and the radiation reflected by beamsplitter 106 in the same way (e.g., during periods when the polarization of the radiation beam 103 changes, the amplitudes of both transmitted and reflected radiation will increase or decrease). Further functionality of the beamsplitter will be described below.

[0028] 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.

[0029] In some embodiments, all or substantially all of the radiation beam 103 passes through beam splitter 106. Alternatively, a portion of the radiation beam may be reflected by beam splitter 106 and directed to optical sensor 108, while another portion of the radiation beam is transmitted through the beam splitter (e.g., directed towards lens 110). In some embodiments, the majority of the intensity of the radiation beam 103 is transmitted through beam splitter 106, while a small portion (e.g., 2-10%) of the intensity of the radiation beam 103 is reflected to optical sensor 108. In some embodiments, substantially equal amounts of radiation beam 103 are transmitted through beam splitter 106 and reflected (e.g., through beam splitter 106) to optical sensor 108.

[0030] Optical sensor 108 can be configured to detect the intensity of a portion of the radiation beam reflected by beam splitter 106. Optical sensor 108 (and optical sensors 116, 130) can be or include sensors having one or more (e.g., a matrix) sensing components. In some embodiments, the sensing components are charge-coupled device (CCD) sensors. In some embodiments, the sensing components are complementary metal-oxide-semiconductor (CMOS) type image sensors. In some embodiments, the sensing components 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 include or are each coupled to a galvanometer to measure current induced by receiving radiation.

[0031] As described below, the intensity detected by optical sensor 108 can be used to normalize the radiation intensity detected by optical sensor 116 and / or optical sensor 130. For example, changes in radiation intensity detected by optical sensor 108 can be used to attenuate changes in radiation intensity output by radiation source 102 and detected by optical sensor 116 and / or optical sensor 130. Specifically, the radiation intensity detected by optical sensor 108 can be used as a relative reference for optical sensor 116 and optical sensor 130 because, in some embodiments, the radiation intensity detected by optical sensor 108 is directly related to the intensity of radiation beam 103. In some examples, power fluctuations in the radiation beam 103 output by source 102 can be detected by optical sensor 108. In some embodiments, the signal output by optical sensor 108 is used to stabilize system 100. In embodiments, variations in the measurement system (e.g., variations between measurements of the same radiation intensity) can be reduced based on the signal output by optical sensor 108. In some embodiments, the signal output by optical sensor 108 can reduce variations in measured values ​​(such as emissivity and / or surface roughness) to less than 0.1%. Therefore, using the beam splitter 106 and the optical sensor 108 can improve the stability of the system 100, such that the variation in this embodiment 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%.

[0032] The use of the aforementioned polarization filter 104 further improves the stability of system 100. In particular, the polarized light emitted from radiation source 102 may exhibit slight fluctuations. The amount of radiation beam 103 passing through beam splitter 106 and the amount of radiation beam 103 reflected by beam splitter 106 may be somewhat dependent on the polarized light. Therefore, slight fluctuations in polarization may be detected as changes in intensity detected by one or more of the optical sensors 108, 116, and 130, leading to system instability. However, by introducing the polarization filter 104, any fluctuations in the polarization of the radiation beam 103 are removed, thereby improving the stability of system measurements (reducing measurement variations).

[0033] In some embodiments, beam splitter 106 directs a radiation beam (e.g., a portion of the radiation beam, most of the radiation beam, all of the radiation beam except for the portion reflected toward optical sensor 108, etc.) toward one or more lenses 110, which may be located on the optical axis of the system. In some embodiments, lens 110 is a double lens. In some embodiments, lens 110 is an objective lens. Lens 110 may be configured to focus the radiation beam to enhance the radiation beam and / or reduce the diameter of the radiation beam. The focal length of lens 110 may be from about 50 mm to about 100 mm. In some embodiments, the focal length of lens 110 may be about 75 mm. In some embodiments, lens 110 may focus the radiation beam onto the surface of object 114 to a spot size with a diameter of less than about 200 micrometers. In some embodiments, lens 110 may focus radiation beam 103 to a spot size of less than 300 micrometers. In some embodiments, lens 110 may focus radiation beam 103 to a spot size of less than 500 micrometers. In some embodiments, the spot size is from about 50 micrometers to 90 micrometers. The spot size can be a function of the focal length of lens 110, the wavelength of radiation beam 103, and the initial width of radiation beam 103. In some embodiments, the spot size can be variable. For example, in some embodiments, lens 110 is attached to an actuator or other translation mechanism that can move the position of lens 110 along the optical axis of system 100. This movement of the position of lens 110 can change the focus setting of the optical system. In some embodiments, an actuator coupled to lens 110 can move lens 110 along the optical axis to change the spot size on the surface of the object 114 under test.

[0034] In some embodiments, object 114 is positioned on support 135. Support 135 may be a movable platform. In some embodiments, support 135 may move about one or more axes (e.g., one axis, two axes, three axes, etc.). For example, support 135 may move in an XY plane orthogonal (e.g., substantially orthogonal) to the direction of the incident radiation beam. In some embodiments, support 135 may rotate about one or more axes. In some embodiments, support 135 may have six or fewer degrees of freedom.

[0035] In some embodiments, the radiation beam is transmitted through lens 110 toward an 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 may have surface roughness. In some examples, the surface of object 114 may reflect and / or scatter radiation. The amount of reflected and / or scattered radiation may depend on one or more properties of the object surface, such as roughness, reflectivity, absorptivity, refractive index, etc. 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... Figure 2 This is a component of the processing chamber 200. In some embodiments, the surface of the object to be measured 114 may be substantially perpendicular to the incident radiation beam. Therefore, if the object has an uneven surface, the orientation of the object relative to the system 100 can be changed when measuring different parts of the object, such that the normal of a point on the surface of the object being measured is aligned with the ray of the radiation beam 103.

[0036] In some embodiments, mirror 112 is coupled to the bottom surface of the convex mirror 124 of the reflecting objective 120 (e.g., as shown). The position and / or size of mirror 112 are such that scattered radiation (e.g., scattered radiation from the surface of object 114) is not blocked by mirror 112. A first portion of the radiation beam can be reflected back towards mirror 112 by the surface of object 114. This first portion of the radiation beam can be referred to as the reflected radiation beam. The reflected radiation beam can then be reflected from mirror 112, reflected back through lens 110, and then reflected from beam splitter 106 towards optical sensor 116.

[0037] In some embodiments, beam splitter 106 reflects a reflected portion of the radiation beam to optical sensor 116. Optical sensor 116 may be configured to detect the intensity of the portion of the radiation beam reflected from the surface of object 114 (i.e., the reflected radiation beam). In some embodiments, the radiation intensity detected by optical sensor 116 (such as the intensity of the reflected radiation beam) is related to the emissivity and / or surface roughness of the surface of object 114.

[0038] In some embodiments, radiation scattered from the surface of object 114 (e.g., indicated by the dashed arrow in FIG. 1 and referred to as the scattered radiation beam) is collected by a reflecting objective 120, referred to as a light collector. The reflecting objective 120 may include a concave inner mirror surface 122 and a convex mirror 124 disposed below or near the inner surface 122. The scattered radiation beam can be collected by the concave inner mirror surface 122 and reflected toward the convex mirror 124. In some embodiments, the convex mirror 124 forms a central shielding region of the reflecting objective 120. In some embodiments, the convex mirror 124 reflects the radiation collected from the scattered radiation beam toward an optical sensor 130 through an aperture 126 in the concave inner mirror surface 122. In some embodiments, the reflecting objective 120 is a Schwarzschild objective. However, those skilled in the art will recognize that other reflecting objectives may also be used. In some embodiments, the optical sensor 130 is configured to detect the intensity of the radiation scattered from the surface of object 114 (e.g., the intensity of the scattered radiation beam). In some embodiments, the radiation intensity detected by the optical sensor 130 (e.g., the radiation intensity scattered by the surface of object 114) is related to the emissivity and / or surface roughness of the surface of object 114.

[0039] In some embodiments, system controller 160 (e.g., a computing device, processing device, etc.) may be communicatively coupled to optical sensor 108, optical sensor 116, and / or optical sensor 130. System controller 160 may be and / or may include computing devices such as personal computers, server computers, programmable logic controllers (PLCs), microcontrollers, system-on-a-chip (SoCs), etc. System controller 132 may include one or more processing devices, which may be general-purpose processing devices such as microprocessors, central processing units, or the like. More specifically, the processing device may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, or a processor implementing other instruction sets or a combination of instruction sets. The processing device may also be one or more special-purpose processing devices such as application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), network processors, or the like. 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 can execute instructions to perform any one or more of the methods described herein and / or embodiments. The instructions can be stored on a computer-readable storage medium, which may include main memory, static memory, secondary memory, and / or processing devices (during execution of the instructions). System controller 132 can also be configured to allow a human operator to input and display data, operating commands, and the like.

[0040] System controller 160 can receive output signals from each optical sensor. In some embodiments, system controller 160 can determine (e.g., via processing logic) the roughness and / or emissivity of the surface of object 114 based on a comparison of the radiation intensity detected by optical sensor 116 and the radiation intensity detected by optical sensor 130. In some embodiments, emissivity is equivalent to 1 minus the reflectivity of the surface of object 114 (e.g., 1 - reflectivity). In some embodiments, the intensity of reflected radiation (e.g., the intensity detected by optical sensor 116) is related to emissivity. For example, emissivity can be considered complementary to reflectivity. Reflectivity can be calculated as the ratio of the intensity of the reflected radiation beam (represented, for example, the radiation intensity detected by optical sensor 116) to the radiation intensity detected by optical sensor 108. Reflectivity can indicate the emissivity of the surface of object 114 through the relationship emissivity = 1 - reflectivity. In some embodiments, the ratio of scattered radiation intensity to reflected radiation intensity indicates surface roughness.

[0041] In some examples, a higher reflected radiation intensity (such as that detected by optical sensor 116) compared to the scattered radiation intensity (such as that detected by optical sensor 130) may indicate a lower emissivity and / or lower surface roughness of the surface of object 114. In some examples, a lower reflected radiation intensity compared to the scattered radiation intensity may indicate a higher emissivity and / or higher surface roughness. In some examples, a higher scattered radiation intensity (such as that detected by optical sensor 130) compared to the reflected radiation intensity may indicate higher surface roughness, while a lower scattered radiation intensity compared to the reflected radiation intensity may indicate lower surface roughness.

[0042] In some embodiments, the system controller 160 may determine that the surface roughness of the object 114 is related to the ratio of the scattered radiation intensity to the reflected radiation intensity. Therefore, the processing device may determine the surface roughness of the object 114 based on the ratio of the radiation intensity detected by the optical sensor 130 to the radiation intensity detected by the optical sensor 116.

[0043] In some embodiments, as described above, system controller 160 may further determine surface roughness and / or emissivity based on sensor data from optical sensor 108. Specifically, system controller 160 may determine normalization coefficients based on sensor data from optical sensor 108. Normalization coefficients can be used to normalize sensor data from optical sensor 116 and / or optical sensor 130. For example, a change in the amplitude of radiation beam 103 may cause a corresponding change in reflected radiation detected by optical sensor 116 and / or scattered radiation detected by optical sensor 130. These changes may cause changes in the surface roughness and / or emissivity calculated by system controller 160. However, optical sensor 108 may also detect changes in the amplitude of radiation beam 103. By determining normalization coefficients based on sensor data from optical sensor 108 (e.g., where the sensor data corresponds to a change in the amplitude of radiation beam 103), changes in sensor data from optical sensors 116 and 130 can be normalized (e.g., based on normalization coefficients). System controller 160 can use the normalized sensor data 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 and the target intensity. The output signals of optical sensor 116 and / or optical sensor 130 may be multiplied by the normalization factor to determine the corrected signal. In some embodiments, the normalization factor may resolve frequency and / or phase mismatches between sensors, nonlinearities in sensor measurements, and / or other non-ideals of system 100A.

[0044] In some embodiments, system 100A can generate a surface roughness map and / or emissivity map of object 114. The surface roughness map and / or emissivity map can be generated by moving object 114 relative to an incident radiation beam (e.g., via a movable support 135) and determining the surface roughness and / or emissivity at various discrete points on the object's surface. In some embodiments, the generated surface roughness map and / or emissivity map may be based on measurements of surface roughness and / or emissivity at various known points on the entire surface of object 114. This map can be used to determine various predicted elements as described below.

[0045] In some embodiments, in lieu of or attached to one or more components of system 100A, system 100 includes a camera. In some examples, a camera operating in the mid-infrared range can image the surface of object 114 to determine emissivity and / or roughness information of the surface of object 114.

[0046] Figure 1BA simplified side view of a system 100B for optically determining emissivity and / or surface roughness, according to aspects of this disclosure, is shown. Features of system 200 with similar feature numbers to system 100 may have similar structures and / or functions as described above. In some embodiments, system 100B includes a rotatable mirror 152 configured to guide a radiation beam to lens 110. In some examples, the optical axis of radiation source 102 may be set approximately perpendicular (e.g., 90 degrees) to the optical axis of lens 110. In some embodiments, rotatable mirror 152 is substantially positioned at the focal plane of lens 110. In some embodiments, rotatable mirror 152 may reflect a radiation beam from the radiation source toward lens 110 at an angle. In response to rotation of rotatable mirror 152 about an axis perpendicular to the optical axis of lens 110 (e.g., an axis in the up-down direction of a drawing page or an axis in and out of the drawing page), rotatable mirror 152 may cause the radiation beam to move across the surface of object 114 in a periodic motion. For example, lens 110 can transform the angular motion of rotatable mirror 152 into lateral motion of the radiation beam (such as periodic lateral motion). In some examples, rotation of rotatable mirror 152 causes the radiation beam to move back and forth periodically across the surface of object 114 (e.g., in a periodic motion manner). The back-and-forth motion of the radiation beam can allow scanning of the surface of object 114.

[0047] In some embodiments, as the object 114 moves slowly along the Y direction of the XY plane via the support 135, the radiation beam moves rapidly back and forth in the X direction (e.g., the X direction of the XY plane) to scan the surface of the object 114. Data collected during the scan (e.g., reflected radiation intensity and / or scattered radiation intensity) can be used to determine (e.g., by the system controller 160) the emissivity surface profile map and / or surface roughness profile map (e.g., one or more profile maps) of the object 114.

[0048] Figure 2 This is a cross-sectional view of a processing chamber 200 (e.g., a semiconductor processing chamber, a display processing chamber, etc.) according to an embodiment of the present disclosure, the processing chamber having been used Figure 1A System 100A or Figure 1BSystem 100B characterizes one or more chamber components. For example, processing chamber 200 can be used in processes that provide a corrosive plasma environment with plasma processing conditions. For example, processing chamber 200 can be a chamber for a plasma etcher or plasma etching reactor, plasma cleaner, etc. Other types of chambers may include deposition chambers, cleaning chambers, oxidation chambers, etc. Examples of chamber components whose surface roughness and / or emissivity can be characterized include substrate support assembly 248, electrostatic chuck (ESC), ring (e.g., process kit ring or single ring), chamber wall, base, gas distribution plate, nozzle 230, gas pipe, nozzle, cover, liner, liner kit, shield, plasma screen, flow equalizer, cooling base, chamber viewport, chamber cover, etc. Chamber components can be made of metal, metal alloy, ceramic, and any combination thereof. Chamber components may include coatings, such as anti-plasma coatings or anti-corrosion coatings, the surface of which can be used Figure 1A-1B The system is characterized. The coating can be deposited or grown by methods such as atomic layer deposition, plasma spraying, chemical vapor deposition, ion-assisted deposition, sputtering, physical vapor deposition, electroplating, and anodizing.

[0049] In one embodiment, the processing chamber 200 includes a chamber body 202 and a nozzle 230, the chamber body and the nozzle surrounding an internal volume 206. The nozzle 230 may include a nozzle base and a nozzle gas distribution plate. Alternatively, in some embodiments, the nozzle 230 may be replaced by a cap and a nozzle. The chamber body 202 may be made of aluminum, stainless steel, or other suitable materials. The chamber body 202 generally includes sidewalls 208 and a bottom 210. Any of the nozzle 230 (or cap and / or nozzle), sidewalls 208, and / or bottom 210 may include the characterized coating.

[0050] An outer liner 216 may be disposed near the sidewall 208 to protect the chamber body 202. The outer liner 216 may be characterized. In one embodiment, the outer liner 216 is made of alumina.

[0051] An exhaust port 226 may be defined within the chamber body 202 and may couple the internal volume 206 to a pump system 228. The pump system 228 may include one or more pumps and throttle valves for evacuating and regulating the pressure of the internal volume 206 of the processing chamber 200.

[0052] Nozzle 230 may be supported on the sidewall 208 and / or top of chamber body 202. In some embodiments, nozzle 230 (or cover) may be opened to allow access to the internal volume 206 of processing chamber 200 and may provide a seal for processing chamber 200 when closed. Gas panel 258 may be coupled to processing chamber 200 to supply process gas and / or cleaning gas to internal volume 206 through nozzle 230 or cover and nozzle. Nozzle 230 is used to process the chamber for dielectric etching (etching dielectric materials). Nozzle 230 may include a gas distribution plate (GDP) with a plurality of gas delivery holes 232 throughout the GDP. Nozzle 230 may include GDP bonded to an aluminum nozzle base or an anodized aluminum nozzle base. GDP 233 may be made of Si or SiC, or may be ceramics such as Y2O3, Al2O3, YAG, etc. In embodiments, nozzle 230 and delivery holes 232 may be characterized using system 100 or 150. For a processing chamber used for conductor etching (etching conductive materials), a cover can be used instead of a nozzle. The cover may include a central nozzle fitted into a central hole in the cover. The cover may be a ceramic such as Al2O3, Y2O3, or YAG, or a ceramic compound comprising a solid solution of Y2O3-ZrO2 and Y4Al2O9. The nozzle may also be a ceramic such as Y2O3 or YAG, or a ceramic compound comprising a solid solution of Y2O3-ZrO2 and Y4Al2O9. According to one embodiment, the cover, nozzle 230 (which includes, for example, a nozzle base, GDP, and / or gas delivery conduit / hole), and / or nozzle may be characterized using system 100 or 150.

[0053] A substrate support assembly 248 is disposed within the internal volume 206 of the processing chamber 200 below the nozzle 230 or the cover. The substrate support assembly 248 holds the substrate 244 during processing and may include an electrostatic chuck adhered to a cooling plate.

[0054] The inner liner may be located around the periphery of the substrate support assembly 248. The inner liner may be a halogen-containing gas-resistant material, such as the material discussed with reference to the outer liner 216. In one embodiment, the inner liner 218 may be made of the same material as the outer liner 216. Furthermore, in embodiments, the inner liner 218 may also be characterized using system 100 or 150.

[0055] Figure 3An illustrative computer system architecture 300 according to aspects of this disclosure is depicted. The computer system architecture 300 includes a client device 320, manufacturing equipment 322, an optical measurement tool 326, a prediction server 312 (which is used, for example, to generate prediction data, provide model adaptation, utilize knowledge bases, etc.), and a data storage 350. The prediction server 312 may be part of a prediction system 310. The prediction system 310 may further include server machines 370 and 380. In some embodiments, the computer system architecture 300 may include a manufacturing system for processing substrates, or the optical measurement tool 326, or may be part of the manufacturing system or the optical measurement tool. Further details regarding the optical measurement tool 326 will be provided later. Figure 1A-1B supply.

[0056] Components of client device 320, manufacturing equipment 322, optical measuring tool 326, prediction system 310, and / or data storage 350 may be coupled to each other via network 340. In some embodiments, network 340 is a public network that provides client device 320 with access to prediction server 312, data storage 350, and other publicly available computing devices. In some embodiments, network 340 is a private network that provides client device 320 with access to manufacturing equipment 322, optical measuring tool 326, data storage 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., LTE networks), routers, hubs, switches, server computers, cloud computing networks, and / or combinations thereof.

[0057] Client device 320 may include computing devices such as personal computers (PCs), laptops, mobile phones, smartphones, tablets, portable eNet computers, network-connected televisions (“Smart TVs”), network-connected media players (e.g., Blu-ray players), set-top boxes, over-the-top (OTT) streaming devices, operator boxes, etc.

[0058] Manufacturing equipment 322 can produce products according to a formula. In some embodiments, manufacturing equipment 322 may include or be part of a manufacturing system, which includes one or more stations (e.g., process chambers, transfer chambers, load locks, factory interfaces, etc.) configured to perform different operations on a substrate.

[0059] Optical measuring tool 326 may be a tool (e.g., a system) for determining the emissivity and / or roughness of the surface of an object under test. Optical measuring tool 326 may be configured to generate data associated with the emissivity and / or surface roughness of the object measured by optical measuring tool 326. In some embodiments, the optical measuring 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 data memory 350, where the data may be accessed (e.g., via network 340). Optical measuring tool 326 may include one or more sensors (e.g., multiple optical sensors) configured to detect radiation and generate data associated with the object under test. In some embodiments, optical measuring tool 326 includes a radiation source to provide a radiation beam for illuminating the surface of the object under test (e.g., a chamber component of the substrate processing chamber of manufacturing equipment 322, etc.). The optical sensors of optical measuring tool 326 may detect radiation reflected and / or scattered by the object surface. In some embodiments, the optical measuring tool 326 can generate emissivity data and / or surface roughness data based on the intensity of reflected and / or scattered radiation detected by an optical sensor. In some embodiments, the optical measuring tool 326 can generate a surface roughness profile and / or emissivity profile of the surface of the object under test by measuring the emissivity and / or surface roughness at multiple locations on the surface of the object under test. In some embodiments, the optical measuring tool 326 can be included in a system for manufacturing components (such as processing chamber components) of the manufacturing equipment 322.

[0060] Data storage 350 may be a memory (e.g., random access memory), a drive (e.g., a hard disk drive, flash drive), a database system, or another type of component or device capable of storing data. Data storage 350 may include multiple storage components (e.g., multiple drives or multiple databases) that can span multiple computing devices (e.g., multiple server computers). Data storage 350 may store emissivity data and surface roughness data (this data is generated, for example, by optical measurement tool 326).

[0061] One or more portions of data storage 350 may be configured to store data that is inaccessible to users of the manufacturing system. In some embodiments, all data stored at data storage 350 may be inaccessible to users of the manufacturing system. In other or similar embodiments, a portion of the data stored at data storage 350 may be inaccessible to users, while another portion of the data stored at data storage 350 may be accessible to users. In some embodiments, the inaccessible data stored at data storage 350 is encrypted using an encryption mechanism unknown to the user (e.g., the data is encrypted using a private encryption key). In other or similar embodiments, data storage 350 may include multiple data storage units, wherein data that is inaccessible to users is stored in a first data storage unit, while data that is accessible to users is stored in a second data storage unit.

[0062] In some embodiments, the prediction system 310 includes server machine 370 and server machine 380. Server machine 370 includes a training set generator 372, which is capable of generating training datasets (e.g., a set of data inputs and a set of target outputs) to train, validate, and / or test machine learning model 390 or a set of machine learning models 390. The following... Figure 4 and 5A Some operations of the training set generator 372 are described in detail. In some embodiments, the training set generator 372 can divide the training data into a training set, a validation set, and a test set.

[0063] Server machine 380 may include training engine 382. An engine can refer to hardware (e.g., circuitry, special-purpose logic, programmable logic, microcode, processing device, etc.), software (e.g., instructions running on a processing device, general-purpose computer system, or special-purpose machine), firmware, microcode, or a combination thereof. Training engine 382 may be able to train machine learning model 390 or a set of machine learning models 390. Machine learning model 390 may refer to a model artifact created by training engine 382 using training data. Training data may include training inputs and corresponding target outputs (the correct answers for the given training inputs). Training engine 382 may identify patterns in the training data that map training inputs to target outputs (the answers to be predicted). Training engine 382 may then ultimately provide machine learning models 390 that capture these patterns. Machine learning model 390 may include linear regression models, partial least squares regression models, Gaussian regression models, random forest models, support vector machine models, neural networks, ridge regression models, etc. In some embodiments, instead of or attached to the machine learning model, machine learning model 390 is a physically based model.

[0064] Training engine 382 can also validate trained machine learning models 390 using a corresponding set of features from the validation set of training set generator 372. In some embodiments, training engine 382 can assign a performance rating to each trained machine learning model in a set of trained machine learning models 390. The performance rating can correspond to the accuracy, speed, and / or efficiency of the corresponding trained model. According to some embodiments described herein, training engine 382 can select trained machine learning models 390 whose performance ratings meet the performance criteria to be used by prediction engine 314. Figure 5A Further details about the training engine 382 are provided.

[0065] The prediction server 312 includes a prediction engine 314 capable of providing data (e.g., emissivity data and / or surface roughness data) from the optical measurement tool 326 as input to a trained machine learning model 390. The prediction engine can execute the trained model 390 on the input to obtain one or more outputs. In an embodiment, the trained model 390 is trained based on training data including surface profiles of the roughness and / or emissivity of the chamber components, and one or more quality metrics of one or more processed substrates. Figure 5B As further described, in some embodiments, prediction engine 314 uses model 390 to process input data (e.g., surface profiles of the roughness and / or emissivity of the chamber component) to predict substrate process results (e.g., one or more substrate quality metrics) for a future substrate to be processed in the processing chamber using the chamber component measured by optical measurement tool 326.

[0066] 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 a larger or smaller number of machines. For example, in some embodiments, server machines 370 and 380 may be integrated into a single machine. In other embodiments, server machines 370 and 380 and / or prediction server 312 may be integrated into a single machine. Generally, the 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. Furthermore, the functionality attributed to a particular component may also be performed by different components or multiple components operating together.

[0067] Figure 4A model training workflow 405 and a model application workflow 417 are illustrated according to one embodiment for determining the predicted results of a processed substrate based on surface profile maps of one or more chamber components. The model training workflow 405 and the model application workflow 417 can be executed by processing logic performed by a processor of a computing device. One or more of these workflows 405, 417 can be implemented, for example, by one or more machine learning models implemented on the processing device and / or other software and / or firmware executed on the processing device.

[0068] Model training workflow 405 is used to train one or more machine learning models (e.g., deep learning models) to determine predicted substrate outcomes for a substrate being processed in a process chamber, the process chamber including one or more chamber components having measured emissivity surface profiles and / or roughness surface profiles. Model application workflow 417 is used to apply the one or more trained machine learning models to perform substrate outcome evaluation. Each component emissivity / roughness data 412 may include surface emissivity and / or roughness at multiple locations of the chamber component in the processing chamber. For example, each component emissivity / roughness data 412 may include an array of surface emissivity measurements and / or surface roughness measurements for a corresponding chamber component. In some embodiments, the component emissivity / roughness data 412 includes one or more emissivity maps and / or roughness maps (e.g., profile maps) of an object surface (e.g., a chamber component surface). In some embodiments, the emissivity maps and / or roughness maps may be generated via the systems 100A or 100B described above.

[0069] This paper describes various machine learning outputs. Specific numbers and arrangements of machine learning models are described and illustrated. However, it should be understood that the number and type of machine learning models used, as well as the arrangement of such models, can be modified to achieve the same or similar end results. Therefore, the machine learning model arrangements described and illustrated are merely examples and should not be construed as limiting.

[0070] In some embodiments, one or more machine learning models are trained to perform one or more substrate result estimation tasks. Each task can be performed by a separate machine learning model. Alternatively, a single machine learning model can perform each task or a subset of tasks. For example, a first machine learning model can be trained to determine the substrate process result, and a second machine learning model can be trained to determine the corresponding correction action. Additionally or alternatively, different machine learning models can be trained to perform different combinations of tasks. In one example, one or more machine learning models can be trained. The trained machine learning (ML) model can be a single shared neural network with multiple shared layers and multiple higher-level dissimilar output layers, where each output layer outputs different predictions, classifications, recognitions, etc. For example, a first higher-level output layer can determine the substrate process result based on input data corresponding to a first chamber component, and a second higher-level output layer can determine the substrate process result based on input data corresponding to a second chamber component.

[0071] One type of machine learning model that can be used to perform some or all of the tasks mentioned above is an artificial neural network, such as a deep neural network. Artificial neural networks typically include feature representation components with classifier or regression layers that map features to a target output space. For example, a convolutional neural network (CNN) contains multiple layers of convolutional filters. Deep learning is a class of machine learning algorithms that uses a cascade of multiple layers of non-linear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. Deep neural networks can learn in a supervised (e.g., classification) and / or unsupervised (e.g., pattern analysis) manner. Deep neural networks consist of a hierarchical structure of layers, with different layers learning different representations corresponding to different levels of abstraction. In deep learning, each layer learns to transform its input data into a slightly more abstract and comprehensive representation. Notably, the deep learning process can learn on its own which features should be optimally placed at which layer. The "depth" in "deep learning" refers to the number of layers through which the data is transformed. More precisely, deep learning systems have a considerable credit allocation path (CAP) depth. A CAP is a chain of transformations from input to output. CAP describes the underlying causal relationship between the input and the output. For feedforward neural networks, the depth of CAP can be the network depth and can be the number of hidden layers plus one. For recurrent neural networks where a signal can propagate more than once through a single layer, the CAP depth may be infinite.

[0072] Training a neural network can be done in a supervised learning manner. This involves feeding the network a training dataset consisting of labeled inputs, observing its outputs, defining the error (defined by measuring the difference between the output and the label values), and using techniques such as deep gradient descent and backpropagation to adjust the network's weights across all layers and nodes to minimize the error. In many applications, repeating this process across many labeled inputs in the training dataset produces a network that can produce the correct output when given inputs different from those present in the training dataset.

[0073] For model training workflow 405, a training dataset should be formed using a training dataset containing hundreds, thousands, tens of thousands, hundreds of thousands, or more instances of component emissivity / roughness data 412 (e.g., surface emissivity / roughness maps). For example, the data may include chamber component emissivity measurements determined using a given number of measurements. In some embodiments, multiple measurements are performed to generate surface emissivity maps of the chamber component surface. This data can be processed to generate one or more training datasets 436 used to train one or more machine learning models. Training data items in training dataset 436 may include component emissivity / roughness data 412, substrate results using a substrate processed with the measured chamber component in a processing chamber, and / or one or more images of the processed substrate.

[0074] To perform training, the processing logic inputs the training dataset 436 into one or more untrained machine learning models. The machine learning models can be initialized before the first input is fed into them. The processing logic trains the untrained machine learning models based on the training dataset to generate one or more trained machine learning models that perform the various operations described above. Training can be performed by sequentially feeding input data such as part emissivity / roughness data 412, images, and / or the results of the processed substrate into the machine learning models.

[0075] Machine learning models process inputs to generate outputs. Artificial neural networks consist of an input layer, which comprises values ​​from data points. The next layer is called a hidden layer, where nodes each receive one or more input values. Each node contains parameters (e.g., weights) applied to the input values. Therefore, each node essentially feeds the input values ​​into a multivariable function (e.g., a nonlinear mathematical transformation) to produce an output value. The next layer could be another hidden layer or an output layer. In both cases, nodes in the next layer receive output values ​​from nodes in the previous layer, each applying weights to those values ​​and then generating its own output value. This can be performed at each layer. The final layer is the output layer, where there is a node for each category, prediction, and / or output that the machine learning model can produce.

[0076] Therefore, the output can include one or more predictions or inferences (e.g., an estimate of the result of processing a substrate in a process chamber, measured by the substrate being processed using specific chamber components in that process chamber). The processing logic can compare the estimated substrate result with historical substrate results. The processing logic determines an error (i.e., classification error) based on the difference between the estimated substrate result and the target substrate result. The processing logic adjusts the weights of one or more nodes in a machine learning model based on the error. An error term or delta can be determined for each node in the artificial neural network. Based on this error, the artificial neural network adjusts one or more parameters (weights of one or more inputs to the node) of one or more of its nodes. Parameters can be updated in a backpropagation manner, such that nodes at the highest layer are updated first, then nodes at the next layer, and so on. An artificial neural network contains multiple layers of "neurons," where each layer receives input values ​​from neurons in the layer above. The parameters of each neuron include weights associated with the values ​​received from each neuron in the layer above. Therefore, adjusting the parameters can include adjusting the weights assigned to each input of one or more neurons in one or more layers of the artificial neural network.

[0077] Once the model parameters are optimized, model validation can be performed to determine if the model has improved and to determine the current accuracy of the deep learning model. After one or more rounds of training, the processing logic can determine whether a stopping criterion has been met. The stopping criterion can be a target level of accuracy, a target number of processed images from the training dataset, a target amount of change in parameters relative to one or more previous data points, a combination 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 if the accuracy of the machine learning model has stopped improving. If the stopping criterion is not met, further training is performed. If the stopping criterion is met, training may be complete. Once the machine learning model is trained, a reserved portion of the training dataset can be used to test the model. Once one or more trained machine learning models 438 are generated, they can be stored in the model storage device 445 and added to the processed substrate results engine 430.

[0078] For model application workflow 417, according to one embodiment, input data 462 may be input to one or more processed substrate result determiners 467, each of which may include a trained neural network or other model. Additionally or alternatively, one or more processed substrate result determiners 467 may apply image processing algorithms to determine the result of the processed substrate. Input data may include a surface emissivity profile and / or roughness profile of the chamber component (this profile is, for example, measured / generated using the optical measurement tools described herein). Furthermore, input data may optionally include one or more images of the chamber component under test. Based on input data 462, the processed substrate result determiner 467 may output one or more estimated results 469 of the processed substrate. The results 469 of the processed substrate may include a predicted quality (e.g., thickness, uniformity, etc.) of one or more thin films deposited or etched on the substrate to be processed in the process chamber using the measured chamber component.

[0079] Action determiner 472 may determine one or more actions 470 to be performed based on the result 469 of the processed substrate. In one embodiment, action determiner 472 compares the result estimate of the processed substrate with one or more result thresholds of the processed substrate. If the result estimate of one or more processed substrates reaches or exceeds the result threshold of the processed substrate, action determiner 472 may determine to recommend replacing the chamber component and / or updating the process parameters for future substrate processing. In this case, action determiner 472 may output a recommendation or notification to replace the chamber component and / or update the process parameters. In some embodiments, action determiner 472 automatically updates the process parameters based on the result 469 of the processed substrate that meets one or more criteria. In some examples, the result 469 of the processed substrate may include estimated conditions of the substrate after one or more processing operations. In some embodiments, estimated conditions may be used to determine one or more updates to the process parameters for future substrate processing using the chamber component in the processing chamber.

[0080] Figure 5A This is a flowchart of a method 500A for generating a training dataset for evaluating the results of training a machine learning model, according to an aspect of this disclosure. Method 500A is executed by processing logic, which may include hardware (circuit systems, dedicated logic, etc.), software (e.g., running on a general-purpose computer system or a dedicated machine), firmware, or some combination thereof. In one embodiment, method 500A may be executed by a computer system (e.g., Figure 3 The operation is performed by a computer system architecture 300. In other or similar embodiments, one or more operations of method 500A may be performed by one or more other machines not shown in the figures.

[0081] At box 510, the processing logic initializes the training set T to an empty set (e.g., {}).

[0082] At block 512, the processing logic obtains substrate process result data (e.g., data associated with the surface of a thin film on the substrate, such as film thickness, uniformity, etc.) related to the substrate processed in the processing chamber of the manufacturing system. In some embodiments, the processing logic uses one or more history chamber components to obtain historical substrate process result data corresponding to the substrate processed in the processing chamber.

[0083] At block 514, the processing logic obtains surface emissivity and / or surface roughness information of a component included in the processing chamber, which has been processed on the aforementioned substrate. As previously mentioned, the surface emissivity and / or surface roughness information can be obtained using the optical measurement tools described herein (such as...). Figure 3 The surface emissivity and / or surface roughness information is obtained using an optical measurement tool (326) or a system for optically determining emissivity and / or surface roughness (such as system 200). In some embodiments, the surface emissivity information and / or surface roughness information may include a profile of the surface of the chamber component under test. In some embodiments, the processing logic obtains historical chamber component surface roughness data and / or historical chamber component emissivity data corresponding to historical measurement results of historical chamber components.

[0084] At block 516, the processing logic generates training input based on the data obtained at block 514 for the surface emissivity and / or roughness of the chamber component. In some embodiments, the training input 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.).

[0085] At block 518, the processing logic can generate a target output based on the substrate process result data obtained at block 512. The target output can correspond to a substrate result metric (data indicating the quality of the processed substrate) of the substrate processed in the processing chamber.

[0086] At block 520, the processing logic generates an input / output map. The input / output map refers to a training input that includes or is based on data from the chamber components, and a target output that includes the training input, where the target output identifies the substrate process result, and where the training input is associated with (or mapped to) the target output. At block 522, the processing logic adds the input / output map to the training set T.

[0087] At box 524, the processing logic determines whether the training set T includes a sufficient amount of training data to train the machine learning model. It should be noted that in some implementations, the sufficiency of the training set T may be determined solely based on the number of input / output mappings in the training set, while in other implementations, the sufficiency of the training set T may be determined based on one or more other criteria (e.g., a measure of the diversity of training examples) in addition to or instead of the number of input / output mappings. In response to determining that the training set T includes a sufficient amount of training data to train the machine learning model, the processing logic provides the training set T to train the machine learning model. In response to determining that the training set does not include a sufficient amount of training data to train the machine learning model, method 500 returns to box 512.

[0088] At box 526, the processing logic provides a training set T to train a machine learning model. In some embodiments, the training set T is provided to (e.g., ...) Figure 3 The training engine 382 of the server machine 380 performs training. In the case of a neural network, for example, given the input values ​​of an input / output mapping (e.g., spectral data and / or chamber data for a previous substrate), the input values ​​of the input / output mapping are input into the neural network, and the output values ​​of the input / output mapping are stored in the output nodes of the neural network. Then, the connection weights in the neural network are adjusted according to a learning algorithm (e.g., backpropagation, etc.), and this procedure is repeated for other input / output mappings in the training set T. After box 526, the machine learning model (such as...) Figure 3 The machine learning model (390) can be used to provide predicted substrate process results for substrates processed using measured chamber components in a processing chamber.

[0089] Figure 5B This is a flowchart of a method 500B for generating predicted processed substrate results using a trained machine learning model, according to an aspect of this disclosure. Method 500B is executed by processing logic, which may include hardware (circuit systems, dedicated logic, etc.), software (e.g., 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 (e.g., Figure 3 The operation is performed by a computer system architecture 300. In other or similar embodiments, one or more operations of method 500B may be performed by one or more other machines not shown in the figures.

[0090] At block 552, the processing logic receives data associated with the emissivity and / or roughness of the surface of the chamber component of the processing chamber. In some embodiments, the data is obtained from an optical measurement tool described herein (such as...). Figure 3The data is received by an optical measuring tool (326) or a system (such as system 100A or system 100B) for optically determining emissivity and / or surface roughness. The data may be raw sensor data or data that has been processed (e.g., by a processing device, computing device, etc.) to determine surface emissivity and / or roughness. In some embodiments, the data is in the form of one or more surface profile maps that indicate surface emissivity and / or roughness.

[0091] At box 554, the processing logic takes the data input received at box 552 and trains a machine learning model. In some embodiments, the trained machine learning model is a model using the references herein. Figure 3 , Figure 4 and / or Figure 5A The described technique is used for training. The trained machine learning model can be trained with data inputs including historical surface roughness data and / or historical 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 data inputs associated with the surface emissivity and / or roughness of the chamber components.

[0092] At block 556, the processing logic receives output from a trained machine learning model, which includes predicted substrate process results corresponding to future substrates to be processed using chamber components in the processing chamber. In some embodiments, the surface emissivity and / or roughness of the chamber components may affect the results of substrates processed in the processing chamber. The predicted substrate process results may reflect these effects.

[0093] Figure 6 This is a flowchart of a method 600 for optically determining emissivity and / or surface roughness, according to an aspect of this disclosure. Method 600 is performed by a system that may include hardware (circuit systems, dedicated logic, optical measurement tools described herein, etc.), software (e.g., running on a general-purpose computer system or a special-purpose machine), firmware, or some combination thereof. In one embodiment, method 600 may be performed by a computer system (e.g., Figure 3 The computer system architecture 300) is used for execution, and in other or similar embodiments, one or more operations of method 600 may be performed by one or more other machines not described in the figures.

[0094] At box 602, the system's radiation source emits a radiation beam. In some embodiments, the radiation beam is an infrared radiation beam in the mid-infrared range (e.g., an infrared radiation beam output from a laser). For example, the wavelength range of the radiation beam can be 1-6 micrometers. In another example, the wavelength range of the radiation beam can be 3-5 micrometers. In some embodiments, the radiation source is a mid-infrared supercontinuum laser emitter configured to operate in the mid-infrared range. Thus, in some embodiments, the radiation beam is a mid-infrared infrared laser beam. In some embodiments, the radiation beam is directed to an object surface via one or more mirrors, filters (such as polarizing filters), lenses, and / or beam splitters. The object surface may reflect a portion of the radiation beam and / or scatter a portion of the radiation beam (as in another portion), at least in part, due to the emissivity and / or roughness of the object surface. In some embodiments, the object is a chamber component of a substrate processing chamber.

[0095] At block 604, the system's first optical sensor detects the intensity of a portion of the radiation beam reflected from the surface of an object (e.g., a chamber component). The intensity of the reflected radiation can at least indicate the emissivity and / or roughness of the object's 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 returns to the radiation source along at least a portion of the path. The beam splitter can direct the reflected radiation along the path to the optical sensor.

[0096] At frame 606, the system's second optical sensor detects the intensity of a portion of the radiation beam scattered by the surface of an object (e.g., a chamber component). The intensity of the scattered radiation can at least indicate the emissivity and / or roughness of the object's surface. In some embodiments, the scattered radiation is collected by a reflecting objective (e.g., a Schwarzschild objective) and directed toward the second optical sensor (e.g., reflected and / or focused). In some embodiments, the reflecting objective is substantially positioned above the object (e.g., as shown in the image). Figure 1A and 1B (As shown). In some embodiments, one or more mirrors, filters, lenses, etc., can guide, process, manipulate, reflect, or otherwise manipulate scattered radiation.

[0097] At block 608, a processing device communicatively coupled to a first optical sensor and a second optical sensor can determine (e.g., via processing logic) at least one of the surface roughness or the emissivity of an object (e.g., a chamber component). In some embodiments, the processing device makes this determination based on a comparison of the intensity of reflected radiation and the intensity of scattered radiation. In some embodiments, manufacturing process parameters (e.g., manufacturing recipe, manufacturing operation, etc.) corresponding to the object are updated (e.g., adjusted) based on the measured roughness and / or measured emissivity. For example, the manufacturing process for a chamber component can be updated based on measured values ​​of the surface roughness and / or emissivity of the sample chamber component. In such an example, the measured values ​​can indicate that the sample chamber component does not meet target thresholds (e.g., target surface roughness thresholds and / or target emissivity thresholds). The update to the manufacturing process can be to manufacture future chamber components within the target thresholds according to the updated manufacturing process parameters.

[0098] In some embodiments, the processing device is communicatively coupled to a third optical sensor (such as a normalized sensor, optical sensor 108 of FIG. 1, etc.). The processing device can use the signal received from the third optical sensor to normalize the signals received from the first and second optical sensors (e.g., normalize the intensity of reflected and / or scattered radiation). In some embodiments, a surface map of an 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 performing multiple individual measurements on the object's surface. Alternatively, the map can be generated by a surface scanning operation (performed, for example, by system 100B of FIG. 1).

[0099] Figure 7The illustration depicts a machine in the example form of computing device 700, within which a set of instructions can be executed to cause the machine to perform any or more of the methods discussed herein. In alternative embodiments, the machine may be connected to (e.g., networked) with other machines in a local area network (LAN), intranet, extranet, or the Internet. The machine may operate as a server or client machine in a client-server network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The machine may be a personal computer (PC), tablet computer, set-top box (STB), personal digital assistant (PDA), cellular phone, web appliance, server, network router, switch, or bridge, or any machine capable of executing a set of instructions (executed sequentially or otherwise) specifying the actions to be taken by the machine. Further, although only a single machine is shown, the term "machine" should also be considered as a collection of any machine (e.g., a computer) that individually or collectively executes a set (or more) of instructions to perform any or more of the methods 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 described herein.

[0100] Example computing device 700 includes processing device 702 that communicates with each other via bus 708, main memory 704 (e.g., read-only memory (ROM), flash memory, dynamic random access memory (DRAM) such as synchronous dynamic random access memory (SDRAM), etc.), static memory 706 (e.g., flash memory, static random access memory (SRAM), etc.), and auxiliary memory (e.g., data storage device 728).

[0101] Processing device 702 may represent one or more general-purpose processors such as microprocessors, central processing units, etc. More specifically, 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. Processing device 702 may also be one or more special-purpose processing devices such as application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), network processors, etc. Processing device 702 may also be or include system-on-a-chip (SoC), programmable logic controllers (PLCs), or other types of processing devices. Processing device 702 is configured to execute processing logic to perform the operations discussed herein.

[0102] The computing device 700 may further include a network interface device 722 for communicating with the network 764. The 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).

[0103] Data storage device 728 may include a machine-readable storage medium (or more specifically a non-transitory computer-readable storage medium) 724 on which one or more sets of instructions 726 embodying any one or more of the functions described herein are stored. Non-transitory storage medium refers to storage media other than a carrier wave. The instructions 726 may also reside wholly or at least partially within main memory 704 and / or processing device 702 during execution by computer device 700, which also constitute computer-readable storage media.

[0104] Although computer-readable storage medium 724 is shown as a single medium in the example embodiment, the term "computer-readable storage medium" should also be understood to include a single medium or multiple media (e.g., a centralized or distributed database and / or associated cache and server) storing the set or more sets of instructions. The term "computer-readable storage medium" should also be understood to include any medium capable of storing or encoding any one or more sets of instructions for methods executed by a machine and causing the machine to perform the contents of this disclosure. Therefore, the term "computer-readable storage medium" should be understood to include (but is not limited to) solid-state memory as well as optical and magnetic media.

[0105] The foregoing description sets forth numerous specific details of examples such as particular systems, components, methods, etc., to provide a good understanding of several embodiments of this disclosure. However, those skilled in the art will understand that at least some embodiments of this disclosure can be practiced without these specific details. In other instances, well-known components or methods are not described in detail, or are presented in a simple block diagram format, to avoid unnecessarily obscuring the disclosure. Therefore, the specific details set forth are merely exemplary. Specific implementations may differ from these exemplary details and are still considered to be within the scope of this disclosure.

[0106] Throughout this specification, the phrase "one / a embodiment" means that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in at least one embodiment. Therefore, the phrase "in one / a embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment. Furthermore, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." When the terms "about" or "approximately" are used herein, they are intended to mean that the accuracy of the presented nominal values ​​is within ±10%.

[0107] Although the operations of the methods herein are shown and described in a specific order, the order of operations for each method can be changed so that certain operations can be performed in reverse order, allowing some operations to be performed at least partially in parallel with other operations. In another embodiment, instructions or sub-operations of different operations can be performed intermittently and / or alternately.

[0108] It should be understood that the above description is intended to be illustrative and not restrictive. Many other embodiments will be apparent to those skilled in the art upon reading and understanding the above description. Therefore, the scope of this disclosure will be determined with reference to the appended claims and the full scope of their equivalents.

Claims

1. A system comprising: The radiation source is configured to emit a radiation beam; A first optical sensor is configured to detect a first intensity of a first portion of the radiation beam reflected from the surface of an object toward a radiation source; A second optical sensor is configured to detect a second intensity of a second portion of the radiation beam scattered by the surface of the object and collected by a reflecting objective lens disposed above the surface of the object, wherein the radiation beam reflected from the surface of the object is directed to the radiation source via a mirror coupled to the bottom surface of the convex mirror of the reflecting objective lens; as well as A processing device communicatively coupled to the first optical sensor and the second optical sensor, wherein the processing device is configured to determine at least one of the roughness of the surface of the object or the emissivity of the surface of the object based on a comparison of the first intensity and the second intensity.

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

3. The system of claim 1, further comprising: The mirror is coupled to the bottom surface of the convex mirror of the reflecting objective, wherein the mirror is configured to guide the radiation beam to the object; as well as The reflecting objective is configured to receive a second portion of the radiation beam scattered by the surface of the object and to guide the second portion of the radiation beam to the second optical sensor.

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

5. The system of claim 3, further comprising: A beam splitter is disposed along the optical axis between the radiation source and the mirror, wherein a first portion of the radiation beam reflected from the surface of the object is reflected by the mirror, returns through one or more lenses, and is guided by the beam splitter to the first optical sensor.

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

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

8. The system of claim 1, further comprising: One or more lenses are configured to focus the radiation beam, wherein the radiation beam is focused on the surface of the object into a spot size with a diameter of less than 200 micrometers.

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

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. A method comprising: A radiation beam is emitted from the radiation source; The first intensity of a first portion of the radiation beam reflected from the surface of the chamber component of the processing chamber toward the radiation source is detected by a first optical sensor. The second intensity of a second portion of the radiation beam scattered by the surface of the chamber component and collected by a reflecting objective lens disposed above the surface of the chamber component is detected by a second optical sensor, wherein the radiation beam reflected from the surface of the chamber component is guided to the radiation source via a mirror coupled to the bottom surface of the convex mirror of the reflecting objective lens; as well as Based on a comparison of the first intensity and the second intensity, a processing device communicatively coupled to the first optical sensor and the second optical sensor determines at least one of the surface roughness of the chamber component or the emissivity of the surface of the chamber component.

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

13. The method of claim 11, further comprising: A third intensity of a portion of the radiation beam emitted by the radiation source is detected by a third optical sensor, and a beam splitter disposed along the optical axis between the radiation source and the mirror guides the portion of the radiation beam emitted by the radiation source to the third optical sensor, wherein the mirror is configured to guide the radiation beam to the chamber component; as well as Based on the detected third intensity, the detected first intensity and the detected second intensity are normalized.

14. The method of claim 11, further comprising: Data associated with at least one of the emissivity or roughness of the surface of the chamber component is input into the model; as well as The model receives an output, which includes a predicted substrate process result, wherein the predicted substrate process result corresponds to a future substrate to be processed using the chamber component.

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

16. The method of claim 11, further comprising: A machine learning model is trained to generate a trained machine learning model, wherein the machine learning model is trained with data inputs including one or more of the following: historical chamber component surface roughness data, historical chamber component emissivity data, data corresponding to the roughness of the surface of the chamber component, and data corresponding to the emissivity of the surface of the chamber component, wherein the data inputs are labeled with corresponding target output data, the target output data including historical substrate process result data corresponding to a substrate processed with one or more historical chamber components.

17. The method of claim 11, further comprising: The surface of the component is scanned by periodically moving the radiation beam across the surface of the component in response to the rotation of the rotatable second mirror.

18. A non-transitory machine-readable storage medium comprising instructions, said instructions, when executed by a processing device, causing the processing device to perform operations including: Receive data associated with at least one of the emissivity or roughness of the surface of the chamber component of the processing chamber; The data associated with at least one of the emissivity or roughness of the surface of the chamber component is input into a trained machine learning model; as well as The trained machine learning model receives output, which includes predicted substrate process results, wherein the predicted substrate process results correspond to a future substrate to be processed using the chamber components in the processing chamber. The receipt of data associated with at least one of the emissivity or the roughness of the surface of the chamber component includes: First sensor data is received from a first optical sensor, the first sensor data indicating a first intensity of a first portion of a radiation beam reflected from the surface of the chamber component toward a radiation source; as well as Second sensor data is received from a second optical sensor, indicating a second intensity of a second portion of the radiation beam scattered by the surface of the chamber component and collected by a reflecting objective disposed above the surface of the chamber component, wherein the radiation beam reflected from the surface of the chamber component is guided to the radiation source via a mirror coupled to the bottom surface of the convex mirror of the reflecting objective. The emissivity or roughness of the surface is at least one based on a comparison of the first intensity and the second intensity.

19. The non-transitory machine-readable storage medium of claim 18, wherein the trained machine learning model is trained with data input, the data input including one or more of the following: historical chamber component surface roughness data, historical chamber component emissivity data, data corresponding to the roughness of the surface of the chamber component, and data corresponding to the emissivity of the surface of the chamber component, wherein the data input is labeled with corresponding target output data, the target output data including historical substrate process result data corresponding to a substrate processed with one or more historical chamber components.

Images