Thermal processing chamber status based on thermal sensor readings

Abstract

A method of characterizing a heat treatment chamber may include training a model using rate of temperature change data from in an existing heat treatment chamber. A supervised learning process may mark these rate of change data based on deposition profiles on the substrate. The trained model may be used to characterize another chamber to determine whether the predicted performance matches the chamber used to train the model. An inert process using a carrier gas may be used to capture temperature data and derive rate of change data without actually depositing a layer on the substrate. The rate of change data may be provided to the model, which may generate component-specific outputs that characterize the extent to which a chamber is predicted to match fingerprint conditions of the chamber (matching at different times) or match between different chambers.

Description

[0001] Cross-references to related applications

[0002] This application claims the benefit and priority of U.S. Non-Provisional Application No. 18 / 190,970, filed March 28, 2023, entitled “Heat Treatment Chamber Status Based on Thermal Sensor Readings,” the entire contents of which are incorporated herein by reference for all purposes. Technical Field

[0003] This disclosure broadly describes techniques for assessing the health of thermal processing chambers in semiconductor manufacturing processes. More specifically, this disclosure describes monitoring the health of a chamber based on the rate of change indicated by thermal sensor readings. Background Technology

[0004] Epitaxial deposition can include any type of crystal growth or deposition to form a new crystalline layer with respect to a known orientation relative to a seed layer. Many modern semiconductor devices utilize epitaxial growth on silicon substrate chips. For example, providing a silicon-based precursor to a deposition chamber at high temperatures can allow for the final formation of an incremental layer of film lattice-aligned with the underlying seed layer. Conventional epitaxial film deposition typically involves a baking operation, which may be performed at temperatures greater than or approximately 700°C or higher. Epitaxial growth has been extended to different device structures and can be used for selective deposition or growth on specific surfaces. Meanwhile, for newer structures, epitaxial film thickness is decreasing. Summary of the Invention

[0005] In some embodiments, a method for characterizing a heat treatment chamber may include performing a process on the heat treatment chamber, wherein the process causes a temperature change within the heat treatment chamber during the process, during which temperature measurements are recorded by one or more temperature sensors in the heat treatment chamber, and / or deriving temperature change rate data from these temperature measurements. The method also includes providing this temperature change rate data to a model. The model may be configured to receive this temperature change rate data as input and provide an output predicting the degree of matching between the outcome of the thermal deposition process performed in the heat treatment chamber and a target outcome. The method may further include receiving the output from the model, which predicts the degree of matching between the outcome of the thermal deposition process and the target outcome, and characterizing the heat treatment chamber based on the output from the model.

[0006] In some embodiments, a system may include one or more processors and one or more memory devices storing instructions that, when executed by the one or more processors, cause the one or more processors to operate. These operations may include causing a heat treatment chamber to perform a process, wherein the process causes a temperature change within the heat treatment chamber during the process, during which temperature measurements are recorded by one or more temperature sensors in the heat treatment chamber, and / or deriving temperature change rate data from these temperature measurements. These operations may also include providing this temperature change rate data to a model. The model may be configured to receive this temperature change rate data as input and provide an output predicting the degree of matching between the outcome of the thermal deposition process performed in the heat treatment chamber and a target outcome. These operations may further include receiving the output from the model predicting the degree of matching between the outcome of the thermal deposition process and the target outcome, and characterizing the heat treatment chamber based on the output from the model.

[0007] In some embodiments, one or more non-transitory computer-readable media may store instructions that, when executed by one or more processors, cause the processors to perform operations that may include causing a heat treatment chamber to perform a process, wherein the process causes a temperature change within the heat treatment chamber during the process, during which temperature measurements are recorded by one or more temperature sensors within the heat treatment chamber, and / or deriving temperature change rate data from these temperature measurements. These operations may also include providing this temperature change rate data to a model. The model may be configured to receive this temperature change rate data as input and provide an output predicting the degree of matching between the outcome of the thermal deposition process performed in the heat treatment chamber and a target outcome. These operations may also include receiving an output from the model predicting the degree of matching between the outcome of the thermal deposition process and the target outcome, and characterizing the heat treatment chamber based on the output from the model.

[0008] In any embodiment, any and all of the following features may be implemented in any combination and not in a limiting manner. Before providing these temperature change rate data to the model, the model may be trained by: receiving training temperature change rate data from multiple executions of the process performed by one or more heat treatment chambers; receiving training results of the thermal deposition process measured from a substrate on which the thermal deposition process is performed by the one or more heat treatment chambers; generating training data based on these training temperature change rate data labeled using these training results of the thermal deposition process; and / or executing a supervised learning algorithm to train the model using these training data. The one or more heat treatment chambers and the heat treatment chamber may be the same chamber, and characterizing the heat treatment chamber may include characterizing whether the current performance of the heat treatment chamber matches the previous performance of the heat treatment chamber. These training temperature change rate data and training results can be received prior to preventative maintenance of the heat treatment chamber, during which at least a portion of the heat treatment chamber can be disassembled, at least one component in the heat treatment chamber can be replaced, and / or the heat treatment chamber can be reassembled; and the heat treatment chamber can be characterized based on the output from the model after the preventative maintenance is completed. The process may include depositing an epitaxial layer on a substrate. The process may include varying the temperature in the heat treatment chamber without the inflow of active precursors, such that the temperature varies in the heat treatment chamber without the deposition of a layer on the substrate. The process may include inert gases flowing into the heat treatment chamber instead of active precursors. The process may include multiple process steps, wherein these process steps may include multiple temperature setpoints, such that the temperature in the heat treatment chamber can move between these temperature setpoints during the process. These temperature change rate data may include an approximate slope of the temperature transition between these temperature setpoints. These temperature measurements may include time series of temperature readings from the one or more temperature sensors, and these rate of change of temperature data may include the calculated first derivative of the time series of temperature readings. The heat treatment chamber may include a quartz dome above a base, and one of the one or more temperature sensors may be configured to measure the temperature of the quartz dome. The heat treatment chamber may include a base, a first temperature sensor of the one or more temperature sensors may be configured to measure the temperature below the base, and a second temperature sensor of the one or more temperature sensors may be configured to measure the temperature of a substrate on top of the base. The heat treatment chamber may include a liner, and a first temperature sensor of the one or more temperature sensors may be configured to measure the temperature of the liner. The model may be trained to model the thermal response of the heat treatment chamber when thermal energy is added to it. This thermal response of the heat treatment chamber may take into account the thermal mass within the heat treatment chamber.The output from the model may include one or more scalar values, which may correspond to the one or more temperature sensors, and indicate the confidence level of the result of the thermal deposition process relative to the target result of each of the one or more temperature sensors. Characterizing the heat treatment chamber based on the output from the model may include characterizing the heat treatment chamber as mismatched with one or more heat treatment chambers used to train the model, and identifying components within the heat treatment chamber as the cause of the mismatch. A tolerance may be provided to the model, indicating the permissible deviation from the target result. Attached Figure Description

[0009] A further understanding of the nature and advantages of the various embodiments can be achieved by referring to the remainder of the specification and accompanying drawings, in which similar element symbols are used in several drawings to refer to similar parts. In some cases, sublabels are associated with element symbols to indicate one of a plurality of similar parts. When an element symbol is referenced without specifying an existing sublabel, it is intended to represent all such plurality of similar parts.

[0010] Figure 1 A schematic side cross-sectional view of a processing chamber according to some embodiments is shown.

[0011] Figure 2 A flowchart is shown, illustrating a method for training a machine learning model to characterize a processing chamber according to some embodiments.

[0012] Figure 3 A block diagram is shown illustrating a method for generating temperature change rate data from a temperature sensor according to some embodiments.

[0013] Figure 4 A graph showing time-series data measured during a process performed by an epitaxial chamber, according to some embodiments, is shown.

[0014] Figure 5 A flowchart illustrating the generation of labels for training temperature change rate data is shown according to some embodiments.

[0015] Figure 6 A flowchart for training a model to predict the performance of an epitaxial chamber, according to some embodiments, is shown.

[0016] Figure 7 A flowchart of a method for characterizing an epitaxial chamber according to some embodiments is shown.

[0017] Figure 8 A flowchart illustrating the use of a trained model to predict the performance of a novel epitaxial chamber, according to some embodiments, is shown.

[0018] Figure 9Alternative scenarios are shown for existing epitaxial chambers undergoing periodic testing or preventative maintenance according to some embodiments.

[0019] Figure 10 An exemplary computer system in which various embodiments can be implemented is shown. Detailed Implementation

[0020] Thermochemical vapor deposition (CVD) is one of the hottest processes in semiconductor manufacturing. During the deposition process, precursor gases may flow into the processing chamber at temperatures ranging from approximately 400°C to approximately 1100°C, during deposition and chamber cleaning processes. The temperature setpoint can vary throughout the process depending on the processing formulation, and the temperature within the chamber will rise / fall between different setpoints based on the chamber's thermal characteristics. The rate and quality of epitaxial deposition depend not only on the absolute temperature but also on the consistent thermal behavior of the processing chamber. Generally, the thermal behavior of the processing chamber can represent the precise temperature distribution within the chamber at different power input levels and temperature setpoints. For example, thermal behavior can be based on the total power supplied to the processing chamber and the distribution of different heat sources within the chamber. In addition to temporary temperature readings, thermal history, including data on the rate of temperature change, can also affect chamber health. As described below, the thermal response may drift as the chamber ages, and a film may build up inside the chamber. This can cause chamber components to absorb varying amounts of energy, thus requiring varying amounts of input energy to reach the temperature setpoint.

[0021] At a more detailed level, the thermal behavior of a processing chamber may depend not only on the power input to the chamber. Furthermore, the thermal behavior can be characterized more accurately by considering the total input flux of thermal energy, the distribution of that energy, how that energy is absorbed by the components within the chamber, the work done by the heat within the chamber, and the heat flux flowing out of the chamber. For example, certain components within the processing chamber may absorb heat emitted into the chamber by a chamber heat source. The base, dome, various gaskets, and other components may absorb a certain amount of heat supplied to the chamber during the deposition process based on their thermal mass. This is not a problem as long as the heat absorbed by these components is consistent between processes and between different processing chambers.

[0022] However, epitaxial deposition technology presents technical challenges. Specifically, the gases and heat supplied to the processing chamber during the epitaxial deposition process can cause coatings or films to form on the surfaces of components exposed inside the processing chamber during the deposition process. For example, while an desired epitaxial film is formed on the substrate, unwanted films may also form simultaneously on the exposed inner surfaces of the processing chamber. These coatings formed on the inner surfaces of the processing chamber can affect the optical properties of these components, which in turn can affect how these components absorb heat during the deposition process. If these inner surfaces are not cleaned between each deposition process, the amount of heat energy absorbed by these surfaces will change compared to the initial state of the processing chamber. Furthermore, the SiC surface may be altered due to etching processes such as HCl etching. Other chamber components, such as heating lamps, may also age over time, affecting the energy and energy distribution within the chamber.

[0023] Altering how heat is absorbed inside the processing chamber will affect the overall thermal behavior of the deposition process. Since the deposition process is largely influenced by temperature transitions within the processing chamber, which in turn are affected by thermal history effects and chamber condition drift between preventative maintenance phases, these variations can lead to mismatched results for substrates processed in the same processing chamber over time. These variations can also result in mismatched results for substrates processed in different processing chambers, whereas the same results were initially expected.

[0024] The embodiments described herein address these and other technical problems by monitoring changes in the thermal behavior of the chamber to detect deviations from the initial state. The processing chamber may include temperature sensors distributed throughout the chamber and configured to measure the temperature of specific components within the chamber. Temperature change rate data for each temperature sensor can be recorded as the temperature transitions between set points in the deposition process. This temperature change rate data can be used to train a model that predicts whether the processing chamber will produce ideal or expected on-chip deposition results based on the temperature change rate data. The model can be used to identify differences in on-chip deposition performance between processing chambers. The model can also be used to identify behavioral drift or changes in individual processing chambers over time as the chamber ages or undergoes preventative maintenance operations. Some embodiments associate specific temperature sensors with corresponding chamber components, enabling the model to identify specific components that cause mismatches.

[0025] Figure 1A schematic side cross-sectional view of a heat treatment chamber 100 according to some embodiments is shown. The treatment chamber 100 may represent a deposition chamber. In some embodiments, the treatment chamber 100 may include an epitaxial deposition chamber. The treatment chamber 100 may be used to grow an epitaxial film on a substrate 102. The treatment chamber 100 may generate a precursor stream through a top surface 150 of the substrate 102. Throughout this disclosure, the epitaxial deposition chamber may be used as a specific example of a heat treatment chamber. However, the embodiments described herein are equally applicable to any thermal deposition chamber. Therefore, any specific reference to an epitaxial deposition chamber may also be considered to refer more generally to any heat treatment chamber.

[0026] Processing chamber 100 may include an upper body 156, a lower body 148 disposed below the upper body 156, and a flow module 112 disposed between the upper body 156 and the lower body 148. The upper body 156, the flow module 112, and the lower body 148 may form the chamber body. Within the chamber body may be a substrate support 106, an upper window 108, a lower window 110 (such as a lower dome), a plurality of upper heat sources 141, and / or a plurality of lower heat sources 143. As shown, a controller 120 may communicate with processing chamber 100 and may be used to control processes and operations, such as those described herein. The controller 120 and processing chamber 100 may be part of a larger substrate processing system or tool platform.

[0027] The processing chamber 100 may also include a plurality of upper heat sources 141 at the top of the heating chamber 100 and a plurality of lower heat sources 143 at the bottom of the heating chamber. These upper heat sources 141 may be disposed between the upper window 108 and the cover 154. These upper heat sources 141 may form part of the upper heating module 155. These lower heat sources 143 may be disposed between the lower window 110 and the chamber floor 152. These lower heat sources 143 form part of the lower heating module 145. Figure 1 In the illustrated implementation, heat sources 141 and 143 can be heating lamps. Other heat sources, such as resistance heaters, light-emitting diodes (LEDs), and / or lasers, can also be used without limitation. Heat sources 141 and 143 can be coupled to reflector 175. Reflector 175 can be configured to redirect thermal energy from heat sources 141 and 143 back to processing space 136.

[0028] The upper window 108 may be an upper dome and is at least partially formed of an energy-transmitting material such as quartz. Therefore, the upper window 108 may also be referred to as a dome or a quartz dome. The lower window 110 is a lower dome and is at least partially formed of an energy-transmitting material such as quartz. The lower window 110 may also simply be referred to as a dome or a quartz dome. The upper window 108 may include a concave or flat first surface 111 (in... Figure 1 In the illustrated implementation, the first surface 111 is flat. The upper window 108 includes a convex second surface 113. The second surface 113 may face the substrate support 106. The upper window 108 may include an inner segment 122 and / or an outer segment 124. The first surface 111 and the second surface 113 may form at least a portion of the inner segment 122. The inner segment 122 may be transparent, while the outer segment 124 may be opaque. The outer segment 124 may be at least partially received in one or more sidewalls of the processing chamber 100 (such as in the flow module 112).

[0029] Processing space 136 and cleanup space 138 may be located between upper window 108 and lower window 110. Processing space 136 and cleanup space 138 may be portions of an interior space at least partially defined by upper window 108, lower window 110 and one or more pads 163. Upper window 108 may at least partially define processing space 136.

[0030] The internal space may include a substrate support 106 disposed therein. The substrate support 106 may be disposed between the upper window 108 and the lower window 110. The substrate support 106 may include a support surface 123 supporting the substrate 102. The substrate support 106 may also be referred to as a base, platform, or stage. The substrate support 106 may include a top surface on which the substrate 102 is disposed. The substrate support 106 may also be attached to a shaft 118. The shaft 118 may be connected to a motion assembly 121. The motion assembly 121 may include one or more actuators and / or adjustment devices that provide movement and / or adjustment of the shaft 118 and / or the substrate support 106 within the processing space 136.

[0031] The substrate support 106 may include a lifting rod hole 107 disposed therein. The lifting rod hole 107 may be sized to accommodate a lifting rod 132 for lifting the substrate 102 from the substrate support 106 before or after a deposition process. When the substrate support 106 descends from a processing position to a transport position, the lifting rod 132 may rest on a lifting rod stop 134. The lifting rod stop 134 may be coupled to a second shaft 104. A substrate (such as substrate 102) may be transported into and / or out of the processing chamber 100 via a transfer gate 137 (such as a slit valve). When the transfer gate 137 is open, a transport device (on which the substrate is supported) may extend into the interior space via the transfer gate 137, such that the lifting rod 132 may lift the substrate from the transport device and lower the substrate onto the substrate support 106 for processing. After processing, the lifting rod 132 can lift the substrate from the substrate support 106 and lower the substrate onto the conveying device, and the conveying device can retract via the open conveying door 137 to remove the substrate from the processing chamber 100.

[0032] The flow module 112 may include a plurality of gas inlets 114, a plurality of purge gas inlets 164, and one or more exhaust ports 116. These gas inlets 114 and purge gas inlets 164 may be located on a side of the flow module 112 opposite to one or more exhaust ports 116. One or more flow guides 117 may be located below these gas inlets 114 and / or one or more exhaust ports 116. The one or more flow guides may include, for example, one or more preheating rings. The one or more flow guides 117 may be located above the purge gas inlets 164. One or more gaskets 163 may be located on the inner surface of the flow module 112 and may protect the flow module 112 from reactive gases used during deposition and / or cleaning operations. The gas inlets 114 and purge gas inlets 164 may each be positioned to allow gas to flow parallel to the top surface 150 of the substrate 102 located within the processing space 136. The gas inlets 114 may be fluidly connected to one or more process gas sources 151 and one or more cleaning gas sources 153. A purge gas inlet 164 may be fluidly connected to one or more purge gas sources 162 and / or one or more cleaning gas sources 153. One or more exhaust ports 116 may be fluidly connected to an exhaust pump 157. One or more process gases supplied using one or more process gas sources 151 may include one or more reactive gases (such as one or more of silicon (Si), phosphorus (P), and / or germanium (Ge)) and / or one or more carrier gases (such as one or more of nitrogen (N2) and / or hydrogen (H2)). One or more purge gases supplied using one or more purge gas sources 162 may include one or more inert gases (such as one or more of argon (Ar), helium (He), hydrogen (H2), and / or nitrogen (N2)). One or more cleaning gases supplied using one or more cleaning gas sources 153 may include one or more of hydrogen (H) and / or chlorine (Cl). In some embodiments, one or more process gases may include silicon phosphide (SiP) and / or phosphine (PH3), and one or more cleaning gases may include hydrochloric acid (HCl).

[0033] One or more exhaust ports 116 may be further connected to or include an exhaust system 178. The exhaust system 178 may fluidly connect one or more exhaust ports 116 and an exhaust pump 157. The exhaust system 178 may facilitate controlled deposition of layers on the substrate 102. The exhaust system 178 may be positioned on the opposite side of the processing chamber 100 relative to the flow module 112.

[0034] Controller 120 may include a central processing unit (CPU), memory containing instructions, and support circuitry for the CPU. For example, controller 120 may include one or more processors. The one or more processors may be distributed via a network or wireless connection among local controllers of processing chamber 100, tool servers on tools or platforms operating multiple processing chambers of different types, and / or cloud-based or facility-based servers. One or more non-transitory computer-readable media may store instructions that cause one or more processors of controller 120 to perform the operations described herein. In general, computer-readable media and one or more processors may constitute controller 120 together with other components, which are not necessarily limited to a single computer system. Instead, controller 120 may be distributed among multiple different computer systems in different locations. In some embodiments, controller 120 may be communicatively coupled to a dedicated controller, and controller 120 may serve as a central controller. Alternatively, any operations performed or described herein may be distributed among controller 120 and other computing systems. For example, model processing operations, model training, and / or storage may be performed by controller 120, another non-site-competitive system, a cloud-based computing system, or any combination of these or other systems. Some of these processing operations can also be assigned to individual sensors or control circuits within the chamber.

[0035] Below Figure 10 Examples of computer systems that can be used to implement at least a portion of controller 120 are described in detail herein. Operating parameters (process gas pressure, process gas flow rate, and / or the rotational position of the process unit) and operations may be stored as software routines in a computer-readable medium, which are executed or invoked to turn controller 120 into a dedicated controller for controlling the operation of the various chambers / modules described herein. Controller 120 is configured to perform any of the operations described herein. The various operations described herein may be performed automatically using controller 120, or some operations may be performed automatically or manually by a user.

[0036] The controller 120 can control various items directly or via other computers and / or controllers. For example, instructions executed by the controller 120 can cause the processing chamber 100 to perform operations in the recipe, such as flowing gas, increasing temperature, receiving substrates, etc. The controller 120 can be configured to control the rotational position, heating, and gas flow through the processing chamber 100 by providing outputs to the heat sources 141, 143, airflow, and motion components 121. Control may include control of the upper heat source 141, lower heat source 143, process gas source 151, purge gas source 162, motion components 121, and exhaust pump 157.

[0037] Controller 120 can be configured to adjust its output based on sensor readings, a system model, and stored readings and calculations. Controller 120 may include embedded software and compensation algorithms for calibrating measurements. Controller 120 may include one or more machine learning and / or artificial intelligence algorithms that estimate optimized parameters for deposition, purification, and / or cleaning operations. The one or more machine learning and / or artificial intelligence algorithms may use, for example, regression models (such as linear regression models) or clustering techniques to estimate the optimized parameters. The algorithm may be unsupervised or supervised.

[0038] The cover 154 may include multiple temperature sensors disposed within or on the cover 154 for measuring the temperature within the processing chamber 100. For example, a central temperature sensor 172 may be disposed on the cover 154 and configured to measure the temperature at or near the central portion of the processing chamber 100. More specifically, the central temperature sensor 172 may be configured to measure the temperature of the upper window 108 or the quartz dome. The central temperature sensor 172 may also be configured to measure the temperature of the top surface 150 of the substrate 102 and / or the substrate support 106. One or more temperature sensors 173 may also be distributed around the periphery of the processing chamber 100. These temperature sensors 173 may be configured to measure specific locations around the periphery of the processing chamber 100. For example, these temperature sensors 173 may point to the periphery of the upper window 108, to the periphery of internal components such as one or more gaskets 163, the substrate support 106, or the base, etc. Although in Figure 1 Although not explicitly shown, the processing chamber 100 may include other temperature sensors distributed throughout the processing chamber 100. For example, temperature sensors may be located in the lower heating module 145 and positioned to measure the temperature at the periphery and / or center of the bottom of the substrate support 106.

[0039] More generally, these temperature sensors may be specifically targeted at various components of the processing chamber 100. For example, the central temperature sensor 172 may be specifically used to measure the temperature at the center of the upper window 108 or the quartz dome. Temperature sensors may be specifically oriented and distributed to measure the temperature below the base or substrate support 106 and / or to measure the temperature at the top of the substrate or base or substrate support 106. Temperature sensors may be distributed and specifically oriented toward the liner in the processing chamber 100. These temperature sensor arrangements are provided by way of example only and are not intended to be limiting. Figure 1 Any component shown or described above may be assigned a specific temperature sensor configured to measure the temperature of that component. As described below, this allows for the analysis of the rate of temperature change associated with a specific component using individual temperature sensor data. This, in turn, allows the controller to identify specific components that may cause the processing chamber 100 to malfunction.

[0040] The temperature sensor can be implemented using any type of temperature sensor. For example, some embodiments may use a pyrometer. Some embodiments may use a thermocouple. Some embodiments may use a resistance temperature detector (RTD). Some embodiments may use a semiconductor-based temperature sensor. Some embodiments may use a temperature scanning system that includes a single sensor (e.g., a pyrometer) and is configured to scan the temperature of the entire chamber along a predetermined path through the upper / lower window. More generally, the temperature sensor can be implemented using any device configured to provide an output that varies in a manner depending on the temperature in the processing chamber 100.

[0041] Temperature sensors can be used to sample the temperature inside the processing chamber 100 during different operations performed in the processing chamber 100. For example, temperature sensors can be used to acquire temperature measurements that can be used to train a model. Figure 2 A flowchart 200 of a method for training a model to characterize a processing chamber, according to some embodiments, is shown. The method may be executed by a controller, including any controller and / or computer system described herein. The processing chamber may include an epitaxial deposition chamber or an epitaxial chamber.

[0042] This method may include receiving training temperature rate of change data (202) from multiple executions of a process performed in one or more thermal deposition chambers. In some embodiments, a model may be trained for a type of epitaxial chamber, and training temperature rate of change data may be received from multiple different epitaxial chambers of this type or from a specific chamber using one or more formulations for a particular film growth. Alternatively, some embodiments may train a model for a specific epitaxial chamber, and training temperature rate of change data may be received from multiple executions of a process on the same chamber. Note that temperature data and temperature rate of change data are used only as an example of data that can be used to characterize a processing chamber. Any other characteristic of the chamber may be used as a substitute for the temperature and temperature rate of change data in the embodiments described herein. For example, in any embodiment, temperature measurements may be replaced by other parameters, such as flow rate, gas concentration, etc. Therefore, temperature and temperature rate of change data are used only as examples and are not intended to be limiting. Any specific embodiment with respect to temperature may be modified without limitation to use any other chamber characteristics.

[0043] Figure 3 A block diagram illustrating a manner for generating temperature change rate data from a temperature sensor according to some embodiments is shown. The epitaxial chamber 302 may include a plurality of temperature sensors 304, such as those described above. Figure 1The temperature sensors shown are temperature sensors 304. When the epitaxial chamber 302 performs the process, temperature sensors 304 can record temperature measurements in real time throughout the process. Sensor sampling stage 310 can generate time-series data 306 as a series of continuous temperature measurements from temperature sensor 304. Time-series data 306 can then be processed by conversion stage 312, which converts time-series data 306 into temperature change rate data 308.

[0044] For example, the process performed in the epitaxial chamber 302 may include successive steps or stages. Each stage may be associated with a temperature setpoint. As the temperature in the epitaxial chamber 302 increases or decreases between these setpoints, transitions between these temperature setpoints in each stage may result in temperature transients. It has been found that the rate of change between these temperature setpoints may be more effective than absolute temperature measurements when characterizing the thermal response of the epitaxial chamber 302. Therefore, the transition stage 312 may analyze time-series data 306 including temperature transients between setpoints and derive temperature rate of change data. For example, the transition stage 312 may interpolate the slope of the best-fitting time-series data 306 at each transition. Alternatively, the transition stage 312 may perform a first derivative on the time-series data 306 to calculate the slope. Thus, the rate of change data 308 may include a set of first-derivative time-series data, slope values, and / or any other indication of the rate of change that may be observed in the time-series data 306.

[0045] Figure 4A graph 400 illustrates time-series data measured during a process performed in an epitaxial chamber, according to some embodiments. The process for generating training temperature data can include many different types of processes. In some embodiments, the process can include an actual epitaxial deposition process in the epitaxial chamber, performed by depositing an epitaxial film on a semiconductor substrate. Other embodiments may use more efficient or accurate methods for generating training temperature data. Instead of performing an actual epitaxial deposition process, these embodiments may run temperature cycles in the epitaxial chamber and record temperature measurements to capture training data. For example, a temperature setpoint from a formulation of an actual epitaxial deposition process can be used. However, instead of using an active deposition precursor typically used in deposition processes, an inert gas can be flowed into the epitaxial chamber instead of an active CVD precursor. The inert gas, such as H2, can include any non-reactive substance that does not cause film deposition on the substrate or the surface of the epitaxial chamber. The temperature setpoint can include a custom setpoint specifically for generating training temperature data, or a setpoint from an actual epitaxial deposition formulation can be used. This prevents the process used to generate training temperature data from failing to create a film or coating on the exposed surfaces of the epitaxial chamber, while still allowing the temperature to cycle between setpoints, just as occurs during actual epitaxial deposition. It also allows multiple cycles of the process to be repeated within the chamber while training temperature data is being acquired, without the need for cleaning. As mentioned above, actual CVD processes may generate surface coatings during use. The model and training process described herein can build a database over time to understand the chamber's performance in response to these surface coatings and other chamber variations over time.

[0046] Graph 400 shows curves representing time-series measurements from temperature sensors that can be used as training temperature data. For example, curve 412 could represent a measurement from a temperature sensor configured to measure the temperature at the top of the base. Curve 414 could represent a measurement from a temperature sensor configured to measure the temperature at the bottom of the base. Curve 410 could represent a measurement from a temperature sensor configured to measure the temperature on a window above the base. Curves 412 and 414 can use a temperature scale on the left Y-axis, while curve 410 can use a temperature scale on the right Y-axis. Other temperature sensors can also record measurements not recorded on... Figure 4 The time-series temperature data is clearly shown in the figure.

[0047] Graph 400 illustrates four distinct phases 402 in the process of capturing training temperature data. Each of these phases 402 can be associated with a different temperature setpoint. Between these temperature setpoints, graph 400 shows the transient temperature as the temperature transitions between the setpoints in each phase 402. For example, curve 412 can transition from a temperature setpoint between 1100°C and 1200°C in phase 402-1 to a new temperature setpoint of approximately 700°C in phase 402-2. The temperature transient between these two setpoints can be approximated as a linear transition. Temperature change rate data can be generated by calculating the derivative of the time series data during the temperature transient, by interpolating the slope, by fitting a line to the time series data, and / or by using any other method to represent the rate of change during the transition.

[0048] The rate of temperature change data can be represented as a set of estimated slope values ​​for the transition between each stage shown in graph 400. These estimated slope values ​​can be calculated for each temperature sensor in the epitaxial chamber. The process for collecting training rate of temperature change data can be repeated on the same epitaxial chamber or in multiple different epitaxial chambers. For example, one or more epitaxial chambers can be installed at a manufacturing facility, and these epitaxial chambers can be used to generate training rate of temperature change data. When a new epitaxial chamber is added to an existing epitaxial chamber at the manufacturing facility, the training rate of temperature change data can be used to train a model to predict whether the new epitaxial chamber will match the results of the existing chamber.

[0049] Some embodiments may use supervised training algorithms to train the model. The training temperature change rate data collected above can be labeled by performing an actual epitaxial deposition process on the substrate and using the results to label the training data. Figure 2 The training method of flowchart 200 may also include receiving training results of the thermal deposition process (204) measured from a substrate on which a thermal deposition process is performed in one or more thermal deposition chambers.

[0050] Figure 5 A flowchart 500 illustrating the generation of labels for training temperature change rate data is shown according to some embodiments. After performing the above-described process for generating training change rate data, the epitaxial chamber 302 can be used to perform an actual epitaxial deposition process 510 on the substrate 502. After the deposition process 510 is completed, deposition profile data 504 can be measured from the substrate 502, which may include the thickness profile of the film sensitive to the thermal distribution and thermal history of the chamber. A metrology process 512 or other measurement processes can be performed on the substrate 502 to measure the characteristics of the deposited epitaxial film. For example, the metrology process 512 can measure the film thickness at different locations on the substrate to determine the film uniformity on the substrate.

[0051] Deposition profile data 504 can be provided to a classification stage 514. A classifier process 508 can be used to generate a label 511 for the deposition profile data 504. For example, the classifier process 508 can compare the thickness, uniformity, resistivity, strain, and / or other properties of the deposition profile data 504 to a target set of properties. A tolerance 506 can be provided to the classifier process 508. If the deposition profile data 504 is within the tolerance 506 of the target set of properties, the classifier process 508 can generate a label 511 indicating that the epitaxial chamber 302 performed as expected. If the deposition profile data 504 is not within the tolerance 506 of the target set of properties, the classifier process 508 can generate a label 511 indicating that the epitaxial chamber did not perform as expected. In some embodiments, the label 511 can be a binary value indicating whether the epitaxial chamber 302 performed as expected. Other embodiments may use a digital scale or numerical value (e.g., 0.0 to 1.0) that indicates, for example, how close the epitaxial chamber 302 is to the substrate from which the target properties are generated.

[0052] Back Figure 2 The training method in flowchart 200 may also include generating training data based on training temperature change rate data labeled using a thermal deposition process (206). Figure 6 A flowchart 600 for training a model to predict epitaxial chamber performance, according to some embodiments, is shown. Training temperature change rate data 308 can be labeled using a corresponding tag 511 for each epitaxial chamber. For example, the epitaxial chamber can perform a temperature cycling process using an inert gas such as H2 as a carrier gas without an active precursor to generate training temperature change rate data 308, after which the epitaxial chamber can perform an actual epitaxial deposition process on the substrate, which can be measured to generate tag 511. Alternatively, the training temperature change rate data 308 can be captured during the actual epitaxial deposition process on the substrate used to generate tag 511. The labeled training temperature change rate data can be considered as training pairs 610 for training the model. Although in Figure 6 Only a single training pair 610 is shown in the figure, but it should be understood that multiple training pairs can be provided to the training algorithm of the model from multiple chambers or from multiple processes in the same chamber.

[0053] Figure 2 The training method in flowchart 200 may also include executing a supervised learning algorithm to train the model using the training data (208). Figure 6The training phase 612 is illustrated as potentially including a method for executing training algorithm 602 on model 604. Model 604 may include a machine learning model trained to model the thermal response of the epitaxial chamber when thermal energy is added. Model 604 may take into account the thermal mass of various components within the chamber, and therefore training algorithm 602 may receive temperature measurements from component-specific temperature sensors throughout the chamber. For example, as training algorithm 602 adjusts the weights or parameters of model 604, these weights or parameters may be trained such that model 604 approximates the thermal behavior of these components when absorbing or releasing thermal energy based on their thermal mass. Training phase 612 may also be trained as a classification model that receives rate-of-change data 308 and outputs a classification based on the degree of matching between the input data and the training data. For example, model 604 may be implemented using a neural network or convolutional learning network to classify the input, but the model is not necessarily limited to neural networks. Any type of model may be used, including data pattern models, physical models, hybrid models, and so on.

[0054] After training phase 612 is completed, the process generates a trained model 606. The trained model 606 can now be used to predict whether the performance of a new or existing epitaxial chamber will fall within the target operating range, without requiring actual deposition processes and measurements of deposition profile data on an actual substrate. Furthermore, as new training data becomes available, the trained model 606 can be continuously retrained and / or improved over time. For example, some implementations may periodically collect temperature change rate data from existing epitaxial chambers. The substrate with the deposited epitaxial film may also be periodically scanned to capture deposition profile data on the substrate. This information can be combined to form new labeled training data, and training phase 612 can be repeated to improve the trained model 606 as needed.

[0055] Figure 7 A flowchart 700 of a method for characterizing an epitaxial chamber according to some embodiments is shown. This method can be performed using a trained model 606 as described above. For example, many different scenarios can benefit from using the trained model 606 to characterize the epitaxial chamber and predict whether the performance of the epitaxial chamber will generate a film within a target property set. For example, when adding a new epitaxial chamber to a manufacturing facility, there may be a concern about matching the performance of the new epitaxial chamber with the existing performance of the chambers already in use. By running the above process to generate temperature change rate data, and subsequently by providing this data as input to the trained model 606, the trained model 606 can be used to predict whether the performance of the new epitaxial chamber will match the properties of the existing epitaxial chambers. The output of the trained model 606 can then indicate the degree or confidence level of the predicted match between the new chamber and the existing chambers.

[0056] The method may include performing a process on a heat treatment chamber that causes the temperature within the chamber to vary during the process (702). This "process" may be related to the above. Figures 3 to 4 The process described herein is the same as that used for measuring the generation temperature. For example, the process could be an inert process, in which no active precursor is supplied to the epitaxial chamber and no actual epitaxial deposition occurs. Instead, the process could include multiple different temperature setpoints that allow the epitaxial chamber to transition between temperatures and exhibit the thermal response of the epitaxial chamber to these transitions.

[0057] The method may also include recording temperature measurements (704) using one or more temperature sensors in the heat treatment chamber during the process. As described above, the temperature sensors may be associated with individual components and / or locations within the epitaxial chamber. These temperature sensors can record temperature measurements during the process as a set of time-series data. The method may also include deriving temperature change rate data from the temperature measurements (706). As described above, the temperature change rate data can be derived using calculated derivatives, slope interpolation, line fitting, and other techniques for representing the rate of change during temperature transitions in the heat treatment chamber.

[0058] The method may further include providing temperature change rate data to the trained model (708). As described above, the trained model may be configured to receive temperature change rate data as input and provide an output predicting the degree of match between the outcome of the epitaxial deposition process performed in the epitaxial chamber and the target outcome. The target outcome may include thickness distribution, resistivity, strain, crystal quality, and / or any other characteristics of the process. Figure 8 A flowchart 800 is shown illustrating the use of a trained model 804 to predict the performance of a new epitaxial chamber according to some embodiments. As described in detail above, training data with multiple labels can be provided from one or more existing epitaxial chambers 802 to train or retrain the trained model 804. When a new epitaxial chamber 806 is added to the set of existing epitaxial chambers 802, the above-described process can be performed on the new epitaxial chamber 806 to generate temperature change rate data 808 for the new epitaxial chamber 806. The temperature change rate data 808 can then be provided as input to the trained model 804.

[0059] Some embodiments may also provide a tolerance 810 for the trained model 804. This allows adjusting how closely the predictive performance of the new epitaxial chamber 806 needs to match the performance of the existing epitaxial chamber 802. For example, increasing the tolerance 810 may relax the classification parameters of the trained model 804, making predicted matches more likely. Conversely, decreasing the tolerance 810 may require the predictive performance of the new epitaxial chamber 806 to more closely match the performance of the existing epitaxial chamber 802.

[0060] The method may also include receiving an output 812 from a trained model 804 that predicts the degree of match between the outcome of the thermal deposition process and the target outcome (710). The output 812 of the trained model 804 may include binary and / or scalar values ​​representing the level or degree of confidence that the predicted performance of the new epitaxial chamber 806 will match the performance of the existing epitaxial chamber 802. For example, some embodiments of the trained model 804 may provide separate outputs 814 that are specific to each sensor recording temperature measurements in the epitaxial chamber 806. This allows the outputs 812 to be used to predict the overall match of the performance of the new epitaxial chamber 806, and also to indicate how close the thermal response of individual components is in the new epitaxial chamber 806. For example, output 814-1 indicates a 95% probability of a match based on temperature change rate data from a first component (e.g., the top of the pedestal), while output 814-2 indicates only a 65% probability of a match based on temperature change rate data from a second component (e.g., a location on a quartz dome). These specific outputs indicating mismatch parameters can be used to match (e.g., adjust, replace, etc.) hardware components between chambers to improve the overall matching result.

[0061] The method may also include model-based output characterization of the heat treatment chamber (712). Characterization of the new epitaxial chamber 806 may include evaluating the output 812 from the trained model 804 to determine the overall probability of a performance match between the new epitaxial chamber 804 and the existing epitaxial chamber 802. Such characterization may include binary characterization (e.g., match, mismatch) and the confidence level or degree of a predicted match.

[0062] In some embodiments, characterization of the new epitaxial chamber 806 may include identifying specific components, such as a temperature sensor, a flow controller, or any other hardware component within the new epitaxial chamber, as a reason for matching determination 816. Figure 8In the example, the match determination 816 may indicate that the new epitaxial chamber 806 was not predicted to match the performance of the epitaxial chamber 802 within tolerance 810. The match determination 816 may further indicate that the sensor associated with output 814-2 (e.g., a temperature sensor recording temperature measurements from the quartz dome) contributes the most to the mismatch. The user can use this information to diagnose the mismatch as a problem with a specific component. For example, the component may be incorrectly installed, resulting in insufficient contact with other interior parts of the epitaxial chamber. The quartz dome may also have a film or coating that reduces heat transfer to the quartz dome. This information can be used to correct problems with the new epitaxial chamber 806, such as reinstalling the quartz dome, replacing the quartz dome, cleaning the quartz dome, etc. More generally, any mismatch identified by the system can be associated with a specific component, and the model / software can therefore suggest calibration, offset, or adjustment of that component to correct the mismatch. For example, if the mismatch is due to temperature drift of the dome caused by transmittance loss, a translation or offset factor can be suggested to the user to recalibrate the component / device. After resolving any issues indicated by the matching determination 816, the method of flowchart 700 can be repeated to determine whether a performance match is now predicted.

[0063] Figure 9 Alternative scenarios are illustrated for an existing epitaxial chamber 906 undergoing periodic testing or preventative maintenance according to some embodiments. As described above, training data from one or more chambers present at chamber 902 can be used to generate or retrain a trained model 904. One of these epitaxial chambers 906 may undergo preventative maintenance (PM). PM may include at least a portion of the removed epitaxial chamber. PM may also include cleaning the epitaxial chamber and / or replacing at least one component of the epitaxial chamber. After reinstalling the epitaxial chamber 906 following the completion of PM, the trained model 904 can be used to test the epitaxial chamber 906 to determine whether PM has an adverse effect on the predictive performance of the epitaxial chamber 906.

[0064] Alternatively, the same process can be performed as part of a test run of the epitaxial chamber 906, without necessarily requiring any part-time processing (PM). For example, each epitaxial chamber 902 can be tested periodically to identify whether performance has drifted over time. These test results can be used to determine whether PM is needed, whether specific parts need to be replaced based on model outputs, and / or whether specific parts need to be cleaned or repaired.

[0065] The epitaxial chamber 906 can be used to generate new temperature change rate data 908, which is then fed to a trained model 904 with optional tolerances 910. The model can be trained prior to performing PM or test runs. The model output 912 can then be used to characterize the epitaxial chamber 906. For example, characterization of the epitaxial chamber 906 may include a health status determination 916, which may include an indication of the performance drift of the epitaxial chamber 906 over time and whether the epitaxial chamber 906 still falls within the target performance tolerance 910. Some embodiments may also provide drift and health status determinations for individual components based on the output 914 assigned to a particular sensor as described above.

[0066] It should be understood that, according to various embodiments, Figure 2 and Figure 7 The specific steps illustrated provide a particular method for training and using a model to predict the performance of an epitaxial chamber. According to alternative embodiments, other sequences of steps may also be performed. For example, alternative embodiments may perform the steps outlined above in a different order. Furthermore, Figure 2 and Figure 7 The individual steps shown may include multiple sub-steps, which can be adapted to various sequences of individual steps for execution. Furthermore, depending on the specific application, additional steps may be added or removed. Many variations, modifications, and alternatives also fall within the scope of this disclosure.

[0067] Each method described herein can be implemented by a computer system. Each step of these methods can be performed automatically by the computer system and / or may provide input / output involving a user. For example, a user may provide input for each step of the method, and each of these inputs may provide a specific output in response to a request for such input, wherein the output is generated by the computer system. Each input may be received in response to a corresponding requested output. Furthermore, input may be received from a user, received as a data stream from another computer system, retrieved from a memory location, retrieved via a network, requested from a network service, and / or similarly. Similarly, output may be provided to a user, provided as a data stream to another computer system, stored in a storage location, sent via a network, provided to a network service, and / or similarly. In short, each step of the methods described herein can be performed by a computer system and may involve any number of inputs, outputs, and / or requests from the computer system, which may or may not involve a user. Steps that do not involve a user may be referred to as being performed automatically by the computer system without human intervention. Therefore, it will be understood from this disclosure that each step of each method described herein may be modified to include input and output to and from the user, or may be performed automatically by a computer system without human intervention, wherein any determination is made by the processor. Furthermore, some embodiments of each method described herein may be implemented as a set of instructions stored on a tangible, non-transitory storage medium to form a tangible software product.

[0068] Figure 10 An exemplary computer system 1000 in which various embodiments can be implemented is shown. System 1000 can be used to implement any of the computer systems described above. As shown, computer system 1000 includes a processing unit 1004 that communicates with a plurality of peripheral subsystems via a bus subsystem 1002. These peripheral subsystems may include a processing acceleration unit 1006, an I / O subsystem 1008, a storage subsystem 1018, and a communication subsystem 1024. Storage subsystem 1018 includes a tangible computer-readable storage medium 1022 and system memory 1010.

[0069] Bus subsystem 1002 provides an mechanism for enabling various components and subsystems of computer system 1000 to communicate with each other for intended purposes. Although bus subsystem 1002 is schematically shown as a single bus, alternative embodiments of the bus subsystem may utilize multiple buses. Bus subsystem 1002 may be any of several types of bus architectures, including memory buses or memory controllers, peripheral buses, and local buses using any of the various bus architectures. For example, such architectures may include Industry Standard Architecture (ISA) buses, Micro Channel Architecture (MCA) buses, Enhanced ISA (EISA) buses, Video Electronics Standards Association (VESA) local buses, and Peripheral Component Interconnect (PCI) buses, which may be implemented as mezzanine buses manufactured according to the IEEE P1386.1 standard.

[0070] Processing unit 1004 may be implemented as one or more integrated circuits (e.g., conventional microprocessors or microcontrollers) to control the operation of computer system 1000. One or more processors may be included in processing unit 1004. These processors may include single-core or multi-core processors. In some embodiments, processing unit 1004 may be implemented as one or more independent processing units 1032 and / or 1034, each including a single-core or multi-core processor. In other embodiments, processing unit 1004 may also be implemented as a quad-core processing unit formed by integrating two dual-core processors into a single chip.

[0071] In various embodiments, processing unit 1004 can execute various programs in response to program code and can maintain multiple concurrently executing programs or processes. At any given time, some or all of the program code to be executed may reside in processor 1004 and / or storage subsystem 1018. Through appropriate programming, processor 1004 can provide the various functions described above. Computer system 1000 may also include processing acceleration unit 1006, which may include a digital signal processor (DSP), a dedicated processor, and / or the like.

[0072] The I / O subsystem 1008 may include user interface input devices and user interface output devices. User interface input devices may include keyboards, pointing devices such as mice or trackballs, touchpads or touchscreens integrated into displays, scroll wheels, click wheels, dial pads, buttons, switches, keypads, audio input devices with voice command recognition systems, microphones, and other types of input devices. Furthermore, user interface input devices may include voice recognition sensing devices that enable users to interact with a voice recognition system via voice commands. User interface input devices may also include, but are not limited to, three-dimensional (3D) mice, joysticks or pointers, gamepads and drawing tablets, as well as audio / visual devices such as speakers, digital cameras, digital video recorders, portable media players, webcams, image scanners, fingerprint scanners, barcode readers, 3D scanners, 3D printers, laser rangefinders, and eye-tracking devices. Additionally, user interface input devices may include, for example, medical imaging input devices such as computed tomography (CT), magnetic resonance imaging (MRI), positional emission computed tomography (PECT), and medical ultrasound examination devices. User interface input devices may also include, for example, audio input devices such as MIDI keyboards, digital musical instruments, augmented reality (AR) input / output devices, virtual reality (VR) input / output devices, etc.

[0073] User interface output devices may include display subsystems, indicator lights, or non-visual displays such as audio output devices. Display subsystems may be cathode ray tubes (CRTs), flat panel displays such as those using liquid crystal displays (LCDs) or plasma displays, projection devices, touchscreens, etc. Generally, the term "output device" is used to encompass all possible types of devices and mechanisms for outputting information from computer system 1000 to the user or other computers. For example, user interface output devices may include, but are not limited to, various display devices that visually convey text, graphics, and audio / video information, such as monitors, printers, speakers, headphones, car navigation systems, plotters, voice output devices, and modems.

[0074] Computer system 1000 may include a storage subsystem 1018 that includes software elements shown to be currently located within system memory 1010. System memory 1010 may store program instructions that are loadable and executable on processing unit 1004, as well as data generated during the execution of these programs.

[0075] Depending on the configuration and type of the computer system 1000, the system memory 1010 may be volatile (such as random access memory (RAM)) and / or non-volatile (such as read-only memory (ROM), flash memory, etc.). RAM typically includes data and / or program modules that the processing unit 1004 can immediately access and / or is currently operating and executing. In some implementations, the system memory 1010 may include various types of memory, such as static random access memory (SRAM) or dynamic random access memory (DRAM). In some implementations, the basic input / output system (BIOS) may typically be stored in ROM, containing basic routines that facilitate the transfer of information between components within the computer system 1000, such as during startup. By way of example and not limitation, system memory 1010 also illustrates application 1012, which may include client applications, web browsers, middleware applications, relational database management systems (RDBMS), program data 1014, and operating system 1016. For example, operating system 1016 may include various versions of Microsoft Windows®, Apple Macintosh®, and / or Linux operating systems, various commercially available UNIX® or UNIX-like operating systems (including but not limited to various GNU / Linux operating systems, Google Chrome® operating system, etc.), and / or mobile operating systems such as iOS, Windows® Phone, Android® OS, BlackBerry® 10 OS, and Palm® OS.

[0076] The storage subsystem 1018 may also provide a tangible computer-readable storage medium for storing basic programmed and data structures that provide the functionality of some embodiments. Software (programs, code modules, instructions) that provides the above-described functionality when executed by a processor may be stored in the storage subsystem 1018. These software modules or instructions may be executed by the processing unit 1004. The storage subsystem 1018 may also provide a repository for storing data used according to some embodiments.

[0077] The storage subsystem 1000 may also include a computer-readable storage medium reader 1020, which may be further connected to a computer-readable storage medium 1022. The computer-readable storage medium 1022, together with and as appropriate, the system memory 1010, can comprehensively represent remote, local, fixed and / or removable storage devices plus storage media for temporarily and / or more persistently containing, storing, transmitting and retrieving computer-readable information.

[0078] The computer-readable storage medium 1022 containing code or portions of code may also include any suitable medium, including storage and communication media, such as, but not limited to, volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing and / or transmitting information. This may include tangible computer-readable storage media such as RAM, ROM, electronically erasable programmable ROM (EEPROM), flash or other memory technologies, CD-ROM, digital versatile disk (DVD), or other optical storage, magnetic cards, magnetic tape, disk storage devices or other magnetic storage devices, or other tangible computer-readable media. This may also include non-tangible computer-readable media such as data signals, data transmissions, or any other medium that can be used to transmit the required information and is accessible by the computing system 1000.

[0079] For example, computer-readable storage medium 1022 may include hard disk drives that read from or write to non-removable, non-volatile magnetic media, disk drives that read from or write to removable, non-volatile magnetic disks, and optical disk drives that read from or write to removable, non-volatile optical disks (such as CD ROMs, DVDs, and Blu-ray® discs) or other optical media. Computer-readable storage medium 1022 may include, but is not limited to, Zip® drives, flash memory cards, universal serial bus (USB) flash drives, secure digital (SD) cards, DVD discs, digital video tapes, etc. Computer-readable storage medium 1022 may also include solid-state drives (SSDs) based on non-volatile memory, such as flash-based SSDs, enterprise flash drives, solid-state ROMs, etc.; volatile memory-based SSDs, such as solid-state RAM, dynamic RAM, static RAM, DRAM-based SSDs, magnetoresistive RAM (MRAM) SSDs, and hybrid SSDs using a combination of DRAM and flash-based SSDs. Disk drives and their associated computer-readable media provide non-volatile storage for computer-readable instructions, data structures, program modules and other data for computer system 1000.

[0080] The communication subsystem 1024 provides an interface to other computer systems and networks. The communication subsystem 1024 serves as an interface for receiving data from the computer system 1000 and sending data from the computer system 1000 to other systems. For example, the communication subsystem 1024 may enable the computer system 1000 to connect to one or more devices via the Internet. In some embodiments, the communication subsystem 1024 may include radio frequency (RF) transceiver components (e.g., using cellular phone technology, advanced data network technologies such as 3G, 4G, or EDGE (Enhanced Data Rate for Global Evolution), WiFi (IEEE 802.11 family of standards or other mobile communication technologies, or any combination thereof), global positioning system (GPS) receiver components, and / or other components for accessing wireless voice and / or data networks. In some embodiments, the communication subsystem 1024 may provide a wired network connection (e.g., an Ethernet network) as a supplement to or alternative to the wireless interface.

[0081] In some embodiments, the communication subsystem 1024 may also receive input communications in the form of structured and / or unstructured data feeds 1026, event streams 1028, event updates 1030, etc., on behalf of one or more users who may use the computer system 1000.

[0082] For example, the communication subsystem 1024 may be configured to receive in real time data feeds 1026 from users of social networks and / or other communication services, or network feeds such as Rich Site Summary (RSS) feeds, and / or from one or more Figure 3 Real-time updates of information sources.

[0083] Furthermore, the communication subsystem 1024 can also be configured to receive data in the form of continuous data streams, which may include event streams 1028 of real-time events and / or event updates 1030. These event streams may be continuous or unrestricted in nature, without a definite end. Examples of applications that generate continuous data may include, for example, sensor data applications, financial quote machines, network performance measurement tools (e.g., network monitoring and business management applications), point-and-click flow analysis tools, vehicle traffic monitoring, etc.

[0084] The communication subsystem 1024 may also be configured to output structured and / or unstructured data feeds 1026, event streams 1028, event updates 1030 and / or the like to one or more databases that can communicate with one or more streaming data source computers coupled to the computer system 1000.

[0085] The computer system 1000 can be of a variety of types, including handheld portable devices (e.g., iPhone® mobile phones, iPad® tablet computers, PDAs), wearable devices, PCs, workstations, mainframes, kiosks, server racks, or any other data processing system.

[0086] Due to the constantly evolving nature of computers and networks, the description of the computer system 1000 shown in the figures is merely a specific example. Many other configurations with more or fewer components are possible compared to the system shown in the figures. For example, custom hardware may be used and / or specific elements may be implemented in hardware, firmware, software (including small applications), or a combination thereof. Furthermore, connections to other computing devices, such as network input / output devices, may be employed. Other ways and / or methods for implementing various embodiments should be apparent based on the disclosure and teachings provided herein.

[0087] As used herein, the terms “about,” “approximately,” or “substantially” may be interpreted as having the scope that a person skilled in the art would expect from the description.

[0088] In the foregoing description, numerous specific details have been set forth for purposes of explanation and to provide a thorough understanding of the various embodiments. However, it will be apparent that some embodiments may be practiced without these specific details. In other instances, well-known structures and apparatuses are shown in block diagram form.

[0089] The foregoing description provides only illustrative embodiments and is not intended to limit the scope, applicability, or configuration of this disclosure. Rather, the foregoing description of various embodiments will provide enabling disclosures for implementing at least one embodiment. It should be understood that various changes may be made to the function and arrangement of elements without departing from the spirit and scope of some embodiments set forth in the appended claims.

[0090] Specific details are set forth in the foregoing description to provide a thorough understanding of the embodiments. However, it should be understood that the embodiments may be practiced without these specific details. For example, circuits, systems, networks, processes, and other components may be shown as components in the form of block diagrams so as not to obscure the embodiments with unnecessary details. In other instances, well-known circuits, processes, algorithms, structures, and techniques may be shown without unnecessary details in order to avoid obscuring the embodiments.

[0091] Furthermore, it should be noted that individual embodiments may be described as processes shown in flow diagrams, flowcharts, data flow diagrams, structural or block diagrams. Although a flow may describe operations as sequential processes, many operations may be executed in parallel or concurrently. Additionally, the order of operations may be rearranged. A process terminates when its operations are completed, but there may be other steps not included in the diagram. A process may correspond to a method, function, step, subroutine, subroutine, etc. When a process corresponds to a function, its termination may correspond to the function returning to the calling function or the main function.

[0092] The term "computer-readable medium" includes, but is not limited to, portable or fixed storage devices, optical storage devices, wireless channels, and various other media capable of storing, containing, or carrying instructions and / or data. A code segment or machine-executable instruction may represent a program, function, subroutine, program, routine, subroutine, module, software package, class, or any combination of instructions, data structures, or program descriptions. A code segment can be coupled to another code segment or hardware circuitry by passing and / or receiving information, data, arguments, parameters, or memory contents. Information, arguments, parameters, data, etc., can be passed, forwarded, or transmitted via any suitable means, including memory sharing, message passing, symbol passing, network transmission, etc.

[0093] Furthermore, embodiments may be implemented using hardware, software, firmware, intermediate software, microcode, hardware description languages, or any combination thereof. When implemented in software, firmware, intermediate software, or microcode, program code or code segments for performing necessary tasks may be stored in a machine-readable medium. The processor can then perform the necessary tasks.

[0094] In the foregoing specification, features have been described with reference to specific embodiments thereof, but it should be understood that not all embodiments are limited thereto. Various features and aspects of some embodiments may be used alone or in combination. Furthermore, embodiments may be used in any number of environments and applications beyond those described herein without departing from the broader spirit and scope of this specification. Therefore, the specification and drawings should be considered illustrative rather than restrictive.

[0095] Furthermore, for ease of illustration, the methods are described in a specific order. It should be understood that in alternative embodiments, these methods may be performed in a different order than described. It should also be understood that the methods described above may be executed by hardware components or may be embodied in a sequence of machine-executable instructions that can be used to cause a machine, such as a general-purpose or special-purpose processor, or logic circuitry programmed with instructions, to execute these methods. These machine-executable instructions may be stored on one or more machine-readable media, such as a CD-ROM or other types of optical disks, floppy disks, ROM, RAM, EPROM, EEPROM, magnetic cards or optical cards, flash memory, or other types of machine-readable media suitable for storing electronic instructions. Alternatively, these methods may be executed by a combination of hardware and software.

Claims

1. A method of characterizing a thermal processing chamber, the method comprising: causing a thermal processing chamber to perform a process, wherein the process causes a temperature in the thermal processing chamber to change during the process; causing temperature measurements to be recorded by one or more temperature sensors in the thermal processing chamber during the process; deriving temperature rate of change data from the temperature measurements; providing the temperature rate of change data to a model configured to receive the temperature rate of change data as input and provide an output predicting a degree of match of a result of a thermal deposition process performed in the thermal processing chamber to a target result; receiving the output from the model, the output predicting a degree of match of the result of the thermal deposition process to a target result; and characterizing the thermal processing chamber based on the output of the model.

2. The method of claim 1, the method further comprising training the model prior to providing the temperature rate of change data to the model, wherein training the model comprises: receiving training temperature rate of change data from a plurality of performances of the process performed by one or more thermal processing chambers; receiving training results of the thermal deposition process measured from substrates on which the thermal deposition process was performed by the one or more thermal processing chambers; generating training data based on the training temperature rate of change data labeled using the training results of the thermal deposition process; performing a supervised learning algorithm to train the model using the training data.

3. The method of claim 2, wherein: the one or more thermal processing chambers and the thermal processing chamber are the same chamber; and characterizing the thermal processing chamber comprises: characterizing whether a current performance of the thermal processing chamber matches a previous performance of the thermal processing chamber.

4. The method of claim 2, wherein: the training temperature rate of change data and the training results are received prior to a preventative maintenance of the thermal processing chamber, wherein at least a portion of the thermal processing chamber is disassembled, at least one component of the thermal processing chamber is replaced, and the thermal processing chamber is reassembled; and the thermal processing chamber is characterized based on the output from the model after the preventative maintenance is completed.

5. The method of claim 1, wherein the process comprises: depositing an epitaxial layer on a substrate.

6. The method of claim 1, wherein the process comprises: causing a temperature in the thermal processing chamber to change without an active precursor flowing into the thermal processing chamber, such that the temperature changes in the thermal processing chamber without a layer being deposited on a substrate.

7. The method of claim 6, wherein the process comprises an inert gas flowing into the thermal processing chamber in place of the active precursor.

8. A system, the system comprising: one or more processors; and one or more memory devices comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising: causing a thermal processing chamber to perform a process, wherein the process causes a temperature in the thermal processing chamber to change during the process; causing temperature measurements to be recorded by one or more temperature sensors in the thermal processing chamber during the process; deriving temperature rate of change data from the temperature measurements; providing the temperature rate of change data to a model configured to receive the temperature rate of change data as input and provide output predicting a degree of match of a result of a thermal deposition process performed in the thermal processing chamber to a target result; receiving the output from the model predicting the degree of match of the result of the thermal deposition process to a target result; and characterizing the thermal processing chamber based on the output of the model.

9. The system of claim 8, wherein the process comprises a plurality of process steps, wherein the plurality of process steps comprise a plurality of temperature setpoints such that a temperature in the thermal processing chamber moves between the plurality of temperature setpoints during the process.

10. The system of claim 9, wherein the temperature rate of change data reports an approximate slope of a temperature transition between the plurality of temperature setpoints.

11. The system of claim 8, wherein: the temperature measurements comprise a time series of temperature readings from the one or more temperature sensors; and the temperature rate of change data reports a computed higher-order derivative of the time series of temperature readings.

12. The system of claim 8, wherein the thermal processing chamber comprises a quartz dome above a pedestal, and a temperature sensor of the one or more temperature sensors is configured to measure a temperature of the quartz dome.

13. The system of claim 8, wherein the thermal processing chamber comprises a pedestal, a first temperature sensor of the one or more temperature sensors is configured to measure a temperature below the pedestal, and a second temperature sensor of the one or more temperature sensors is configured to measure a temperature of a substrate on top of the pedestal.

14. The system of claim 8, wherein the thermal processing chamber comprises a liner, and a first temperature sensor of the one or more temperature sensors is configured to measure a temperature of the liner.

15. One or more non-transitory computer-readable media comprising instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising: causing a thermal processing chamber to perform a process, wherein the process causes a temperature in the thermal processing chamber to change during the process; causing temperature measurements to be recorded by one or more temperature sensors in the thermal processing chamber during the process; deriving temperature rate of change data from the temperature measurements; providing the temperature rate of change data to a model configured to receive the temperature rate of change data as input and provide output predicting a degree of match of a result of a thermal deposition process performed in the thermal processing chamber to a target result; receiving the output from the model predicting the degree of match of the result of the thermal deposition process to a target result; and characterizing the thermal processing chamber based on the output of the model. ​ 16. The one or more non-transitory computer-readable media of claim 15, wherein the model is trained to model a thermal response of the thermal processing chamber when thermal energy is added to the thermal processing chamber.

17. The one or more non-transitory computer-readable media of claim 16, wherein the thermal response of the thermal processing chamber accounts for a thermal mass of the thermal processing chamber.

18. The one or more non-transitory computer-readable media of claim 15, wherein the output of the model comprises one or more scalar values corresponding to the one or more temperature sensors and indicative of a confidence level of the result of the thermal deposition process to the target result of each of the one or more temperature sensors.

19. The one or more non-transitory computer-readable media of claim 15, wherein characterizing the thermal processing chamber based on the output from the model comprises: characterizing the thermal processing chamber as mismatched to one or more thermal processing chambers used to train the model; and identifying a component of the thermal processing chamber as a cause of the mismatch of the thermal processing chamber to the one or more chambers.

20. The one or more non-transitory computer-readable media of claim 15, wherein the operations further comprise: providing the model with a tolerance indicative of an allowed deviation from the target result.

Images