How to monitor the surface condition of components

Abstract

The method includes applying thermal energy to a component, determining a thermal response of the component in response to the application of the thermal energy, and determining a thermal characteristic of the component based on the reference thermal response and the thermal response. The method includes predicting a surface condition of the component based on the thermal characteristic and a predictive analytics model, where the predictive analytics model relates the thermal characteristic of the component to the estimated surface condition of the component.

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to U.S. Provisional Application No. 63 / 019,267, filed May 2, 2020, the disclosure of which is incorporated herein by reference.

[0002] The present disclosure generally relates to a method for monitoring the surface condition of components in a thermal system, such as a showerhead and / or pedestal in a semiconductor processing chamber. [Background technology]

[0003] The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.

[0004] The emissivity of a material is its efficiency at emitting energy as thermal radiation. The emissivity of a system component's surface changes over time. For example, in a semiconductor processing chamber where various deposition processes are performed, chemical reactions of the deposition material may occur within the semiconductor processing chamber and cause unwanted deposition of the deposition material on the chamber walls, liner, and lid. In a fluid line, scale may build up on the fluid line's surface. The emissivity of a system component's surface can be affected by deposits and scale buildup. When a system component is used to generate or transfer heat, changes in the emissivity of the system component's surface can affect the desired heat output and performance of the system component. Summary of the Invention [Problem to be solved by the invention]

[0005] However, changes in the emissivity of system component surfaces are generally not well understood. If a system component degrades significantly due to changes in emissivity, system maintenance will be required to replace the degraded component, resulting in unplanned downtime. To maintain system component performance and / or reduce / prevent downtime, preventative maintenance is typically scheduled for cleaning, refurbishing, or replacing critical components based on the expected rate of change rather than the actual need. As a result, preventative maintenance may be performed too late or too early.

[0006] The present disclosure addresses, among other things, problems associated with detecting changes in emissivity of the surface of a piece of equipment. [Means for solving the problem]

[0007] In one aspect, a method includes applying thermal energy to a component, determining a thermal response of the component in response to the application of the thermal energy, and determining a thermal property of the component based on a reference thermal response and the thermal response. The method also includes predicting a surface condition of the component based on the thermal property and a predictive analytics model, the predictive analytics model relating the thermal property of the component to an estimated surface condition of the component.

[0008] In one form, the thermal characteristic is based on a difference between the reference thermal response and the thermal response.

[0009] In one form, the thermal property is the emissivity of the component, the thermal coupling between different regions of the component, the thermal gain of the component, the electrical resistance-temperature relationship of the component, the gas convective coupling of the component, or a combination thereof.

[0010] In one form, applying thermal energy to the component further comprises increasing the thermal energy applied to the component.

[0011] In one form, applying thermal energy to the component further comprises reducing the thermal energy applied to the component.

[0012] In one form, the surface condition indicates an amount of material deposit on the surface of the component.

[0013] In one form, the thermal response is the rate at which thermal energy is dissipated by the component.

[0014] In one form, the method further includes varying at least one of an intensity and a duration of the thermal energy to generate a thermal signature of the component, the thermal signature being a pictorial representation of the thermal response.

[0015] In one form, the method further includes determining the thermal property of the component based on a reference thermal signature and the thermal signature.

[0016] In one form, the component is selected from the group consisting of a semiconductor processing chamber wall, a semiconductor processing chamber liner, a semiconductor processing chamber showerhead, a semiconductor processing chamber lid, a fluid heating tube wall, a heater surface, and a heater sheath.

[0017] In one form, the method further includes measuring the temperature of the component for a predetermined period of time to determine the thermal response.

[0018] In one form, the method further includes determining energy dissipation by the component based on the change in temperature of the component over the predetermined time period.

[0019] In one form, the method further includes determining a change in emissivity of the component based on the change in temperature of the component over the predetermined time period.

[0020] In one form, the thermal response of the component is determined in response to the temperature of the component being equal to a predetermined temperature.

[0021] The present disclosure provides a system comprising a component, a thermal control system adapted to apply thermal energy to the component, and a controller, wherein the controller is adapted to determine a thermal response in response to the application of thermal energy, determine a thermal property of the component based on a difference between the thermal response and a reference thermal response, and predict an amount of material deposited on a surface of the component based on the thermal property and a predictive analytical model, wherein the thermal response is a rate of dissipation of the thermal energy by the component, the reference thermal response is a reference dissipation rate of the thermal energy of the component in response to the application of the thermal energy, and the predictive analytical model relates the thermal property of the component to an estimated surface condition of the component.

[0022] In one form, the thermal property is the emissivity of the component, the thermal coupling between different regions of the component, the thermal gain of the component, the electrical resistance-temperature relationship of the component, the gas convective coupling of the component, or a combination thereof.

[0023] In one form, the component is selected from the group consisting of a semiconductor processing chamber wall, a semiconductor processing chamber liner, a semiconductor processing chamber showerhead, a semiconductor processing chamber lid, a fluid heating tube wall, a heater surface, and a heater sheath.

[0024] In one form, the thermal control system further comprises a heater adapted to provide the thermal energy to the component.

[0025] In one embodiment, the predictive analytics model is generated during a training routine.

[0026] In one form, the component is a component of a semiconductor processing system.

[0027] Further areas of applicability will become apparent from the description provided herein. It should be understood that the description and specific examples are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure. [Brief explanation of the drawings]

[0028] In order that the present disclosure may be better understood, various aspects thereof will now be described, by way of example, with reference to the accompanying drawings, in which:

[0029] [Figure 1] 1 is an example of a semiconductor processing laboratory in accordance with the teachings of the present disclosure.

[0030] [Figure 2] 1 is a schematic diagram of a semiconductor processing chamber and monitoring system in accordance with the teachings of the present disclosure.

[0031] [Figure 3] FIG. 2 is a functional block diagram of a thermal response determination module in accordance with the teachings of the present disclosure.

[0032] [Figure 4A] 1 is an illustration of a measured thermal response and a reference thermal response of a component in accordance with the teachings of the present disclosure.

[0033] [Figure 4B] 1 is an illustration of measured thermal responses of multiple components and a reference thermal response of a component in accordance with the teachings of the present disclosure.

[0034] [Figure 5] 1 is a flowchart of an example of a training routine performed by a monitoring system in accordance with the teachings of the present disclosure.

[0035] [Figure 6] 1 is a flow chart of an example of a surface condition prediction routine performed by a monitoring system in accordance with the teachings of the present disclosure.

[0036] The drawings described herein are for illustration purposes only and are not intended to limit the scope of the present disclosure in any way. DETAILED DESCRIPTION OF THE INVENTION

[0037] The following description is merely exemplary in nature and is in no way intended to limit the present disclosure, application, or uses. It should be understood that throughout the drawings, corresponding reference numerals indicate like or corresponding parts and features.

[0038] The present disclosure provides a monitoring system adapted to monitor the thermal properties of components, such as emissivity, to predict the surface condition of the components. For example, in a semiconductor processing system, coking on a heater or other component of the semiconductor processing system increases emissivity and decreases convective heat transfer, causing the heater to operate at a higher temperature and with increased energy consumption. The monitoring system of the present disclosure can accurately detect coking on a heater or other component of the semiconductor processing system and alert an operator and / or system controller of the detected condition. The monitoring system also locates material deposits on various components of the semiconductor processing system, thereby enabling an operator and / or system controller to adapt to and / or improve material deposits when implementing control parameters for a semiconductor manufacturing process routine.

[0039] More particularly, in one aspect, a monitoring system applies thermal energy to a component, determines a thermal response of the component in response to the application of the thermal energy, and determines a thermal characteristic of the component based on the reference thermal response and the thermal response. The monitoring system then predicts a surface condition of the component based on the thermal characteristic and a predictive analytical model, where the predictive analytical model associates multiple thermal characteristics of the component with multiple estimated surface conditions of the component.

[0040] 1, in one application, the control system of the present disclosure is provided in a semiconductor processing system 10 that includes at least one chamber 2 having one or more heaters (not shown) disposed therein. Although not shown, one or more control systems are provided to control the heaters. The semiconductor processing system 10 includes other subsystems for processing semiconductor wafers that may affect the thermal response of the heaters. For example, a flow path system including delivery lines 4 and exhaust lines 6 delivers process gases to and from chamber 2.

[0041] 2, the semiconductor processing system 10-1 is further adapted to monitor the surface condition of the components and includes at least one heater 14, a plurality of temperature sensors 16, and a monitoring system 18 for monitoring and predicting the surface condition of the components. In one form, the components can be various system components of the semiconductor processing chamber 22 and / or heating tubes of the semiconductor processing system 10-1. By way of example, the components can be the wall 12-1 of the semiconductor processing chamber 22, the liner 12-2 of the semiconductor processing chamber 22, the showerhead 12-3 of the semiconductor processing chamber 22, the lid 12-4 of the semiconductor processing chamber 22, the wall 12-5 of the fluid heating tube 26, the top layer 12-6 of the wafer support pedestal 20, the surface of the heater 14, and / or the sheath 12-7 of the heater 14 (collectively / individually referred to hereinafter as "components 12").

[0042] In one aspect, the surface condition of component 12 can be an amount of material deposits or vapor depositions on the surface of component 12. In one aspect, the material deposits or vapor depositions affect the emissivity of the surface of component 12 and the heat transfer from the surface of component 12 to the surrounding environment (e.g., a wafer disposed on wafer support pedestal 20). As such, monitoring system 18, as described in more detail below, monitors changes in the thermal properties of the surface of component 12 to thereby predict the state and / or amount of material deposits and vapor depositions on the surface of component 12. In one aspect, the thermal properties include, but are not limited to, the emissivity of component 12, thermal coupling between regions of component 12, thermal gain of component 12, electrical resistance-temperature relationship of component 12, and gas convective coupling of component 12. It should be understood that various other thermal properties may be determined, and the present disclosure is not limited to the example thermal properties described herein.

[0043] In one embodiment, the at least one heater 14 can be integrated into the component 12 or disposed externally to the component 12. In one embodiment, the at least one heater 14 can provide thermal energy to the component 12. As used herein, "providing thermal energy to the component 12" refers to increasing or decreasing the thermal energy provided to a surface of the component 12 and / or an environment proximate (i.e., adjacent and / or nearby) to the component 12. In one example, increasing the thermal energy provided to the component 12 can include heating the surface of the component 12 and / or an environment proximate to the component 12. In another example, decreasing the thermal energy provided to the component 12 can include cooling the surface of the component 12 and / or an environment proximate to the component 12. While the semiconductor processing system 10-1 is shown with at least one heater 14, it should be understood that the heater 14 can be eliminated from the semiconductor processing system 10-1 if thermal energy is provided externally to a fluid (e.g., gas) via a fluid heating conduit 26 to create a plasma within the semiconductor processing chamber 22.

[0044] In one embodiment, multiple temperature sensors 16 may be incorporated within or disposed external to the component 12 to measure the temperature of the surface and / or the ambient environment of the component 12. In one example, the temperature sensors 16 include, but are not limited to, thermocouples, resistance temperature detectors (RTDs), infrared sensors, and / or other conventional temperature-sensing devices. In one embodiment, the temperature sensors 16 are “two-wire” heaters incorporated within the component 12 (e.g., the wafer support pedestal 20). A two-wire heater includes a resistive heating element that functions as both a heater and a temperature sensor, with only two lead wires operably connected to the heating element, rather than four. Such two-wire functionality is disclosed, for example, in commonly assigned U.S. Pat. No. 7,196,295, the disclosure of which is incorporated herein by reference in its entirety. Typically, in a two-wire system, the resistive heating element is defined by a material whose resistance changes with temperature, such that the average temperature of the resistive heating element can be determined based on the change in resistance of the resistive heating element. In one form, the resistance of a resistive heating element is determined by first measuring the voltage across and current through the heating element and then calculating using Ohm's Law. The resistive heating element can be defined by a material with a relatively high temperature coefficient of resistance (TRC), a negative TCR material, or a material with a non-linear TCR.

[0045] In one embodiment, the monitoring system 18 includes a thermal control system 30, a thermal response determination module 32, a characteristic module 34, a surface condition module 36, a predictive analytical model database 38, an alert module 40, a surface condition verification module 42, and a surface condition lookup table database 44. The modules, systems, and / or databases of the monitoring system 18 can be co-located or distributed across different locations (e.g., via one or more edge computing devices) and appropriately communicatively coupled. While the monitoring system 18 is illustrated as part of the semiconductor processing system 10-1, the monitoring system 18 can also be located remotely from the semiconductor processing system 10-1. In one embodiment, the monitoring system 18 and the temperature sensor 16 are communicatively coupled using wired and / or wireless communication protocols (e.g., Bluetooth-based protocols, cellular protocols, Wireless Fidelity (Wi-Fi)-based protocols, Near Field Communication (NFC) protocols, Ultra-Wideband (UWB) protocols, among others).

[0046] In one form, the thermal control system 30 is adapted to control the operation of the heater 14 and / or the flow of fluid supplied to the semiconductor processing chamber 22 through the fluid heating conduit 26. In one example, the thermal control system 30 may include a power supply and one or more power conversion circuits for powering the heater 14 to provide thermal energy to the component 12. Accordingly, to perform the functionality described herein, the thermal control system 30 may include one or more processors adapted to execute instructions stored in a non-transitory computer-readable medium (e.g., random access memory (RAM) and / or read-only memory (ROM)) to control the power conversion circuits and the power supply. As another example, the thermal control system 30 may control a radio frequency (RF) plasma generator (not shown) to increase / decrease the thermal energy provided to the fluid heating conduit 26. In one form, the thermal control system 30 applies thermal energy until a set temperature of the component 12, a set temperature of the ambient environment of the component 12, and / or a set temperature of another component in the semiconductor processing chamber 22 is reached. In one variation, the monitoring system 18 communicates with a thermal control system 30 or its controller that is included in an existing semiconductor processing system.

[0047] In one form, the thermal response determination module 32 is adapted to receive temperature data obtained by the temperature sensor 16 and determine a thermal response of the component 12 in response to the thermal control system 30 applying thermal energy to the component 12. In one form, the thermal response of the component 12 refers to how quickly the component 12 dissipates thermal energy into the surrounding environment after the thermal energy is applied to the component 12. In one example, the thermal response determination module 32 is adapted to determine how quickly the component 12 dissipates thermal energy as a function of temperature change over a predetermined period of time. In some forms, the thermal response can be determined when the temperature of the component 12 equals a predetermined temperature and / or for a predetermined period of time, as described in more detail below. In one form, the thermal response refers to a parameter of the system applying thermal energy (e.g., the voltage, current, electrical resistance, and / or other parameters of the heater 14 when the heater 14 applies thermal energy).

[0048] In one form, as shown in FIG. 3 , the property module 34 is adapted to determine the thermal properties of the part 12 and includes a reference emissivity model database 52, a reference thermal coupling model database 54, a reference heat gain model database 56, a reference RT correlation model database 58, a reference gas convection coupling model database 60, a reference thermal signature database 61, and a thermal property module 62.

[0049] In one form, the reference emissivity model database 52 stores a reference emissivity model for the component 12. In one example, the reference emissivity model may represent the emissivity of the component 12 when there is no material deposit on the surface of the component 12. It should be appreciated that the reference emissivity model database 52 may include additional reference emissivity models that represent the emissivity of the component 12 when a predetermined amount of material deposit is on the surface of the component 12.

[0050] In one form, the reference thermal coupling model database 54 stores a reference thermal coupling model of the component 12. In one example, the reference thermal coupling model may represent the thermal coupling between the component 12 and another component (e.g., the conductivity, transmissibility, and emissivity between two adjacent and / or spaced apart components 12 and / or heaters 14) when there is no material deposit on the surface of the component 12. It should be appreciated that the reference thermal coupling model database 54 may include additional reference thermal coupling models that represent the thermal coupling of the component 12 with different components in the semiconductor processing system 10-1 and / or with different amounts of material deposit on the surface of the component 12.

[0051] In one form, the reference heat gain model database 56 stores a reference heat gain model for the component 12. In one example, the reference heat gain model may indicate the heat gain of the component 12 at a given temperature when there is no material deposit on the surface of the component 12. It should be appreciated that the reference heat gain model database 56 may include additional reference heat gain models that indicate the heat gain of the component 12 at different temperatures and / or with different amounts of material deposit on the surface of the component 12.

[0052] In one form, the reference RT correlation model database 58 stores a reference electrical resistance-temperature correlation model for the component 12. In one example, the reference electrical resistance-temperature correlation model may represent a correlation between the electrical resistance and the temperature of the component 12 when there is no material deposit on the surface of the component 12. It should be understood that the reference RT correlation model database 58 may include additional reference electrical resistance-temperature models that represent an electrical resistance-temperature correlation for the component 12 when a predetermined amount of material deposit is on the surface of the component 12.

[0053] In one form, the reference gas-convection coupling model database 60 stores a reference gas-convection coupling model for the component 12. In one example, the reference gas-convection coupling model may describe the transfer of heat from a fluid (e.g., gas) supplied to the component 12 via the fluid heating tubes 26 and / or plasma when there is no material deposit on the surface of the component 12. It should be appreciated that the reference gas-convection coupling model database 60 may include additional reference gas-convection coupling models that describe the transfer of heat from a fluid (e.g., gas) supplied to the component 12 via the fluid heating tubes 26 and / or plasma when there is a predetermined amount of material deposit on the surface of the component 12.

[0054] In one form, the reference emissivity model, the reference thermal coupling model, the reference thermal coupling model, the reference heat gain model, the reference RT correlation model, and the reference gas convection coupling model (collectively referred to herein as "reference models") are generated during a calibration routine performed by the monitoring system 18 and / or during a machine learning routine performed by the surface condition module 36, as described in more detail below.

[0055] In one form, the reference thermal signature database 61 stores a reference thermal signature of the component 12. In one example, the reference thermal signature is a pictorial representation of the thermal response of varying intensity and / or duration of thermal energy applied to the component 12 when there is no material deposit on the surface of the component 12. It should be understood that the reference thermal signature database 61 can store additional reference thermal signatures of the component 12 corresponding to predetermined amounts of material deposit on the surface of the component 12.

[0056] In one form, the thermal property module 62 is adapted to determine thermal properties of the component 12 based on the difference between the thermal response and one or more reference models. In one form, the thermal property module 62 can compare the thermal response to a reference emissivity model to determine whether the emissivity of the component 12 has changed. In one example, as shown in graph 100 of FIG. 4A , the thermal property module 62 can determine that the emissivity of the component 12 has changed based on the reference emissivity model 102 of the component 12 and the thermal response 104 of the component 12, which explains a lower maximum temperature and a faster rate of temperature decay over a given time.

[0057] 4B , a second component (e.g., heater 14) of semiconductor processing system 10 can be subjected to thermal energy, and temperature sensor 16 can monitor the rate of change of temperature of the second component, shown as thermal response 112. Further, reference emissivity model 116 can correspond to an estimated thermal response of a given component 12 when the second component is subjected to thermal energy. Thus, thermal property module 62 can determine, based on thermal response 114, that the emissivity of component 12 has changed, which explains the higher local maximum temperature over a given period of time.

[0058] As another example, the thermal property module 62 can generate a thermal signature of the component 12 based on the thermal response data and compare the thermal signature to one or more reference thermal signatures to determine whether the emissivity, thermal coupling, etc. of the component 12 has changed. In one form, thermal signatures of shorter energy pulses are associated with features in close proximity to the heating element (e.g., features in conductive contact with the heater sheath), while thermal signatures of longer energy pulses are associated with higher decoupling, such as features that are radiatively heated. It should be appreciated that the thermal property module 62 can also compare the thermal response to any reference model to determine whether there is a corresponding change in the thermal property.

[0059] 2 , the surface condition module 36 is adapted to predict the surface condition of the component 12 based on the thermal properties and the surface condition module 36 is adapted to predict the surface condition based on at least one of the surface condition look-up tables stored in the surface condition look-up table database 44 and the predictive analytics models stored in the predictive analytics model database 38.

[0060] In one form, the surface condition lookup table is a lookup table that associates various thermal properties of the component 12 with various empirically obtained surface conditions of the component 12. Thus, an operator can generate the lookup table by placing various known amounts and / or distribution patterns of material on the component 12 and comparing, for example, the change in emissivity for the known amounts of material to a reference emissivity model. Thus, the surface condition module 36 can reference the surface condition lookup table to identify corresponding changes in thermal properties (e.g., changes in emissivity) and predict the corresponding surface condition of the component 12 (e.g., the amount and / or distribution of material deposits on the surface of the component 12). In some forms, the monitoring system 18 can not include a surface condition lookup table database 44 for storing the surface condition lookup table.

[0061] In one form, the predictive analytical model associates various thermal properties of the component 12 with various estimated surface conditions of the component 12. In one form, the surface condition module 36 may comprise an artificial neural network, a convolutional neural network, and / or other similar machine learning computing system adapted to perform machine learning routines, such as supervised learning routines, unsupervised learning routines, reinforcement learning routines, self-learning routines, and black-box modeling routines, to generate the predictive analytical model. During the machine learning routines, the thermal control system 30 may apply thermal energy to the component 12 in pulses, steps, or ramps, with periodic or aperiodic timing and / or varying amplitudes. Thus, the supervised learning routines may describe the thermal response as a function of unknown model parameters (e.g., applied power, gas flow adjacent to the component 12, gas pressure adjacent to the component 12, and thermal energy in pulses, steps, ramps, periodic or aperiodic timing, and varying amplitudes of pulses of thermal energy).

[0062] In one example, when the surface condition module 36 performs a supervised learning routine, known amounts and / or distributions of material on the surface of the part 12 are used to develop a predictive analytics model that relates the amount / distribution of material and / or other unknown model parameters to changes in thermal properties (e.g., changes in thermal bonding), and the supervised learning routine is run iteratively for different amounts / distributions to improve the accuracy of the predictive analytics model.

[0063] As another example, if the surface condition module 36 performs an unsupervised learning routine (e.g., the surface condition module 36 is an autoencoder neural network performing an unsupervised learning routine), the unknown quantity and / or distribution of material disposed on the part 12 is used to develop a predictive analytics model relating the material quantity / dispersion and / or other unknown model parameters to changes in thermal properties (e.g., changes in emissivity).

[0064] Thus, the predictive analytical model enables the surface condition module 36 to predict the surface condition based on the change in emissivity (or change in other thermal properties) of the component 12. In one example, the surface condition module 36 correlates the determined change in emissivity of the component 12 with the predictive analytical model to predict whether the change in emissivity is “normal” (i.e., a decrease or decrease from an estimated material deposit on the surface of the component 12, resulting in a heat dissipation rate within a predetermined and / or estimated range) or “abnormal” (i.e., an increase or increase from an estimated material deposit on the surface of the component 12, resulting in a heat dissipation rate greater than a predetermined and / or estimated range). It should be understood that the surface condition module 36 may use a variety of other qualitative and / or quantitative characteristics to characterize the component 12 based on the predictive analytical model, including but not limited to the examples described herein.

[0065] In one form, the warning module 40 includes various user interfaces for indicating the presence of material deposits on the surface of the component 12. In one example, the warning module 40 can include various visual interfaces (e.g., a touchscreen, a display monitor, an augmented reality device, and / or a plurality of light emitting diodes (LEDs)), auditory interfaces (e.g., a speaker circuit for audibly outputting a message corresponding to material deposits), and / or tactile interfaces (e.g., a vibration motor circuit that vibrates when material deposits are greater than a threshold value).

[0066] In one embodiment, the surface condition verification module 42 is adapted to verify and / or calibrate the predictive analytical model and / or surface condition lookup table when the warning module 40 outputs a signal indicative of material deposition on the surface of the part 12. In one example, the surface condition verification module 42 includes a visual interface, such as a touchscreen device, that provides an operator with a display and vibration of the predicted material deposition amount / variance. The visual interface of the surface condition verification module 42 may also include one or more operable graphic elements that allow the operator to verify the predictions and / or adjust parameters of the predictive analytical model and / or surface condition lookup table. In some embodiments, the monitoring system 18 may not include a surface condition verification module 42 for monitoring the surface condition of the part 12.

[0067] 5 shows a flowchart illustrating an example training routine 500. At 504, the thermal control system 30 or its operator selects thermal energy parameters (e.g., pulse, amplitude, duration, etc.). Optionally, at 506, when the supervised learning routine is performed, the surface condition module 36 or its operator selects surface condition parameters (e.g., amount and / or distribution of material deposits on the component 12). At 508, the thermal control system 30 applies thermal energy to the component 12, and at 512, the thermal response determination module 32 determines the thermal response of the component 12.

[0068] At 516, the signature module 34 determines whether a reference model associated with the part 12 and / or thermal response is stored in a corresponding database (i.e., one of the reference emissivity model database 52, the reference thermal coupling model database 54, the reference heat gain model database 56, the reference RT correlation model database 58, the reference gas convection coupling model database 60, and the reference thermal signature database 61). If so, the routine 500 proceeds to 520. Otherwise, if the reference model is not stored in a corresponding database, the routine 500 proceeds to 518 where the signature module 34 generates and stores a reference thermal response for the given thermal energy parameters, and then proceeds to 532.

[0069] At 520, the characteristic module 34 determines thermal characteristics of the component 12 based on the thermal response and the reference thermal response, and the surface condition module 36 predicts a corresponding surface condition based on the thermal characteristics and the predictive analytical model. At 524, the surface condition module 36 generates / updates the predictive analytical model based on the thermal characteristics and the associated surface condition. At 528, the surface condition module 36 determines whether additional training is required. If so, the routine 500 proceeds to 532, where the monitoring system 18 receives new thermal energy parameters and / or surface condition parameters, and proceeds to 508. Otherwise, the routine 500 ends.

[0070] 6 shows a flowchart illustrating an example surface condition prediction routine 600 executed by the surface condition module 36. In one example, the surface condition prediction routine 600 can be executed while the semiconductor processing system 10-1 is operating at periodic intervals and / or at various other time intervals. At 604, the thermal control system 30 applies thermal energy to the component 12, and at 608, the thermal response determination module 32 determines a thermal response of the component 12. At 612, the characteristic module 34 determines a thermal characteristic of the component 12 based on the thermal response and a reference thermal response. At 616, the surface condition module 36 predicts a corresponding surface condition based on the thermal characteristic and a predictive analytical model.

[0071] At 620, the monitoring system 18 determines whether the predicted surface condition will activate the alert module 40. If so, the routine 600 proceeds to 624. Otherwise, if the alert module 40 is not activated at 620, the routine 600 ends. At 624, the surface condition verification module 42 determines whether the predicted surface condition corresponds to the actual surface condition of the part 12. If so, the routine 600 proceeds to 632, where the surface condition verification module 42 determines whether the predictive analytical model is accurate. If the predicted surface condition at 624 does not correspond to the actual surface condition of the part 12, the surface condition verification module 42 updates the predictive analytical model at 628.

[0072] It should be understood that the routines 500, 600 are merely exemplary routines and that the monitoring system 18 may perform other routines.

[0073] Although the monitoring system 18 is described herein as predicting the surface condition of the component 12 of the semiconductor processing system 10, it should be understood that the monitoring system 18 may be adapted for use in other environments and is not limited to the semiconductor processing system 10 described herein.

[0074] The disclosed monitoring system detects relative changes in emissivity, thereby generating predictive preventative maintenance solutions based on the detected relative changes in emissivity. Predictive / preventative maintenance can be based on actual changes in various components of the semiconductor processing system, as opposed to an arbitrary preventative maintenance schedule. As such, the monitoring system can reduce maintenance costs and downtime, improving equipment uptime.

[0075] Unless expressly stated otherwise, all numerical values ​​indicating mechanical / thermal properties, compositional proportions, dimensions and / or tolerances, or other characteristics will be understood as being modified by the word "about" or "approximately" when describing the scope of this disclosure. This modification may be desirable for various reasons, including industrial practices, material, manufacturing, and assembly tolerances, and performance testing.

[0076] As used herein, the phrase at least one of A, B, and C should be construed to mean a logical non-exclusive OR (A OR B OR C), and not to mean "at least one of A, at least one of B, and at least one of C."

[0077] The description of the present disclosure is merely exemplary in nature and, thus, variations that do not depart from the gist of the disclosure are intended to be within the scope of the disclosure. Such variations are not to be regarded as a departure from the spirit and scope of the disclosure.

[0078] In the drawings, the direction of the arrows indicated generally indicates the flow of information (data or instructions) that is of interest to the illustration. For example, if element A and element B exchange various information, but the information sent from element A to element B is relevant to the illustration, the arrow will point from element A to element B. This one-way arrow does not imply that other information is not being sent from element B to element A. Also, for information sent from element A to element B, element B can send a request for that information to element A or receive a confirmation of that information.

[0079] As used herein, the term "controller" or "module" may mean an application-specific integrated circuit (ASIC); a digital, analog, or mixed analog / digital discrete circuit; a digital, analog, or mixed analog / digital integrated circuit; a combinatorial logic circuit; a field programmable gate array (FPGA); a processor circuit (shared, dedicated, or group) that executes code; a memory circuit (shared, dedicated, or group) that stores code to be executed by the processor circuit; or other suitable hardware components that provide the described functionality, such as, but not limited to, transfer drivers and systems, transceivers, routers, input / output interface hardware, among others; or a combination of some or all of the above, such as in a system-on-chip.

[0080] The term "memory" is part of the term "computer-readable medium." As used herein, the term "computer-readable medium" does not include transitory electrical or electromagnetic signals propagating through a medium (such as a carrier wave). As such, the term "computer-readable medium" may be considered tangible and non-transient. Non-limiting examples of non-transient, tangible computer-readable media include non-volatile memory circuits (such as flash memory circuits, erasable programmable read-only memory circuits, or masked read-only circuits), volatile memory circuits (such as static random access memory circuits or dynamic random access memory circuits), magnetic storage media (such as analog or digital magnetic tape or hard disk drives), and optical storage media (such as CDs, DVDs, or Blu-ray discs).

[0081] The apparatus and methods described herein can be implemented partially or completely by a special-purpose computer created by configuring a general-purpose computer to perform one or more specific functions embodied in a computer program. The functional blocks, flowchart elements, and other elements described above function as software specifications and can be translated into a computer program by the routine work of a skilled engineer or programmer.

Claims

1. providing thermal energy to the component; determining a thermal response of the component in response to applying the thermal energy; determining a thermal characteristic of the component based on a reference thermal response and the thermal response; predicting a surface condition of the component based on the thermal characteristics and a predictive analytical model; Including, the predictive analytics model relates the thermal properties of the part to an estimated surface condition of the part; The method, wherein the surface condition indicates an amount of material deposit on a surface of the component.

2. The method of claim 1 , wherein the thermal characteristic is based on a difference between the reference thermal response and the thermal response.

3. 2. The method of claim 1, wherein the thermal property is an emissivity of the component, a thermal coupling between different regions of the component, a thermal gain of the component, an electrical resistance-temperature relationship of the component, a gas convective coupling of the component, or a combination thereof.

4. The method of claim 1 , wherein applying thermal energy to the component further comprises increasing the thermal energy applied to the component.

5. The method of claim 1 , wherein applying thermal energy to the component further comprises reducing the thermal energy applied to the component.

6. The method of claim 1 , wherein the thermal response is the rate at which thermal energy is dissipated by the component.

7. The method of claim 1 , further comprising varying at least one of an intensity and duration of the thermal energy to generate a thermal signature of the component, the thermal signature being a pictorial representation of the thermal response.

8. The method of claim 7 , further comprising determining the thermal property of the component based on a reference thermal signature and the thermal signature.

9. 10. The method of claim 1, wherein the component is selected from the group consisting of a wall of a semiconductor processing chamber, a liner of the semiconductor processing chamber, a showerhead of the semiconductor processing chamber, a lid of the semiconductor processing chamber, a wall of a fluid heating tube, a surface of a heater, and a sheath of a heater.

10. The method of claim 1 further comprising measuring the temperature of the component for a predetermined period of time to determine the thermal response.

11. The method of claim 10 , further comprising determining energy dissipation by the component based on the change in temperature of the component over the predetermined time period.

12. The method of claim 11 , further comprising determining a change in emissivity of the component based on the change in temperature of the component over the predetermined time period.

13. The method of claim 1 , wherein the thermal response of the component is determined as a function of the temperature of the component being equal to a predetermined temperature.

14. Parts and a thermal control system adapted to provide thermal energy to the component; a control unit, The control unit determining a thermal response in response to the application of thermal energy; determining a thermal characteristic of the component based on a difference between a reference thermal response and the thermal response; predicting an amount of material deposit on a surface of the component based on the thermal characteristics and a predictive analytical model; the thermal response is a rate at which the thermal energy is dissipated by the part, the reference thermal response is a reference rate at which the thermal energy is dissipated by the part in response to applying the thermal energy, and the predictive analytical model relates the thermal properties of the part to an estimated surface condition of the part.

15. 15. The system of claim 14, wherein the thermal property is an emissivity of the component, a thermal coupling between different regions of the component, a thermal gain of the component, an electrical resistance-temperature relationship of the component, a gas convective coupling of the component, or a combination thereof.

16. 15. The system of claim 14, wherein the component is selected from the group consisting of a wall of a semiconductor processing chamber, a liner of the semiconductor processing chamber, a showerhead of the semiconductor processing chamber, a lid of the semiconductor processing chamber, a wall of a fluid heating tube, a surface of a heater, and a sheath of a heater.

17. The system of claim 14 , wherein the thermal control system further comprises a heater adapted to provide the thermal energy to the component.

18. The system of claim 14 , wherein the predictive analytics model is generated during a training routine.

19. The system of claim 14 , wherein the component is a component of a semiconductor processing system.

Images