Virtual sensors for predicting and monitoring the temperature of chamber components

Abstract

A method and apparatus for substantially sensing the temperature of hardware components of a semiconductor processing chamber are disclosed. In one or more embodiments, a method for operating a processing chamber suitable for use in semiconductor manufacturing includes receiving a process recipe for a manufacturing process and monitoring a first temperature of a first hardware component of the processing chamber using a sensor. The method further includes using a model of the processing chamber to synthesize a first virtual temperature of a second hardware component of the processing chamber based on the received process recipe and the first temperature of the first hardware component.

Description

Technical Field

[0001]

[0001] Embodiments of the present disclosure generally relate to substantially sensing, predicting, and / or monitoring the temperature of hardware components such as an upper plate within a deposition chamber. The deposition can be an epitaxial deposition chamber useful in semiconductor manufacturing.

Background Art

[0002]

[0002] Improved process control leads to improved yield and quality during semiconductor manufacturing. To better control process results, it is useful to control the temperature of chamber hardware components such as an upper plate located within the chamber, as the hardware can radiate thermal energy to the substrate and affect the process results.

[0003]

[0003] However, it is difficult to accurately measure the temperatures of various hardware components. Measuring the temperatures of various hardware components is difficult due to hardware constraints such as the location of the hardware or the material of which the hardware is composed. As an example, using similar materials can pose challenges when measuring the temperature of a particular component using an infrared pyrometer. Adjusting the material composition of a particular component can complicate the calibration of the pyrometer, can complicate the design of the pyrometer, and can increase the overall cost of the pyrometer and the deposition chamber.

[0004]

[0004] Therefore, there is a need for improved systems and methods for determining hardware temperatures such as upper plate temperature.

Summary of the Invention

[0005]

[0005] Embodiments of the present disclosure generally relate to substantially sensing, predicting, and / or monitoring the temperature of hardware components such as a separated (e.g., upper) plate within a deposition chamber such as an epitaxial deposition chamber useful in semiconductor manufacturing.

[0006]

[0006] In one or more embodiments, a method for operating a processing chamber suitable for use in semiconductor manufacturing includes receiving a process recipe for a manufacturing process and monitoring a first temperature of a first hardware component of the processing chamber using a sensor. The method further includes using a model of the processing chamber to synthesize a first virtual temperature of a second hardware component of the processing chamber based on the received process recipe and the first temperature of the first hardware component.

[0007]

[0007] In one or more embodiments, a method for operating a processing chamber suitable for use in semiconductor manufacturing includes receiving a processing recipe for a deposition process in the processing chamber and using a virtual model based on the received processing recipe to synthesize a virtual temperature of an upper plate or substrate support and a virtual temperature of a separation plate. The method further includes determining whether a first difference between one or more temperature measurements of the upper plate or substrate support and the synthesized virtual temperature of the upper plate or substrate support is within a threshold. The method further includes adjusting the virtual model in response to the first difference being outside the threshold until the first difference is within the threshold, and adjusting the virtual model includes adjusting the virtual temperature of the separation plate.

[0008]

[0008] In one or more embodiments, the non-temporary computer-readable medium includes instructions, which, when executed by the system's processor, cause the system to receive a process recipe for a manufacturing process, to monitor a first temperature of a first hardware component of a processing chamber using sensors, and to synthesize a first virtual temperature of a second hardware component of a processing chamber based on the received process recipe and the first temperature of the first hardware component, using a model of the processing chamber.

[0009]

[0009] To allow for a more detailed understanding of the features of the Disclosure outlined above, a more specific description of the Disclosure can be obtained by referring to embodiments, some of which are shown in the accompanying drawings. However, it should be noted that the accompanying drawings show only exemplary embodiments and should not be considered limiting in scope, as the Disclosure may also permit other equally valid embodiments. [Brief explanation of the drawing]

[0010] [Figure 1] This is a schematic side cross-sectional view of a processing chamber according to one or more embodiments. [Figure 2] Methods related to temperature control during processing, according to one or more embodiments, are shown. [Figure 3] The following describes exemplary operations relating to temperature control during processing according to one or more embodiments. [Figure 4] A method for operating a processing chamber according to one or more embodiments of this disclosure is shown. [Figure 5] This document describes an exemplary processing system for training and / or utilizing machine learning models to determine the temperature of hardware components used in semiconductor manufacturing. [Modes for carrying out the invention]

[0011]

[0015] To facilitate understanding, the same reference numerals were used where possible to indicate identical elements common to multiple figures. It is assumed that elements and features of one embodiment may be usefully incorporated into other embodiments without further description.

[0012]

[0016] This disclosure relates to a system, apparatus, and method for monitoring hardware temperature for semiconductor manufacturing.

[0013]

[0017] Embodiments of this disclosure relate to real-time estimation (e.g., "virtual sensing") of hardware temperature within a semiconductor processing system. For example, using a virtual model that includes or utilizes system modeling algorithms and the geometric dimensions of a processing chamber, the temperature of hardware components, such as hardware that is difficult to measure directly during semiconductor processing, can be predicted or estimated. Using measurements captured during past and / or current process executions, the temperature of hardware components can be estimated, and / or parameters can be synthesized to achieve a given hardware component temperature. Machine learning algorithms (MLAs) can be incorporated to update the virtual model and improve accuracy. MLAs can utilize physical-based models, database models, or a combination of physical-based and database models.

[0014]

[0018] Methods for system modeling using system modeling algorithms can utilize one or a combination of finite element modeling, finite space modeling, finite difference modeling, fluid dynamics modeling (e.g., Navier-Stokes equations), process parameters, physical constraints (e.g., conservation of mass / energy equations), material quality and dimensions, empirical data, and other factors for the behavior of the processing system and environment. The model can solve governing equations related to the processing chamber, such as fluid dynamics equations, energy equations, heat equations, and electric / magnetic field equations. The model can also solve estimates of temperature, thermal gradient, fluid flow, charge, and magnetic field strength at various points within the processing system. The estimated equations and / or values ​​from the system model facilitate the determination of specific operating modes of the processing system. However, conventional models are difficult to utilize in the processing system during processing due to real-time changes in the processing system. Therefore, conventional models have inaccurate results. The disclosed embodiments address these challenges by 1) updating the model using machine learning algorithms, or 2) utilizing real-time processing data. In one non-limiting example, aspects of the present disclosure provide an estimation of the temperature of a separation plate in an epitaxial processing chamber. Appropriate mathematical techniques such as orthogonal decomposition, equilibrium methods, and reduced basis methods can be used to reduce the order of the model and accelerate execution time.

[0015]

[0019] A neural network (e.g., an MLA as described herein) generally uses multiple inputs, such as from different sensors, to produce one or more outputs. Inputs can be made at the same time as or at different times as the outputs. Outputs can be simulated. Each input (e.g., p_1, p_2, ..., p_R) corresponds to the corresponding element (e.g., w) of the weight matrix W. 1,1 ,w 1,2 ,…,w 1,RThe inputs are weighted by a.b. Each neuron has a bias b, which is added to the weighted input to form the net input n = Wp + b. The net input n is then applied to the transfer function f. The transfer function may be a linear or nonlinear function of n. A particular transfer function is selected based on the problem to be solved. Typical transfer functions are linear functions, hard limit functions, hyperbolic tangent sigmoid functions (tansig), log sigmoid functions (logsig), or race functions. The output of neuron a can be defined as a = f(Wp + b).

[0016]

[0020] A single-layer network of S neurons can operate on an input vector p and produce an output a, but combinations of layers create multilayer neural networks. The layer whose output is the network output is the output layer. The other layers are called hidden layers. After the architecture is defined, the next step is to train the multilayer neural network. A preferred training method is called backpropagation, which is a generalization of the Least Mean Squared Error (LMS) algorithm. Backpropagation is an approximate steep gradient descent algorithm whose performance index is the mean squared error. The general operation of inverse proportion is to propagate the input to the network first, then compute the sensitivity backward through the network, and use this sensitivity to update the weights and biases using the steep gradient law. This process is repeated until the objective function is minimized or several iterations are performed.

[0017]

[0021] In this solution, the input may include one or more physical properties (such as temperature) of one or more processing chamber components (e.g., temperature measurements of hardware components), one or more chemical properties of one or more processing chamber components, one or more processing recipe parameters, and / or measurements of one or more stimuli. The output may include the temperature of processing chamber components such as the upper plate. In one or more embodiments, the target top plate temperature can be used as input and the processing recipe parameters can be output.

[0018]

[0022] As described herein, the program may use both the MLA and one or more virtual models to determine the program's output. The MLA and / or virtual models within the program utilize measured processing parameters to generate virtual or composite temperatures of processing chamber components that are difficult or impossible to measure directly. In other words, a combination of measurements and system modeling can be used to estimate the “virtual” temperature of components that are not measured (or are unmeasurable). Measured values ​​of one or more input data parameters (e.g., actual temperature measurements of hardware, gas flow, pressure, etc.) and one or more output data parameters (e.g., temperature) may be used to train the program. The virtual models may include virtual replicas or digital twins of the processing system. Training may be performed in a test run environment, but the actual hardware is intended for use in a commercial manufacturing environment. Training the MLA improves the accuracy of the results. Accuracy is particularly improved in response to changes in conditions within the processing system. For example, processing of substrates such as semiconductor substrates within the system leads to degradation of hardware components. Degraded components include lamps that may have reduced output or plates that may have reduced transparency. These degradations affect the simulation accuracy for the physical processing chamber. However, aspects of this disclosure provide real-time updates of programs and / or models through simulation verification and use of MLA. These real-time updates resulted in improved performance.

[0019]

[0023] Figure 1 is a schematic side cross-sectional view of a processing chamber 100 according to one or more embodiments. The processing chamber 100 is a deposition chamber. In one or more embodiments, the processing chamber 100 is an epitaxial deposition chamber. The processing chamber 100 is used to grow an epitaxial film on a substrate 102. The processing chamber 100 generates a crossflow of precursor across the upper surface 150 of the substrate 102. The processing chamber 100 is shown under the processing conditions in Figure 1.

[0020]

[0024] The processing chamber 100 includes an upper body 156, a lower body 148 positioned below the upper body 156, and a flow module 112 positioned between the upper body 156 and the lower body 148. The upper body 156, the flow module 112, and the lower body 148 form the chamber body. Inside the chamber body are a substrate support 106, an upper plate 108 (e.g., an upper window such as an upper dome), a lower plate 110 (e.g., a lower window such as a lower dome), a plurality of upper heat sources 141, and a plurality of lower heat sources 143. In one or more embodiments, the upper heat sources 141 include upper lamps, and the lower heat sources 143 include lower lamps. This disclosure intends that other heat sources may be used for the various heat sources described herein (in addition to or instead of lamps). For example, resistance heaters, light-emitting diodes (LEDs), and / or lasers may be used for the various heat sources described herein.

[0021]

[0025] The substrate support 106 is disposed between the upper plate 108 and the lower plate 110. The substrate support 106 supports the substrate 102. In one or more embodiments, the substrate support 106 includes a susceptor. Other substrate supports (e.g., substrate carriers and / or one or more ring segments that support one or more outer regions of the substrate 102) are contemplated by the present disclosure. A plurality of upper heat sources 141 are disposed between the upper plate 108 and the lid 154. The plurality of upper heat sources 141 form part of the upper heat source module 155. The lid 154 includes a plurality of sensor devices 196, 197, 198 disposed therein or thereon. Each of the sensor devices 196, 197, 198 may be configured to measure one or more temperatures within the processing chamber 100. The lower sensor device 195 is configured to measure one or more temperatures within the processing chamber 100. In one or more embodiments, each of the sensor devices 195, 196, 197, 198 is a pyrometer. Each of the sensor devices 195, 196, 197, 198 may be an optical sensor device such as a pyrometer. The present disclosure contemplates that sensors other than pyrometers may be used. Each of the sensor devices 195, 196, 197, 198 is a single wavelength sensor device or a multi-wavelength (such as dual wavelength) sensor device. The lower sensor device 195 is disposed adjacent to the floor 152 disposed within the lower body 148.

[0022]

[0026] It is contemplated that the processing chamber 100 may include any one, any two, or any three of the four illustrated sensor devices 195, 196, 197, 198. It is also contemplated that the processing chamber 100 may include one or more additional sensor devices in addition to the sensor devices 195, 196, 197, 198. The processing chamber 100 may include sensor devices disposed at different positions and / or in different orientations than the illustrated sensor devices 195, 196, 197, 198.

[0023]

[0027] The plurality of lower heat sources 143 are disposed between the lower plate 110 and the floor 152. The plurality of lower heat sources 143 form part of the lower heat source module 145. The upper plate 108 is an upper dome and / or is formed of a substantially transmissive material such as an energy transmissive material or a radiation transmissive material (such as quartz). The lower plate 110 is a lower dome and / or is also formed of an energy transmissive material such as quartz.

[0024]

[0028] An upper space 136 and a purge space 138 are formed between the upper plate 108 and the lower plate 110. The upper space 136 and the purge space 138 are part of an internal space that is at least partially defined by the upper plate 108, the lower plate 110, and one or more liners 111, 163.

[0025]

[0029] A substrate support 106 is disposed in the internal space. The substrate support 106 includes an upper surface, and a substrate 102 is disposed on the upper surface. The substrate support 106 is attached to a shaft 118. In one or more embodiments, the substrate support 106 is connected to the shaft 118 via one or more arms 119 connected to the shaft 118. The shaft 118 is connected to a motion assembly 121. The motion assembly 121 includes 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 upper space 136.

[0026]

[0030] The substrate support 106 optionally includes lift pin holes 107 disposed therein. Each of the lift pin holes 107 is sized to accommodate a lift pin 132 for lifting the substrate 102 from the substrate support 106 before or after the deposition process is performed. The lift pin 132 can be placed on a lift pin stop 134 when the substrate support 106 descends from the processing position to the transfer position. The lift pin stop 134 can include a plurality of arms 139 attached to a second shaft 135 disposed around the shaft 118.

[0027]

[0031] The flow module 112 includes one or more gas inlets 114 (e.g., multiple gas inlets), one or more purge gas inlets 164 (e.g., multiple purge gas inlets), and one or more gas exhaust ports 116. The one or more gas inlets 114 and the one or more purge gas inlets 164 are located on the opposite side of the flow module 112 from the one or more gas exhaust ports 116. A preheating ring 117 is located below the one or more gas inlets 114 and the one or more gas exhaust ports 116. The preheating ring 117 is located above the one or more purge gas inlets 164. One or more liners 111, 163 are located on the inner surface of the flow module 112 to protect the flow module 112 from reactive gases used during deposition and / or cleaning operations. One or more gas inlets 114 and one or more purge gas inlets 164 are arranged to allow one or more processing gases P1 and one or more purge gases P2 to flow parallel to the upper surface 150 of the substrate 102 located in the upper space 136. One or more gas inlets 114 are fluidly connected to one or more processing gas sources 151 and one or more cleaning gas sources 153. One or more purge gas inlets 164 are fluidly connected to one or more purge gas sources 162. One or more gas exhaust ports 116 are fluidly connected to an exhaust pump 157. One or more process gases P1 supplied using one or more process gas sources 151 may contain one or more reactive gases (one or more of silicon (Si), phosphorus (P), and / or germanium (Ge)) and / or one or more carrier gases (one or more of nitrogen (N2) and / or hydrogen (H2)). One or more purge gases P2 supplied using one or more purge gas sources 162 may contain one or more inert gases (such as one or more of argon (Ar), helium (He), and / or nitrogen (N2)). One or more scrubbing gases supplied using one or more scrubbing gas sources 153 may contain one or more of hydrogen (H) and / or chlorine (Cl).In one or more embodiments, one or more processing gases P1 include silicon phosphide (SiP) and / or phosphorus (PH3), and one or more washing gases include hydrochloric acid (HCl).

[0028]

[0032] One or more gas exhaust ports 116 are further connected to or include an exhaust system 178. The exhaust system 178 fluidly connects one or more gas exhaust ports 116 to an exhaust pump 157. The exhaust system 178 can assist in the controlled deposition of layers onto the substrate 102. The exhaust system 178 is located on the opposite side of the processing chamber 100 from the flow module 112.

[0029]

[0033] A plate 171 (also called a top plate or separation plate) having a first surface 172 and a second surface 173 opposite the first surface 172 is positioned between the upper plate 108 and the substrate support 106. In one or more embodiments, the plate 171 is formed from quartz. In one or more embodiments, the plate 171 is part of a flow guide structure. The second surface 173 faces the substrate support 106. The processing chamber 100 includes one or more liners 111, 163. The upper liner 163 includes an annular section 181 and one or more ledges 182 extending inward relative to the annular section 181. One or more ledges 182 are configured to support one or more outer regions of the second surface 173 of the plate 171. The upper liner 163 includes one or more inlet openings 183 and one or more outlet openings 185. In one or more embodiments, the plate 171 is disk-shaped, and the annular section 181 is ring-shaped. The plate 171 may also be rectangular in shape. The plate 171 divides the upper space 136 between the substrate support 106 and the upper plate 108 into a lower section 136a and an upper section 136b. The lower section 136a is the processing section. In one or more embodiments, the plate 171 is a separation plate that fluidly separates the upper section 136b from the lower section 136a at least partially (partially or completely equally).

[0030]

[0034] Because plate 171 is located relatively close to the substrate 102 during processing, plate 171 affects the temperature of the substrate 102. Plate 171 may also affect the temperature of the gaseous precursor flowing through the substrate 102. Therefore, the activation or depletion of the gaseous precursor is also affected. The temperature of the gaseous precursor also affects the growth rate on the substrate 102, the selectivity of epitaxial growth on the substrate 102, the dopant density, or the film quality. Therefore, controlling the temperature of plate 171 within a given operating plate promotes improvements in processing uniformity, such as deposition uniformity. To control the temperature of plate 171 within the operating plate, it is helpful to first determine the temperature of plate 171. However, because plate 171, the upper plate 108, and the lower plate are each made of quartz, sensors 195-198 may not be able to determine the temperature of plate 171. However, aspects of the present disclosure improve the processing by virtually sensing the temperature of plate 171.

[0031]

[0035] The flow module 112 (which may be at least part of the side wall of the processing chamber 100) includes one or more gas inlets 114 that are in fluid communication with the lower part 136a. The flow module 112 includes one or more second gas inlets 175 that are in fluid communication with the upper part 136b. One or more gas inlets 114 are in fluid communication with one or more flow gaps between the upper liner 163 and the lower liner 111. One or more second gas inlets 175 are in fluid communication with one or more inlet openings 183 of the upper liner 163.

[0032]

[0036] During a deposition operation (e.g., an epitaxial growth operation), one or more process gases P1 flow into the lower section 136a through one or more gas inlets 114 and through one or more gaps, and flow over the substrate 102. During the deposition operation, one or more purge gases P2 flow into the upper section 136b through one or more second gas inlets 175 and through one or more inlet openings 183 of the lower liner 111. One or more purge gases P2 flow simultaneously with the flow of one or more process gases P1. By flowing one or more purge gases P2 through the upper section 136b, it becomes easier to reduce or prevent the flow of one or more process gases P1 into the upper section 136b, which could contaminate the upper section 136b. One or more process gases P1 are exhausted through one or more gas exhaust ports 116 through the gap between the upper liner 163 and the lower liner 111. One or more purge gases P2 are exhausted through one or more outlet openings 185, through the same gap between the upper liner 163 and the lower liner 111, and through the same one or more gas exhaust ports 116 as the one or more processing gases P1. The present disclosure envisions that one or more purge gases P2 may be exhausted separately through one or more second gas exhaust ports separated from the one or more gas exhaust ports 116.

[0033]

[0037] The disclosure also intends that during the loading operation, one or more purge gases P2 may be supplied to the purge space 138 (through one or more purge gas inlets 164) and discharged from the purge space 138.

[0034]

[0038] During the cleaning operation, one or more cleaning gases flow into the lower section 136a through one or more gas inlets 114 and through one or more gaps (between the upper liner 163 and the lower liner 111). During the cleaning operation, one or more cleaning gases also simultaneously flow into the upper section 136b through one or more second gas inlets 175 and through one or more inlet openings 183 of the upper liner 163. The disclosure intends that one or more cleaning gases used to clean surfaces adjacent to the upper section 136b may be the same as or different from one or more cleaning gases used to clean surfaces adjacent to the lower section 136a.

[0035]

[0039] The processing chamber 100 facilitates the separation of the gas supplied to the upper part 136b from the gas supplied to the lower part 136a, and facilitates parameter adjustment. Furthermore, one or more purge gases and one or more washing gases can be supplied separately to the upper part 136b to facilitate the reduction of contamination of the upper plate 108 and / or plate 171.

[0036]

[0040] As shown in the figure, the controller 190 communicates with the processing chamber 100 and is used to control processes and methods, such as the operation of the method described herein.

[0037]

[0041] The controller 190 is configured to receive data or inputs as sensor readings from a plurality of sensors. The sensors may include, for example, sensors for monitoring the growth of one or more layers on the substrate 102, sensors for monitoring the growth or residue on the inner surfaces of the chamber components of the processing chamber 100 (e.g., the inner surfaces of the plate 171 and / or one or more liners 111, 163), and / or sensors for monitoring the temperature of the substrate 102, substrate support 106, plate 171, and / or liners 111, 163. The controller 190 has or communicates with a system model of the processing chamber 100. The system model is a program or a set of algorithms configured to estimate parameters within the processing chamber 100 (e.g., gas flow rate, gas pressure, processing temperature, rotational position of components, heating profile, coating conditions, and / or cleaning conditions). The system model estimates parameters throughout the deposition and / or cleaning operations. The controller 190 is further configured to store read, calculated, and user input data. The readings and calculations include previous sensor readings, such as any previous sensor readings within the processing chamber 100. The readings and calculations further include stored calculated values ​​after the sensor readings have been measured by the controller 190 and run through the system model. Thus, the controller 190 is configured to retrieve both the stored readings and calculated values, and to save them for future use. By maintaining previous readings and calculations, the controller 190 can adjust the system model over time to reflect a more accurate version of the processing chamber 100. In this way, the controller's configuration or the application run by the controller functions as an operational improvement engine.

[0038]

[0042] The controller 190 facilitates monitoring of system conditions, estimates parameters, controls processing operation or recipe parameters, generates warnings on the display, stops the deposition operation, initiates a chamber downtime period, delays subsequent iterations of the deposition operation, starts a cleaning operation, stops the cleaning operation, adjusts heating power, and / or adjusts the process recipe in other ways.

[0039]

[0043] The controller 190 may be for a specific processing chamber, a set of processing chambers, or an entire semiconductor processing tool. The controller 190 is configured to run a program that includes both the MLA and a virtual model of the processing chamber. The virtual model may be a digital twin or a virtual sensor model. The program and virtual model may be run to estimate and edit the processes of a processing chamber, a single processing chamber, a semiconductor processing tool, or a sub-part of a semiconductor manufacturing facility. The program may run on a controller at any level of the semiconductor manufacturing facility, or it may run on the cloud or metaverse.

[0040]

[0044] The controller 190 includes a central processing unit (CPU) 193 (e.g., a processor), a memory 191 containing instructions, and support circuitry 192 for the CPU 193. The controller 190 controls various items directly or via other computers and / or controllers. In one or more embodiments, the controller 190 is communicably connected to a dedicated controller, and the controller 190 functions as a central controller.

[0041]

[0045] The controller 190 is any form of general-purpose computer processor used in an industrial environment to control various substrate processing chambers and devices, as well as subprocessors on or within them. The memory 191, or non-transient computer-readable medium, is one or more readily available memory (e.g., random access memory (RAM), dynamic random access memory (DRAM), static RAM (SRAM), and synchronous dynamic RAM (SDRAM (e.g., DDR1, DDR2, DDR3, DDR3L, LPDDR3, DDR4, LPDDR4, etc.)), read-only memory (ROM), floppy disks, hard disks, flash drives, or any other form of local or remote digital storage. The support circuit 192 of the controller 190 is connected to the CPU 193 to support the CPU 193. The support circuitry 192 includes a cache, power supply, clock circuitry, input / output circuits, and subsystems, etc. Operating parameters, simulations, and machine learning algorithms are stored in memory 191 as software routines that are executed or invoked to transform controller 190 into a purpose-specific controller that controls the operation of the various chambers / modules described herein. Controller 190 is configured to perform any of the methods described herein. While embodiments herein describe specific embodiments stored locally in memory 191, it is assumed that one or more embodiments may be stored remotely and accessed via a data connection.

[0042]

[0046] In one or more embodiments, which can be combined with other embodiments, the controller 190 includes a mass storage device, an input control unit, and a display unit. The controller 190 monitors the temperature of the substrate 102, the temperature of the substrate support 106, the temperature of the plate 171, the processing gas flow, and / or the purge gas flow. In one or more embodiments, the controller 190 includes multiple controllers 190, thereby storing the stored reads and calculations and system models in a controller separate from the controller 190 that controls the operation of the processing chamber 100. In one or more embodiments, the system model and all stored reads and calculations are stored within the controller 190.

[0043]

[0047] Controller 190 is configured to control sensor devices 195, 196, 197, 198, deposition, cleaning, rotational position, heating, gas flow through the processing chamber 100, and other operations by providing commands or control signals to various components of the system. Controller 190 is configured to adjust outputs to the controller based on sensor readings, system models, and stored readings and calculated values, all of which may interact with or be updated by the MLA or other software applications. The MLA may implement, adjust, and / or improve one or more algorithms, inputs, outputs, or variables described herein. Additionally or alternatively, the MLA may rank or prioritize specific aspects of adjustments to the processing chamber 100 or the methods described herein. The MLA may consider other changes in the processing system, such as hardware replacement and / or degradation. In one or more embodiments, the MLA describes upstream or downstream changes that may occur in the processing system due to variable changes in the processing chamber 100. For example, if variable "A" is adjusted to cause a change in process mode "B", and such adjustment unintentionally causes a change in process mode "C", the MLA can take such a change in mode "C" into account. In such embodiments, one or more machine learning algorithms and / or artificial intelligence algorithms embody predictive modes related to the implementation of the processing chamber 100.

[0044]

[0048] In one or more embodiments, the controller 190 automatically performs the operations described herein without using one or more machine learning algorithms or artificial intelligence algorithms. In one or more embodiments, the controller 190 compares measured values ​​(such as increased and / or decreased readings) with data in a lookup table and / or library to determine whether coating conditions and / or cleaning conditions have been detected. The controller 190 may store the measured values ​​as data in the lookup table and / or library.

[0045]

[0049] Figure 2 shows a method 200 relating to real-time estimation of the hardware temperature of a processing chamber according to one or more embodiments. Method 200 can be performed by one or more programs using, for example, MLA, virtual models, or other applications as described herein. Method 200 can be implemented using one or more computing systems, for example, one or more processors, and a non-temporary computer-readable medium containing instructions for performing the techniques described herein.

[0046]

[0050] Method 200 begins with operation 210, in which real-time processing parameter measurements are received from the processing chamber (e.g., sensors 195-198 from processing chamber 100). The measurements may include, for example, the temperature of the upper plate 108, the temperature of the lower plate 110, the temperature of the substrate support 106, or the temperature of the substrate 102. The measured parameters may not include the temperature of plate 171 because they are provided by a virtual model.

[0047]

[0051] In operation 220, the measured values ​​are provided to a virtual model of the processing chamber.

[0048]

[0052] In operation 230, the synthesized parameters are received as output from the virtual model. For example, the virtual model may synthesize the temperature of plate 171 by considering historical data and / or training data. At least some of the synthesized parameters are different from the measured parameters. For example, the virtual model may synthesize the upper plate temperature based on the temperature measured in the processing chamber 100, as well as one or more known or estimated operating characteristics such as temperature, pressure, and flow rate.

[0049]

[0053] Training data and virtual models can initially be established empirically. For example, correlations between sensor measurements (such as measurements from sensors 195-198) can be determined to enable the synthesis of temperatures for plate 171. These correlations are not determined during substrate processing, but the model can be generated by other means. For example, a pyrometer can be placed in the processing system in a position that allows measurement of plate 171 while avoiding interference from the upper plate 108 or plate 110. Such a configuration may negatively affect the uniformity of deposition, but is sufficient to establish baseline relationships when using test substrates in non-commercial manufacturing environments. Additionally or alternatively, it is thought that baseline relationships of the algorithms and models herein can be established using aspects of U.S. Patent Application No. 18 / 132,861, filed April 10, 2023 (incorporated herein by reference).

[0050]

[0054] In operation 240, processing parameter adjustments are determined in real time based on the synthesized parameters. For example, processing recipe conditions are adjusted to achieve the target temperature of plate 171, thereby improving the uniformity of deposition. Adjustable processing recipe conditions include, but are not limited to, gas flow rate, gas composition, heater output (e.g., lamp output), substrate support position, exhaust flow rate, and top plate blower motor output.

[0051]

[0055] In operation 250, an instruction including the adjusted processing parameters is provided to the processing chamber 100. In one or more embodiments, according to method 200, real-time measurements are performed continuously and real-time adjustments are performed continuously.

[0052]

[0056] Figure 3 shows exemplary operations related to temperature control during processing according to one or more embodiments. Operation 300 includes inputting a process recipe for a deposition or washing process to be performed in the processing chamber 100 in sub-operation 310. The processing recipe includes variables such as substrate position, heater output (e.g., lamp output), pressure, temperature, gas flow rate, and gas composition.

[0053]

[0057] The processing recipe is input to a virtual model of the processing chamber 100 in sub-operation 320. The processing chamber 100 may be a deposition chamber such as an epitaxial deposition chamber. Accordingly, the algorithm of the virtual model synthesizes (or estimates) predetermined output values ​​corresponding to the state of the processing chamber 100. For example, the output may include one or more of the following: the temperature of the upper plate (e.g., the separation plate), the temperature of the upper plate, the temperature of the lower plate, and the temperature of the substrate support.

[0054]

[0058] In sub-operation 330, at least some outputs from sub-operation 320 are compared with measured sensor data from a physical processing chamber corresponding to the virtual model. The measured sensor data is verified during sub-operation 315. Sub-operation 315 may be performed before, after, or concurrently with the provision of substantially modeled data from sub-operation 320. For example, the temperature of the upper plate, the temperature of the lower plate, and / or the temperature of the substrate support are measured by sensors in the physical processing chamber and compared with the output of the virtual model. This comparison allows for verification of the accuracy of the virtual model. The comparison of composite values ​​from the virtual model with actual measured data from the physical model provides an indirect means of verifying that the remaining data output by the virtual model is accurate. In particular, the temperature of the top plate (which may not be directly measured during processing) can be estimated to be accurate if the temperatures of other components adjacent to the top plate are accurate.

[0055]

[0059] If the comparison in sub-operation 330 results in a difference less than a threshold, i.e., the virtual is within a predetermined accuracy tolerance, operation 300 proceeds to sub-operation 340. The threshold can be a predetermined threshold. The threshold can be a threshold. The predetermined threshold can be selected, for example, by the user and / or the controller described herein. For example, the user and / or the virtual model described herein can select and / or update the predetermined threshold. In sub-operation 340, data indicating the temperature of the top plate is output to the controller or memory and / or the data is output to the user or operator, for example, on a display screen. The data can be plotted in the controller or memory and / or the data can be plotted on a display screen. The output may include the average top plate temperature, a top plate temperature profile, or a top plate temperature range. The output may be specific to a particular time during substrate processing or cleaning operations. For example, the output can be selected by the operator to correspond to preheating, cleaning, deposition, or a specific process (e.g., two minutes during the execution of the process). It is assumed that the output can be generated at various operator-selected intervals, including before, after, or during substrate deposition.

[0056]

[0060] Returning to sub-operation 330, if the difference between one or more measured values ​​and one or more predicted values ​​exceeds a threshold, the operation proceeds to sub-operation 350. In sub-operation 350, the program uses the MLA to adjust one or more model parameters, such as the optical properties of the upper or lower plate, heater output (e.g., lamp output) efficiency, and thermal contact resistance. The program and / or MLA can use data received from the processing chamber's physical sensors to determine which model parameters should be adjusted to more closely fit the physical chamber. After updating the virtual model in sub-operation 350 to create the adjusted virtual model, operation 300 returns to sub-operation 320. Operation 300 continues until sub-operation 340 is completed. If sub-operation 340 is not completed after a predetermined time, an error message is generated for the operator.

[0057]

[0061] Figure 4 shows a method 400 for operating a processing chamber according to one or more embodiments. Method 400 begins with operation 410, in which a substrate in the processing chamber is heated to a predetermined processing temperature according to a processing recipe. In operation 420, one or more processing gases are introduced into the processing chamber to flow over the heated substrate, according to the processing recipe. In operation 430, a first temperature in the processing chamber is monitored, for example, by measurement using a sensor. In one or more embodiments, the sensor is a pyrometer that measures the temperature of the upper plate (e.g., upper window) in the processing chamber.

[0058]

[0062] In operation 440, a second temperature within the processing chamber is monitored by measurement using a sensor. For example, the sensor is a pyrometer that measures the temperature of the substrate support within the processing chamber. In operation 450, a virtual model of the processing chamber synthesizes virtual temperatures of unmeasured components of the physical processing chamber. For example, the virtual model synthesizes the temperature of plates such as plate 171 within the processing chamber. In addition, in operation 450, the virtual model synthesizes the temperatures corresponding to the measured components (e.g., the monitored temperatures in operations 430 and 440). If the synthesized temperatures of the measured components are within a threshold (e.g., a predetermined tolerance for the measured values ​​of the physical processing chamber), an output is generated in operation 460. The accuracy of the virtual model is verified by comparing the synthesized values ​​with the measured values. The output in operation 460 shows the synthesized temperature of the top plate. The output can display one or more synthesized temperatures to the user, for example, on a display. The output can store one or more synthesized temperatures in memory. For example, the output may label one or more of the synthesized temperatures as "pass" for future use, such as future virtual model operations and / or future substrate processing operations.

[0059]

[0063] If the combined temperature exceeds a threshold (such as a predetermined tolerance for the measurement), method 400 proceeds to operation 470. During operation 470, one or more parameters of the virtual model are updated using MLA. Adjusting the virtual model includes adjusting one or more virtual temperatures of the upper plate, substrate support, and / or isolation plate to produce improved virtual temperatures of one or more of the upper plate, substrate support, and / or isolation plate. In one or more embodiments, the virtual temperature of the (predictable) isolation plate is adjusted. Method 400 then returns to operation 450, and method 400 proceeds until an output is generated in operation 460. Operation 470 may include deleting (or saving as described above) one or more of the combined temperatures. The output may store one or more of the combined temperatures in memory. As an example, the output may label one or more of the combined temperatures as “fail” for future use.

[0060]

[0064] Method 400 is illustrated with respect to the measurement of the upper plate and substrate support temperatures in operations 430 and 440, but measurements of other hardware components are also possible. Note that the upper plate and substrate support temperatures provide useful reference data points for verifying the accuracy of the virtual model because they are physically close to the upper plate. Specifically, a temperature gradient may exist between the substrate support (which readily absorbs heat radiation from the lamp) and the upper plate (which partially absorbs heat radiation from the lamp, the substrate support, and the substrate placed on the substrate support). Therefore, the temperature of the upper plate is generally between the temperature of the upper plate and the temperature of the substrate support. If the virtual model synthesizes the temperature of the top plate outside the gradient, the inaccuracy of the virtual model can be easily determined.

[0061]

[0065] This disclosure intends to allow for the omission of one or more operations of the methods described herein. For example, operations 470 and / or 460 may be omitted from method 400.

[0062]

[0066] Figure 5 shows an exemplary computer system 500 used for real-time virtual temperature sensing according to one or more embodiments. In one embodiment, the computer system 500 may be (or may be used instead of) the controller 190 in Figure 1. As shown, the system 500 includes a central processing unit (CPU) 193 and one or more I / O device interfaces 504 that can enable various I / O devices 514 (e.g., keyboard, display, mouse device, pen input, sensor, pyrometer, etc.) to connect to the system 600, a network interface 506, memory 191, and one or more interconnects 512.

[0063]

[0067] As shown in the figure, memory 191 includes a virtual model 518 of the physical processing chamber and a machine learning algorithm (MLA) 520 (which can be embedded in a neural network). The MLA 520 stored in memory 191 performs one or more of the methods and operations described above with respect to Figures 1 to 4. For example, the virtual model 518 and the MLA facilitate the synthesis of a virtual temperature of the upper plate of the physical processing chamber. The system 500 can use the synthesized parameters to provide instructions and information to the processing chamber, provide output to a display, or improve the virtual model 518. The virtual model includes improved transparency values ​​for the upper plate and / or improved heater output values.

[0064]

[0068] While embodiments of this specification describe synthesis temperatures, it should be noted that other metrics may also be synthesized. Furthermore, it should be noted that other hardware components may also be subject to synthesis metric determination. For example, process kits, liners, substrate supports, preheating rings, and other hardware components may have synthesized temperatures (or other metrics) according to the embodiments described herein.

[0065]

[0069] The methods disclosed herein include one or more operations or actions to achieve the method. The operations and / or actions of the method may be interchangeable with one another without departing from the claims. In other words, unless a particular order of operations or actions is specified, the order and / or use of a particular operation and / or action may be modified without departing from the claims. Furthermore, the various operations of the methods described above may be performed by any suitable means capable of performing the corresponding function. Such means may include, but are not limited to, circuits, application-specific integrated circuits (ASICs), or processors, as well as various hardware and / or software components and / or modules. Generally, where operations are shown in the figures, these operations may have corresponding means-plus-function components with similar numbering.

[0066]

[0070] Various exemplary logic blocks, modules, and circuits described in connection with this disclosure may be implemented or run in general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices (PLDs), discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. The general-purpose processor may be a microprocessor, but alternatively, the processor may be any commercially available processor, controller, microcontroller, or state machine. Furthermore, the processor may be implemented as a combination of arithmetic devices (e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors connected to a DSP core, or any other such configuration).

[0067]

[0071] The processing system may be implemented using a bus architecture. The bus may include any number of interconnection buses and bridges, depending on the specific application and overall design constraints of the processing system. The bus can, among other things, connect various circuits, including processors, machine-readable media, and input / output devices. User interfaces (e.g., keypads, displays, mice, joysticks, augmented reality, virtual reality, etc.) may also be connected to the bus. The bus may also link various other circuits (e.g., timing sources, peripherals, voltage regulators, power management circuits, and other types of circuits well known in the art), so further discussion is not necessary. The processor may be implemented using one or more general-purpose processors and / or application-specific processors. Examples include microprocessors, microcontrollers, DSP processors, and other circuits capable of running software. Those skilled in the art will recognize how to best implement the functions described for the processing system, depending on the specific application and the overall design constraints imposed on the system as a whole.

[0068]

[0072] When implemented in software, functionality may be stored or transmitted as one or more instructions or code on a computer-readable medium. Software should be broadly interpreted to mean instructions, data, or any combination thereof, whether referred to as software, firmware, middleware, microcode, hardware description language, or other names. Computer-readable medium includes both computer storage and communication media, such as any medium that facilitates the transfer of computer programs from one location to another. A processor may be responsible for managing bus and general-purpose processing, including the execution of software modules stored on a computer-readable storage medium. A computer-readable storage medium may be coupled to a processor so that the processor can read information from and write information to the storage medium. In an alternative example, the storage medium may be integrated with the processor. For example, a computer-readable medium may include a computer-readable storage medium with instructions stored separately from transmission lines, data-modulated carriers, and / or wireless nodes, all of which may be accessed by the processor via a bus interface. Alternatively or additionally, computer-readable media, or any portion thereof, may be integrated into the processor, as in the case of caches and / or general-purpose register files. Examples of machine-readable storage media may include, for example, RAM (random access memory), flash memory, ROM (read-only memory), PROM (programmable read-only memory), EPROM (erasable programmable read-only memory), EEPROM (electrically erasable programmable read-only memory), registers, magnetic disks, optical disks, hard drives, or any other suitable storage media, or any combination thereof. Machine-readable media may be embodied in computer program products.

[0069]

[0073] A software module may contain a single instruction or many instructions, and may be distributed across several different code segments, between different programs, and across multiple storage media. A computer-readable medium may contain a large number of software modules. When executed by a device such as a processor, a software module contains instructions that cause the processing system to perform various functions. A software module may include transmit modules and receive modules. Each software module may reside in a single storage device or be distributed across multiple storage devices. As an example, a software module may be loaded from a hard drive into RAM when a trigger event occurs. While a software module is executing, the processor may load some of the instructions into a cache to increase access speed. Then, one or more cache lines may be loaded into a general-purpose register file for execution by the processor. When considering the function of a software module, it is important to understand that the processor performs that function when it executes instructions from that software module.

[0070]

[0074] The benefits of this disclosure include accurate monitoring and adjustment (e.g., optimization) of processing parameters in processing recipes, adjustment of processing parameters in processing recipes to account for aging and wear of chamber components, and real-time and in-situ adjustment of processing parameters in processing recipes. The benefits also include accurate and efficient prediction of measurements.

[0071]

[0075] It is assumed that one or more embodiments disclosed herein may be combined. For example, one or more embodiments, features, components, operations, and / or characteristics of the processing chamber 100, method 200, operation 300, method 400, and / or computer system 500 may be combined. Furthermore, it is assumed that one or more embodiments disclosed herein may include some or all of the aforementioned advantages.

[0072]

[0076] While the above description applies to embodiments of the present disclosure, other embodiments and further embodiments of the present disclosure can be devised without departing from the basic scope of the present disclosure, and the scope of the present disclosure is defined by the following claims.

Claims

1. A method for operating a processing chamber suitable for use in semiconductor manufacturing, Receiving process recipes for the manufacturing process, Using a sensor, the first temperature of the first hardware component of the processing chamber is monitored, Using the model of the processing chamber, a first virtual temperature of the second hardware component of the processing chamber is synthesized based on the received process recipe and the first temperature of the first hardware component. Methods that include...

2. Using the aforementioned model, the second virtual temperature of the first hardware component is synthesized, Determining whether the first difference between the first temperature and the second virtual temperature of the first hardware component is within a threshold, In response to the first difference being outside the threshold, the model is adjusted until the first difference falls within the threshold. The method according to claim 1, further comprising:

3. The method according to claim 2, wherein adjusting the model includes updating the first virtual temperature.

4. Using a sensor, the second temperature of the third hardware component of the processing chamber is monitored, Using the aforementioned model, the third virtual temperature of the third hardware component is synthesized, To determine whether the second difference between the second temperature and the third virtual temperature of the third hardware component is within the threshold, In response to the fact that the second difference is outside the threshold, the model is adjusted until the second difference falls within the threshold. The method according to claim 2, including the method described in claim 2.

5. Monitoring the first temperature of the first hardware component is While the substrate is being heated, and While the processing gas is flowing over the substrate... The method according to claim 1, which is performed in the following way.

6. The method according to claim 4, wherein the first hardware component is one of the upper plate or substrate support of the processing chamber, the second hardware component is a separation plate of the processing chamber, and the third hardware component is another upper plate of the substrate support.

7. The method according to claim 6, wherein the upper plate and the separation plate are formed from quartz.

8. The method according to claim 2, wherein the first virtual temperature is updated using a machine learning algorithm.

9. A method for operating a processing chamber suitable for use in semiconductor manufacturing, Receiving a processing recipe for the deposition process in the processing chamber, Using a virtual model based on the received processing recipe, the virtual temperature of the upper plate or substrate support and the virtual temperature of the separation plate are combined. Determining whether the first difference between one or more temperature measurements of the upper plate or the substrate support and the combined virtual temperature of the upper plate or the substrate support is within a threshold, Adjusting the virtual model in response to the first difference being outside the threshold until the first difference falls within the threshold, wherein adjusting the virtual model includes adjusting the virtual temperature of the separation plate. A method that includes this.

10. The method according to claim 9, further comprising synthesizing improved virtual temperatures for each of the upper plate, the substrate support, and the isolation plate based on the adjusted virtual model when the first difference is outside the threshold.

11. The method according to claim 9, further comprising adjusting the processing parameters of the processing chamber if the first difference is within the threshold, wherein the adjusted processing parameters of the processing chamber include one or more of a gas flow rate, a substrate support position, or a heater output.

12. The method according to claim 11, wherein the separation plate is disposed between the upper plate and the substrate support, and the upper plate and the separation plate are formed from quartz.

13. The method according to claim 12, wherein the virtual model is updated using a machine learning algorithm.

14. The method according to claim 10, wherein the virtual model includes an improved transparency value for the upper plate or an improved heater output value.

15. The method according to claim 9, further comprising determining whether a second difference between one or more temperature measurements of the substrate support and the combined virtual temperature of the substrate support is within the threshold, and if the second difference is outside the threshold, adjusting the virtual model until the second difference falls within the threshold.

16. A non-temporary computer-readable medium containing instructions, wherein, when the instructions are executed by the system's processor, the system... Receiving process recipes for the manufacturing process, Using a sensor, the first temperature of the first hardware component of the processing chamber is monitored, Using the model of the processing chamber, a first virtual temperature of the second hardware component of the processing chamber is synthesized based on the received process recipe and the first temperature of the first hardware component. A non-temporary computer-readable medium that enables the operation of [the process].

17. The instruction to the system Using the aforementioned model, the second virtual temperature of the first hardware component is synthesized, Determining whether the first difference between the first temperature and the second virtual temperature of the first hardware component is within a threshold, In response to the first difference being outside the threshold, the model is adjusted until the first difference falls within the threshold. A non-temporary computer-readable medium according to claim 16, further enabling the following:

18. The instruction to the system Using a sensor, the second temperature of the third hardware component of the processing chamber is monitored, Using the aforementioned model, the third virtual temperature of the third hardware component is synthesized, To determine whether the second difference between the second temperature and the third virtual temperature of the third hardware component is within the threshold, In response to the fact that the second difference is outside the threshold, the model is adjusted until the second difference falls within the threshold. A non-temporary computer-readable medium according to claim 17, further enabling the following:

19. The instruction to the system If the first difference is within the threshold, the processing parameters of the processing chamber are further adjusted, the adjusted processing parameters of the processing chamber include one or more of the following: gas flow rate, substrate support position, or heater output, the non-temporary computer-readable medium according to claim 17.

20. The non-temporary computer-readable medium according to claim 17, wherein adjusting the model includes updating one or more transparency values ​​of the heater output values.

Images