Controlling concentration profiles for deposited films using machine learning

Abstract

A method and system are provided for controlling a concentration profile of a deposited film using machine learning. During a deposition process for a substrate, data associated with a target concentration profile for a film deposited on a surface of the substrate is provided as an input to a trained machine learning model. One or more outputs of the trained machine learning model are obtained. Process recipe data identifying one or more sets of deposition process settings are determined from the one or more outputs. For each set of deposition process settings, an indication of a level of confidence that the respective set of deposition process settings corresponds to a target concentration profile for a film deposited on the substrate is also determined. In response to identifying the respective set of deposition process settings having a level of confidence that satisfies a level of confidence criterion, one or more operations of the deposition process are performed according to the respective set of deposition process settings.

Description

Technical Field

[0001] Embodiments of the present disclosure generally relate to manufacturing systems, and more particularly, to controlling concentration profiles for deposited films using machine learning.

Background Art

[0002] Processing electronic devices in a manufacturing system can involve creating intricately patterned material layers on the surface of a substrate. The manufacturing system can deposit a film on the surface of the substrate and perform an etching process to form complex patterns within the deposited film. The type of material and the concentration of each material in the deposited film can affect the performance of the etching process (e.g., the rate of the etching process, the accuracy of the etching process, etc.). As electronic devices become more detailed and complex, the operator of the manufacturing system may seek to adjust or enhance the material properties of the deposited film in order to create an etched substrate that meets specific device specifications. However, it can be difficult for an operator to identify the appropriate manufacturing steps or settings that will result in an electronic device that meets the device specifications.

Summary of the Invention

[0003] Some of the embodiments described encompass a method which includes providing data associated with a target concentration profile for a film deposited on the surface of a substrate during a deposition process for the substrate in a process chamber of a manufacturing system as input to a trained machine learning model. The method further includes obtaining one or more outputs of the trained machine learning model. The method further includes process recipe data identifying one or more sets of deposition process settings, and for each set of deposition process settings, determining from one or more outputs that indicate the level of confidence that each set of deposition process settings corresponds to the target concentration profile for a film deposited on the substrate. The method further includes identifying each set of deposition process settings that has a level of confidence that satisfies a level of confidence criterion. The method further includes performing one or more operations of the deposition process according to each set of deposition process settings.

[0004] In some embodiments, the system includes memory and a processing device coupled to the memory. The processing device will predict one or more deposition settings for a deposition process to be performed on the current substrate in the manufacturing system. The deposition process includes depositing a film on the surface of the current substrate. The processing device will further generate first training data for a machine learning model. The first training data includes historical data associated with one or more previous deposition settings for a previous deposition process previously performed on a previous (preceding) substrate in the manufacturing system, where the previous deposition process includes depositing a previous film on the surface of the previous substrate. The processing device will further generate second training data for the machine learning model. The second training data is associated with historical concentration profiles for previous films deposited on the surface of the previous substrate. The processing device will further provide the first and second training data to train the machine learning model to predict, for a deposition process to be performed on the current substrate, which set of deposition settings for the deposition process corresponds to a target concentration profile for the film deposited on the surface of the current substrate.

[0005] In some embodiments, a non-temporary computer-readable storage medium includes instructions, which, when executed by a processing device, cause the processing device to provide data associated with a target concentration profile for a film deposited on the surface of a substrate during a deposition process for the substrate in a process chamber of a manufacturing system, as input to a trained machine learning model. The processing device further obtains one or more outputs of the trained machine learning model. The processing device further determines from one or more outputs process recipe data identifying one or more sets of deposition process settings, and for each set of deposition process settings, a confidence level indicating that each set of deposition process settings corresponds to a target concentration profile for a film deposited on the substrate. The processing device further identifies each set of deposition process settings having a confidence level that satisfies a confidence criterion level. The processing device further performs one or more operations of the deposition process according to each set of deposition process settings.

[0006] This disclosure is illustrated, not as an limitation but as an example, in the drawings in the accompanying drawings, where the same reference numeral indicates similar elements. It should be noted that any reference in this disclosure to “a certain” embodiment or “one” embodiment does not necessarily refer to the same embodiment, but rather means at least one. [Brief explanation of the drawing]

[0007] [Figure 1] This is a diagram illustrating an illustrative computer system architecture according to the aspects of this disclosure. [Figure 2] This is a flowchart of a method for training a machine learning model according to the aspects of this disclosure. [Figure 3] This is a schematic top view of an example manufacturing system according to the embodiments of this disclosure. [Figure 4] This is a schematic cross-sectional side view of an example process chamber of an example manufacturing system according to an aspect of the present disclosure. [Figure 5] This is a flowchart of a method for controlling a concentration profile for a deposited film using machine learning, according to an aspect of this disclosure. [Figure 6A] This figure illustrates the deposition of a film having a target concentration profile on the surface of a substrate according to an aspect of the present disclosure. [Figure 6B] This figure illustrates the deposition of a film having a target concentration profile on the surface of a substrate according to an aspect of the present disclosure. [Figure 6C] This figure illustrates the deposition of a film having a target concentration profile on the surface of a substrate according to an aspect of the present disclosure. [Figure 7] This is a block diagram of an illustrative computer system operating in accordance with one or more aspects of the present disclosure. [Modes for carrying out the invention]

[0008] The implementations described herein provide systems and methods for controlling concentration profiles for deposited films using machine learning. Films can be deposited on the surface of a substrate during a deposition process carried out in a process chamber of a manufacturing system. The film may comprise one or more layers of material formed during the deposition process. For example, a first layer of material may be formed directly on the substrate surface (referred to as the proximal layer or proximal edge of the film). After the first layer is formed on the substrate surface, a second layer of material may be formed on the first layer. This process continues until the deposition process is complete and the final layer is formed for the film (referred to as the distal layer or distal edge of the film).

[0009] In some embodiments, each layer of the deposited film material may contain multiple different materials. For example, a film deposited on the surface of a substrate may contain one or more boron and silicon-containing layers. The boron and silicon-containing layers may be used as a mask for the etching process. The mask defines specific structures (e.g., vertical openings, electrical contact openings, etc.) that are formed on the substrate during the etching process. Certain materials in the boron and silicon-containing layers remain on the substrate surface during the etching process (referred to as etch-resistant materials), while other materials are etched away by the plasma (referred to as etchable materials).

[0010] In some embodiments, the structural characteristics of openings etched onto the substrate surface may be influenced by the concentration of specific materials in each layer of the deposited film. For example, in a film containing boron and silicon-containing layers, the etching process may be carried out to create opening sidewalls and opening beds on the substrate. Boron and silicon-containing layers with low boron concentrations may increase the etching selectivity of the layers above the etch-stopping layer (i.e., the layer of material that terminates the etching process for at least a portion of the substrate), allowing for the formation of more precise opening beds. However, low boron concentrations may result in rougher and less precise opening sidewalls than boron and silicon-containing layers with high boron concentrations. Conversely, boron and silicon-containing layers with high boron concentrations may allow for the formation of precise opening sidewalls, but may result in less precise opening beds than boron and silicon-containing layers with low boron concentrations. As the complexity of electronic devices increases, so does the specificity and sensitivity of the structures etched onto the substrate surface. As shown above, the specificity and sensitivity of the structures etched onto the substrate surface may depend on the concentration of specific materials in various layers of the deposited film.

[0011] In some cases, a user of a manufacturing system (e.g., an operator) may want to perform a deposition process to deposit a film having a target concentration profile on the surface of a substrate. The concentration profile refers to a specific concentration gradient of the deposited film with respect to its final thickness (i.e., the change in the concentration of a particular material between different layers of the deposited film). For example, a concentration profile for a boron and silicon-containing film may include a proximal layer with a low concentration of boron and a distal layer with a high concentration of boron, where the boron concentration in the film layers between the proximal and distal layers increases linearly. In some embodiments, the target concentration profile for a film may be a film concentration profile that facilitates etching of a structure onto the surface of a substrate with a target accuracy (e.g., 95% accuracy, 98% accuracy, 99.9999999% accuracy, etc.).

[0012] In some cases, determining the settings for a deposition process that yield a deposited film with a target concentration profile can be difficult. For example, a deposition process setting that increases or decreases the flow of a precursor of a particular material at a constant rate (i.e., linearly) may not yield a deposited film with a concentration profile that includes a linear increase or decrease of the particular material between the proximal and distal layers of the deposited film. For example, diborane (B2H6) can be used as a precursor for silicon-based and boron-based deposition processes. Increasing the flow of diborane can increase the amount of boron (B) in the process chamber, which can increase the deposition rate for the process. In some cases, the increased deposition rate can lead to nonlinear profiles of silicon and boron in the deposited film. In some cases, a significant number of experiments may be conducted (e.g., by the user of the manufacturing system) to attempt to determine the deposition process settings that yield a deposited film with a target concentration profile. However, these experiments can consume a considerable amount of manufacturing system resources, and the appropriate deposition process settings for the target concentration profile may not be identified.

[0013] Aspects of this disclosure address the shortcomings described above and others by providing systems and methods for controlling concentration profiles for deposited films using machine learning. A processing device in a manufacturing system may provide data associated with a target concentration profile for a film deposited on the surface of a substrate as input to a trained machine learning model during the deposition process. The machine learning model may be trained to predict, for the deposition process, which set of deposition settings corresponds to the target concentration profile for a film deposited on the surface of the substrate. In some embodiments, the processing device may receive data associated with the target concentration profile from a client device connected to the manufacturing system. For example, a user of the manufacturing system may provide via the client device data indicating the target thickness for the film, the target initial concentration for the proximal layer of the film, the target final concentration for the distal layer of the film, and the target shape (i.e., linear shape, nonlinear shape, etc.) for the concentration gradient between the proximal and distal layers of the film. In response to providing data associated with the target concentration profile for the film as input to a machine learning model, the processing device may obtain one or more outputs of the machine learning model. The processing device may determine, based on one or more outputs, process recipe data that identifies one or more sets of deposition process settings, and for each set of deposition process settings, the confidence level that each set of deposition process settings corresponds to the target concentration profile. The processing device may identify each set of deposition settings that has a confidence level that satisfies a confidence criterion level (e.g., exceeds the confidence threshold level) and perform the deposition process for the substrate according to each set of deposition settings.

[0014] As described above, a machine learning model can be trained to predict which set of deposition settings corresponds to a target concentration profile for a film deposited on the substrate surface during the deposition process. In some embodiments, the machine learning model can be trained based on historical data associated with previous deposition processes performed on one or more previous substrates in the manufacturing system. For example, first training data for the machine learning model may include historical data associated with previous deposition settings for previous deposition processes previously performed in the manufacturing system to deposit a previous film on the surface of a previous substrate. Second training data for the machine learning model may be associated with historical concentration profiles for previous films deposited on the substrate surface. In some embodiments, the historical concentration profiles may correspond to historical measurements of the previous film (e.g., the thickness of the previous film) and historical concentrations associated with the previous film. Processing logic (e.g., a processing device in the manufacturing system) may provide the first and second training data to train the machine learning model.

[0015] Aspects of this disclosure address the shortcomings of the prior art by providing a system and method for predicting deposition settings corresponding to a target profile for a film deposited on the surface of a substrate. Using data associated with past deposition processes performed on previous substrates in a manufacturing system, a machine learning model can be trained to predict deposition settings corresponding to a target concentration profile for a current substrate being processed in the manufacturing system. A processing device in the manufacturing system can provide data associated with the target concentration profile as input to a trained machine learning model and determine a set of deposition settings corresponding to the target concentration profile based on the output of the trained machine learning model. By using a machine learning model trained to identify deposition settings corresponding to a target concentration profile, a significant number of experiments are not performed to determine the deposition process settings that yield a deposited film with the target concentration profile. The reduction in the number of experiments reduces the consumption of manufacturing system leases, resulting in increased overall throughput and efficiency, as well as a reduction in the overall latency of the manufacturing system.

[0016] Figure 1 depicts an illustrative computer system architecture 100 according to an aspect of the present disclosure. In some embodiments, the computer system architecture 100 may be included as part of a manufacturing system for processing substrates, such as the manufacturing system 300 in Figure 3. The computer system architecture 100 includes a client device 120, manufacturing equipment 124, metrology instruments 128, a prediction server 112 (e.g., for generating prediction data, providing model adaptation, using a knowledge base, etc.), and a data store 140. The prediction server 112 may be part of a prediction system 110. The prediction system 110 may further include server machines 170 and 180. The manufacturing equipment 124 may include a sensor 125 configured to capture data about the substrates being processed in the manufacturing system. In some embodiments, the manufacturing equipment 124 and the sensor 126 may be part of a sensor system including a sensor server (e.g., a field service server (FSS) in a manufacturing facility) and a sensor identifier reader (e.g., a Front Opening Unified Pod (FOUP) radio frequency identification (RFID) reader for a sensor system). In some embodiments, the metrology instrument 128 may be part of a metrology system that includes a metrology server (e.g., a metrology database, a metrology folder, etc.) and a metrology identifier reader (e.g., a FOUP RFID reader for the metrology system).

[0017] The manufacturing apparatus 124 can produce products such as electronic devices by following a recipe or by running a run over a period of time. The manufacturing apparatus 124 may include a process chamber, such as the process chamber 400 described with reference to Figure 4. The manufacturing apparatus 124 may perform processes for a substrate (e.g., a wafer) in the process chamber. Examples of substrate processes include a deposition process for depositing a film on the surface of the substrate and an etching process for forming a pattern on the surface of the substrate. The manufacturing apparatus 124 may perform each process according to a process recipe. The process recipe may define a specific set of operations performed on the substrate during the process and may include one or more settings associated with each operation. For example, a deposition process recipe may include a temperature setting for the process chamber, a pressure setting for the process chamber, and a flow rate setting for the precursor material to be contained in the film deposited on the substrate surface.

[0018] In some embodiments, the manufacturing apparatus 124 may include sensors 126 configured to generate data associated with the substrate being processed in the manufacturing apparatus 124. For example, the process chamber may include one or more sensors configured to generate spectral or non-spectral data associated with the substrate before, during, and / or after a process (e.g., a deposition process) is performed on the substrate. In some embodiments, the spectral data generated by the sensors 126 may indicate the concentration of one or more materials deposited on the surface of the substrate. Sensors 126 configured to generate spectral data associated with the substrate may include reflectance sensors, ellipsometry sensors, thermal spectral sensors, capacitive sensors, and the like. Sensors 126 configured to generate non-spectral data associated with the substrate may include temperature sensors, pressure sensors, flow sensors, voltage sensors, and the like. Further details regarding the manufacturing apparatus 124 are provided with reference to Figures 3 and 4.

[0019] In some embodiments, sensor 126 may provide sensor data associated with manufacturing apparatus 124. The sensor data may include one or more values such as temperature (e.g., heater temperature), setpoint (SP), pressure, high frequency radio frequency (HFRF), voltage of an electrostatic chuck (ESC), current, material flow, power, voltage, etc. The sensor data may be associated with or indicative of manufacturing parameters such as hardware parameters (e.g., settings or components of manufacturing apparatus 124 such as size, type, etc.), or process parameters of manufacturing apparatus 124. The sensor data may be provided while manufacturing apparatus 124 is performing a manufacturing process (e.g., instrument readout while processing a product). The sensor data may vary for each substrate.

[0020] Metrology instrument 128 may provide metrology data associated with a substrate processed by manufacturing apparatus 124. The metrology data may include values such as film property data (e.g., wafer space film properties), dimensions (e.g., thickness, height, etc.), dielectric constant, dopant concentration, density, defects, etc. In some embodiments, the metrology data may further include values of one or more surface profile property data (e.g., etch rate, etch rate uniformity, critical dimensions of one or more features included on a surface of the substrate, critical dimension uniformity across the surface of the substrate, edge placement error, etc.). The metrology data may be of a finished or semi-finished product. The metrology data may vary for each substrate.

[0021] In some embodiments, the metrology instrument 128 may be included as part of the manufacturing apparatus 124. For example, the metrology instrument 128 may be included inside or coupled to a process chamber and may be configured to generate metrology data about the substrate before, during, and / or after a process (e.g., a deposition process, an etching process, etc.) while the substrate remains inside the process chamber. In such a case, the metrology instrument 128 may be referred to as an in-situ metrology instrument. In another example, the metrology instrument 128 may be coupled to another station of the manufacturing apparatus 124. For example, the metrology instrument may be coupled to a transfer chamber such as the transfer chamber 310 in Figure 3, a load lock such as the load lock 320, or a factory interface such as the factory interface 306. In such a case, the metrology instrument 128 may be referred to as an integrated metrology instrument. In other or similar embodiments, the metrology instrument 128 is not coupled to a station of the manufacturing apparatus 124. In such a case, the metrology instrument 128 may be referred to as an in-line metrology instrument or an external metrology instrument. In some embodiments, an integrated metrological instrument and / or an inline metrological instrument is configured to generate metrological data about the substrate before and / or after the process.

[0022] The client device 120 may include computing devices such as personal computers (PCs), laptops, mobile phones, smartphones, tablet computers, netbook computers, network-connected televisions ("smart TVs"), network-connected media players (e.g., Blu-ray players), set-top boxes, over-the-top (OTT) streaming devices, and operator boxes. In some embodiments, metrological data may be received from the client device 120. The client device 120 may display a graphical user interface (GUI) that allows the user to provide measurements as input for substrates being processed in the manufacturing system.

[0023] The data store 140 can be a memory (e.g., random access memory), a driver (e.g., hard driver, flash driver), a database system, or another type of component or device capable of storing data. The data store 140 can include multiple storage components (e.g., multiple drivers or multiple databases) that can span across multiple computing devices (e.g., multiple server computers). The data store 140 can store data associated with processing substrates in the manufacturing apparatus 124. For example, the data store 140 can store data (referred to as process data) collected by the sensor 126 in the manufacturing apparatus 124 before, during, or after the substrate process. The process data can refer to past process data (e.g., process data generated for previous substrates processed in the manufacturing system) and / or current process data (e.g., process data generated for the current substrate being processed in the manufacturing system). The data store can also store spectral or non-spectral data associated with a portion of the substrate being processed in the manufacturing apparatus 124. The spectral data can include past spectral data and / or current spectral data.

[0024] In some embodiments, the data store 140 may also store concentration profile data associated with the film deposited on the substrate surface. As previously described, a concentration profile refers to a specific concentration gradient of the deposited film with respect to the final thickness of the deposited film (i.e., the change in the concentration of a particular material between different layers of the deposited film). In some embodiments, the concentration profile data may include the thickness or film deposited on the substrate surface, the initial concentration of a particular material in the film (e.g., the concentration of a particular material in the proximal layer of the film), and the final concentration of a particular material in the film (e.g., the concentration of a particular material in the distal layer of the film). In some embodiments, the concentration profile data may also include a rate of change in the concentration of a particular material within the film layers between the proximal and distal layers. For example, the concentration profile data may include a linear rate of change (i.e., a constant rate of change) or a nonlinear rate of change (i.e., a non-constant rate of change) of the concentration of a particular material in the layers between the proximal and distal layers of the deposited film. In some embodiments, the concentration profile data may be provided by a user of the manufacturing system (e.g., an operator) (e.g., via a client device 120). In other or similar embodiments, concentration profile data may be determined by a processing device in the manufacturing system (e.g., the system controller 328 in Figure 3) based on sensor data and / or metrological data stored in the data store 140. The concentration profile data may refer to historical concentration profile data (e.g., concentration profile data for a previous film deposited on a previous substrate) or current concentration profile data (e.g., concentration profile data for the current film deposited on the current substrate).

[0025] In some embodiments, the concentration profile data may also include data associated with a target concentration profile for a film deposited on the surface of a substrate. For example, a user of the operating system (e.g., an operator) may provide the data associated with the target concentration profile via a client device 120. The data associated with the target concentration profile may include at least one of the following: the target thickness of the film deposited on the surface of the substrate, the target initial concentration of a particular material in the film (e.g., the concentration of the particular material in the proximal layer of the film), and the target final concentration of a particular material in the film (e.g., the concentration of the particular material in the distal layer of the film). In some embodiments, the data associated with the target concentration may also include a target rate of change (e.g., linear, nonlinear, etc.) of the concentration gradient for a particular material within the layers between the proximal and distal layers of the film.

[0026] The data store 140 may also store context data associated with one or more substrates processed in the manufacturing system. Context data may include recipe names, recipe step numbers, preventive maintenance indicators, operators, etc. Context data may refer to historical context data (e.g., context data associated with previous processes performed on previous substrates) and / or current process data (e.g., context data associated with current or future processes performed on previous substrates). In some embodiments, context data may also include one or more settings associated with a particular process. For example, context data for a deposition process may include temperature settings for the process chamber, pressure settings for the process chamber, flow rate settings for the precursor material of the film deposited on the substrate, etc.

[0027] In some embodiments, the data store 140 may be configured to store data that is inaccessible to users of the manufacturing system. For example, process data, spectral data, and context data obtained about substrates being processed in the manufacturing system are inaccessible to users of the manufacturing system (e.g., operators). In some embodiments, all data stored in the data store 140 may be inaccessible to users of the manufacturing system. In other or similar embodiments, some of the data stored in the data store 140 may be inaccessible to users, while other parts of the data stored in the data store 140 may be accessible to users. In some embodiments, one or more parts of the data stored in the data store 140 may be encrypted using an encryption mechanism unknown to the user (e.g., the data is encrypted using a private encryption key). In other or similar embodiments, the data store 140 may include multiple data stores, where data inaccessible to users is stored in one or more first data stores, and data accessible to users is stored in one or more second data stores.

[0028] In some embodiments, the prediction system 110 includes server machines 170 and 180. Server machine 170 includes a training set generator 172 capable of generating training datasets (e.g., a set of data inputs and a set of target outputs) for training, validating, and / or testing a machine learning model 190. Some operations of the dataset generator 172 are described below in detail with respect to Figure 2. In some embodiments, the dataset generator 172 may split the training data into a training set, a validation set, and a test set. In some embodiments, the prediction system 110 generates multiple sets of training data.

[0029] The server machine 180 may include a training engine 182, a validation engine 184, a selection engine 185, and / or a test engine 186. An engine may refer to hardware (e.g., circuits, dedicated logic, programmable logic, microcode, processing devices, etc.), software (e.g., instruction runs on processing devices, general-purpose computer systems, or dedicated machines), firmware, microcode, or a combination thereof. The training engine 182 may have the capability to train a machine learning model 190. The machine learning model 190 may refer to a model artifact created by the training engine 182 using training data containing training inputs and corresponding target outputs (the correct answers for each training input). The training engine 182 may discover patterns in the training data that map training inputs to target outputs (expected answers) and provide a machine learning model 190 that captures these patterns. Machine learning models 190 may use one or more of the following: support vector machines (SVMs), radial basis functions (RBFs), clustering, supervised machine learning, semi-supervised machine learning, unsupervised machine learning, k-nearest neighbor algorithms (k-NNs), linear regression, ridge regression, random forests, and neural networks (e.g., artificial neural networks).

[0030] The validation engine 184 may have the ability to validate the trained machine learning model 190 using a corresponding set of features from the validation set generator 172. The validation engine 184 may determine the accuracy of each trained machine learning model 190 based on the corresponding set of features from the validation set. The validation engine 184 may discard trained machine learning models 190 that have an accuracy that does not meet a threshold accuracy. In some embodiments, the selection engine 185 may have the ability to select trained machine learning models 190 that have an accuracy that meets a threshold accuracy. In some embodiments, the selection engine 185 may have the ability to select the trained machine learning model 190 that has the highest accuracy.

[0031] The test engine 186 may have the ability to test trained machine learning models 190 using a corresponding set of features from a test set derived from the dataset generator 172. For example, a first trained machine learning model 190 trained using a first set of features from a training set may be tested using a first set of features from a test set. Based on the test set, the test engine 186 may determine which trained machine learning model 190 has the highest accuracy among the trained machine learning models.

[0032] The prediction server 112 includes a prediction component 114 that provides data associated with a target concentration profile for a film deposited on the surface of the substrate during the deposition process for the substrate, and has the capability to run a trained machine learning model 190 on the input to obtain one or more outputs. As described in detail below with respect to Figure 7, in some embodiments, the prediction component 114 also has the capability to determine process recipe data from the output of the trained machine learning model 190 and to use that process recipe data to predict deposition settings corresponding to a target concentration profile for a film deposited on the surface of the substrate. The process recipe data may include one or more sets of deposition process settings, and for each set of deposition process settings, may include or indicate a level of confidence that each set of deposition settings corresponds to a target concentration profile. Each set of deposition process settings may be associated with a specific concentration profile for a film deposited on the surface of the substrate. The prediction system 110 may determine that each set of deposition process settings corresponds to a target concentration profile in response to determining that the difference between the specific profile associated with each set of deposition process settings and the target concentration profile is below a difference threshold.

[0033] The client device 120, manufacturing equipment 124, sensors 126, metrology instruments 128, prediction server 112, data store 140, server machine 170, and server machine 180 may be connected to each other via network 130. In some embodiments, network 130 is a public network that provides client device 120 with access to prediction server 112, data store 140, and other publicly available computing devices. In some embodiments, network 130 is a private network that provides client device 120 with access to manufacturing equipment 124, metrology instruments 128, data store 140, and other privately available computing devices. Network 130 may include one or more wide area networks (WANs), local area networks (LANs), wired networks (e.g., Ethernet networks), wireless networks (e.g., 802.11 networks or Wi-Fi networks), cellular networks (e.g., Long-Term Evolution (LTE) networks), routers, hubs, switches, server computers, cloud computing networks, and / or combinations thereof.

[0034] It should be noted that in some other implementations, the functionality of server machines 170 and 180, as well as the prediction server 112, may be provided by fewer machines. For example, in some embodiments, server machines 170 and 180 are integrated into a single machine, while in some other or similar embodiments, server machines 170 and 180, as well as the prediction server 112, may be integrated into a single machine.

[0035] In general, functions described in one implementation as being performed by server machine 170, server machine 180, and / or prediction server 112 may also be performed on client device 120. In addition, functionality belonging to a particular component may be performed by different or multiple components working together.

[0036] In some embodiments, “User” may be represented as a single individual. However, other embodiments of the present disclosure include cases where “User” is an entity controlled by multiple users and / or automation sources. For example, a collection of individual users united as a group of administrators may be considered “User.”

[0037] Figure 2 is a flowchart 200 of a method for training a machine learning model according to an aspect of the present disclosure. Method 200 is implemented by processing logic which may include hardware (circuits, dedicated logic, etc.), software (such as a run on a general-purpose computer system or a dedicated machine), firmware, or any combination thereof. In one implementation, Method 200 may be implemented by a computer system such as the computer system architecture of Figure 1. In other or similar implementations, one or more operations of Method 200 may be implemented by one or more other machines not depicted in the figure. In some embodiments, one or more operations of Method 200 may be implemented by a training set generator 172 on a server machine 170.

[0038] For the sake of simplicity of explanation, the Method is described and explained as a series of actions. However, the actions provided herein may occur in various orders and / or simultaneously, and together with other actions not presented and explained herein. Furthermore, not all illustrated actions can be performed to implement the Method according to the disclosed subject matter. In addition, those skilled in the art will understand that the Method may alternatively be represented as a series of correlated states or events in a state diagram. Furthermore, it should be understood that the Method disclosed herein may be stored in a manufactured article to facilitate the transport and transfer of such Method to a computing device. Where used herein, the term "manufactured article" is intended to encompass a computer program accessible from any computer-readable device or storage medium.

[0039] In block 210, the processing logic initializes the training set T to an empty set (e.g., {}). In block 212, the processing logic obtains data associated with a previous deposition process performed to deposit a film on the surface of the previous substrate. In some embodiments, the data associated with the deposition process is historical data associated with one or more previous deposition settings for a previous deposition process previously performed on the previous substrate in the manufacturing system. For example, the historical data may be historical context data associated with the previous deposition process stored in the data store 140. In some embodiments, one or more previous deposition settings may include at least one of a previous temperature setting for a previous deposition process, a previous pressure setting for a previous deposition setting, or a previous flow rate setting for one or more material precursors of the previous film deposited on the surface of the previous substrate. The flow rate setting may refer to a flow rate setting for the precursor in an initial instance of the previous deposition process (referred to as the initial flow rate setting), a flow rate setting for the precursor in a final instance of the previous deposition process (referred to as the final flow rate setting), or the ramping rate of the flow rate of the precursor during the deposition process. In one example, the precursor of the previous film may include a boron-containing precursor or a silicon-containing precursor.

[0040] In block 214, the processing logic obtains concentration profile data associated with the film deposited on the surface of the previous substrate. As discussed earlier, the concentration profile refers to a specific concentration gradient of the deposited film with respect to its final thickness. The concentration profile data may include historical concentration profile data for the previous film deposited on the surface of the previous substrate. In some embodiments, the historical concentration profile for the previous film may correspond to historical measurements associated with the previous film (e.g., the thickness of the previous film) and historical concentrations associated with the previous film. In some embodiments, the historical concentration profile for the previous film may, additionally or alternatively, correspond to historical concentration gradients associated with the previous film. According to the embodiments described earlier, the processing logic may obtain the concentration profile data associated with the deposited film from the data store 140.

[0041] In block 216, the processing logic generates first training data based on acquired data associated with a previous deposition process performed on the previous substrate (e.g., data acquired in block 212). In block 218, the processing logic generates second training data based on concentration profile data associated with a film deposited on the surface of the previous substrate (e.g., data acquired in block 214). In block 220, the processing logic generates a mapping between the first and second training data. The mapping refers to first training data including, or based on, data for a previous deposition process performed on the previous substrate, and second training data including, or based on, concentration profile data associated with a film deposited on the surface of the previous substrate, where the first training data is associated with (or mapped to) the second training data. In block 224, the processing logic adds the mapping to training set T.

[0042] In block 226, the processing logic determines whether the training set T contains a sufficient amount of training data to train a machine learning model. Note that in some implementations, the satisfiesty of the training set T may be determined simply based on the number of mappings in the training set, while in some other implementations, the satisfiesty of the training set T may be determined based on the number of input / output mappings, or instead, on one or more other criteria (e.g., a measure of the diversity of the training examples). In response to determining that the training set does not contain a sufficient amount of training data to train a machine learning model, method 200 returns to block 212. In response to determining that the training set T contains a sufficient amount of training data to train a machine learning model, method 200 continues to block 228.

[0043] In block 228, the processing logic provides a training set T to train a machine learning model. In one implementation, the training set T is provided to the training engine 182 of the server machine 180 to perform the training. For a neural network, for example, the input values ​​of a given input / output mapping are inputs to the neural network, and the output values ​​of the input / output mapping are stored in the output nodes of the neural network. The connection weights within the neural network are then adjusted according to a learning algorithm (e.g., backpropagation), and this procedure is repeated for other input / output mappings in the training set T. After block 228, the machine learning model 190 may be used to predict which set of deposition settings for a deposition process corresponds to the target concentration profile for the film deposited on the surface of the current substrate, for a deposition process to be performed on the current substrate.

[0044] In some embodiments, a manufacturing system may include two or more process chambers. For example, manufacturing system 300, an example in Figure 3, illustrates several process chambers 314, 316, and 318. Note that in some embodiments, data acquired to train a machine learning model and data collected to be provided as input to a trained machine learning model may be associated with the same process chamber of the manufacturing system. In other or similar embodiments, data acquired to train a machine learning model and data collected to be provided as input to a trained machine learning model may be associated with different process chambers of the manufacturing system. In other or similar embodiments, data acquired to train a machine learning model may be associated with a process chamber of a first manufacturing system, and data collected to be provided as input to a trained machine learning model may be associated with a process chamber of a second manufacturing system.

[0045] Figure 3 is a schematic top view of an example manufacturing system 300 according to an aspect of the present disclosure. The manufacturing system 300 can carry out one or more processes on a substrate 302. The substrate 302 may be any preferably rigid, fixed-dimension planar article suitable for fabricating electronic devices or circuit components thereon, such as a silicon-containing disk or wafer, a patterned wafer, a glass plate, or the like.

[0046] The manufacturing system 300 may include a process tool 304 and a factory interface 306 coupled to the process tool 304. The process tool 304 may include a housing 308 having a transfer chamber 310 inside. The transfer chamber 310 may include one or more process chambers (also referred to as processing chambers) 314, 316, 318 arranged around it and coupled thereto. The process chambers 314, 316, 318 may be coupled to the transfer chamber 310 through their respective ports, such as slit valves or similar. The transfer chamber 310 may also include a transfer chamber robot 312 configured to transfer substrates 302 between the process chambers 314, 316, 318, a load lock 320, etc. The transfer chamber robot 312 may include one or more arms, each arm including one or more end effectors at the end of each arm. The end effectors may be configured to handle specific objects such as wafers.

[0047] Process chambers 314, 316, and 318 can be adapted to perform any number of processes on the substrate 302. The same or different substrate processes may occur in each process chamber 314, 316, and 318. Substrate processes may include atomic layer deposition (ALD), physical vapor deposition (PVD), chemical vapor deposition (CVD), etching, annealing, curing, pre-cleaning, metal or metal oxide removal, or similar. Other processes may be performed thereon on the substrate. Each process chamber 314, 316, and 318 may include one or more sensors configured to capture data about the substrate 302 before, after, or during the substrate process. For example, one or more sensors may be configured to capture spectral data and / or non-spectral data about a portion of the substrate 302 during the substrate process. In other or similar embodiments, one or more sensors may be configured to capture data related to the environment within process chambers 314, 316, and 318 before, after, or during the substrate process. For example, one or more sensors may be configured to capture data related to the temperature, pressure, gas concentration, and other environmental factors within the process chambers 314, 316, and 318 during the substrate process.

[0048] The load lock 320 may also be coupled to the housing 308 and the transfer chamber 310. The load lock 320 may be configured to interface with and coupled to the transfer chamber 310 and the factory interface 306 on one side. In some embodiments, the load lock 320 may have an environmentally controlled atmosphere that can change from a vacuum environment (where the substrate may be transferred to or from the transfer chamber 310) to an inert gas environment close to atmospheric pressure (where the substrate may be transferred to or from the factory interface 306). The factory interface 306 may be any suitable housing, such as an Equipment Front End Module (EFEM). The factory interface 306 may be configured to receive the substrate 302 from a substrate carrier 322 (e.g., a forward-opening unified pod (FOUP)) which docks to various load ports 324 of the factory interface 306. The factory interface robot 326 (shown by a dotted line) may be configured to transfer the substrate 302 between the carrier (also referred to as a container) 322 and the load lock 320. The carrier 322 may be a substrate storage carrier or a replacement parts storage carrier.

[0049] The manufacturing system 300 may also be connected to a client device (not shown) configured to provide information about the manufacturing system 300 to a user (e.g., an operator). In some embodiments, the client device may provide information to the user of the manufacturing system 300 via one or more graphical user interfaces (GUIs). For example, the client device may, via the GUI, provide information about a target concentration profile for a film to be deposited on the surface of the substrate 302 during the deposition process carried out in process chambers 314, 316, and 318. The client device may also provide information about modifications to the process recipe, taking into account each set of deposition settings that are expected to correspond to the target profile, according to embodiments described herein.

[0050] The manufacturing system 300 may also include a system controller 328. The system controller 328 may be, and / or include, a computing device such as a personal computer, a server computer, a programmable logic control unit (PLC), or a microcontroller. The system controller 328 may include one or more processing devices that may be general-purpose processing devices, such as a microprocessor, a central processing unit, or the like. More specifically, the processing device may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, or a processor that implements another instruction set, or a processor that implements a combination of instruction sets. The processing device may also be one or more special-purpose processing devices, such as an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), a network processor, or the like. The system controller 328 may include data storage devices (e.g., one or more disk drivers and / or solid drivers), main memory, static memory, a network interface, and / or other components. The system controller 328 may execute instructions to implement any one or more of the methodologies and / or embodiments described herein. In some embodiments, the system controller 328 may execute instructions to implement one or more operations in the manufacturing system 300 according to a process recipe. Instructions may be stored in a computer-readable storage medium which may include main memory, static memory, secondary storage, and / or processing devices (while the instructions are being executed).

[0051] The system controller 328 may receive data from sensors on or contained within various parts of the manufacturing system 300 (e.g., processing chambers 314, 316, 318, transfer chamber 310, load lock 320, etc.). In some embodiments, the data received by the system controller 328 may include spectral and / or non-spectral data for a portion of the substrate 302. In other or similar embodiments, the data received by the system controller 328 may include data associated with processing the substrate 302 in the processing chambers 314, 316, 318, as previously described. For the purposes of this description, the system controller 328 is described as receiving data from sensors contained within the process chambers 314, 316, 318. However, the system controller 328 may receive data from any part of the manufacturing system 300 and may use the data received from that part in accordance with the embodiments described herein. In an illustrative example, the system controller 328 may receive data from one or more sensors for process chambers 314, 316, and 318 before, after, or during the substrate process in the process chambers 314, 316, and 318. Data received from sensors in various parts of the manufacturing system 300 may be stored in a data store 350. The data store 350 may be included as a component within the system controller 328 or may be a component separate from the system controller 328. In some embodiments, the data store 350 may be the data store 140 described with reference to Figure 1.

[0052] Figure 4 is a schematic cross-sectional side view of a process chamber 400 according to an aspect of the present disclosure. In some embodiments, the process chamber 400 may correspond to process chambers 314, 316, and 318 described with respect to Figure 3. The process chamber 400 may be used for processes that provide a corrosive plasma environment. For example, the process chamber 400 may be a chamber for a plasma etcher or plasma etching reactor. In another example, the process chamber may be a chamber for a deposition process, as described earlier. In one embodiment, the process chamber 400 includes a chamber body 402 and a shower head 430 surrounding the internal volume 406. The shower head 430 may include a shower head base and a shower head gas distribution plate. Alternatively, the shower head 430 may be replaced in some embodiments by a lid and nozzles, or in other embodiments by a plurality of fan-shaped shower head compartments and a plasma generator. The chamber body 402 may be made from aluminum, stainless steel, or other preferred materials such as titanium (Ti). The chamber body 402 typically includes side walls 408 and a bottom 410. An exhaust port 426 may be defined within the chamber body 402, and the internal volume 406 may be connected to a pump system 428. The pump system 428 may include one or more pumps and throttle valves used to vacuum and regulate the pressure of the internal volume 406 of the process chamber 400.

[0053] The shower head 430 may be supported on the side wall 408 of the chamber body 402. The shower head 420 (or lid) may be opened to allow access to the internal volume 406 of the process chamber 400 and may provide a seal on the process chamber 400 when closed. A gas panel 458 may be coupled to the process chamber 400 to supply process and / or cleaning gases to the internal volume 406 through the shower head 430 or the lid and nozzle (e.g., through openings in the shower head or the lid and nozzle). For example, the gas panel 458 may provide a precursor material for a film 451 deposited on the surface of the substrate 302. In some embodiments, the precursor may include a silicon-based precursor or a boron-based precursor. The shower head 430 may include a gas distribution plate (GDP) and may have a plurality of gas delivery holes 432 (also referred to as channels) throughout the GDP. A substrate support assembly 448 is disposed in the internal volume 406 of the process chamber 400 below the shower head 430. The substrate support assembly 448 holds the substrate 302 during processing (e.g., during the deposition process).

[0054] In some embodiments, the process chamber 400 may be equipped with a concentration detection component 460. The concentration detection component 460 may include one or more sensors (e.g., acoustic sensors, optical sensors, ellipsometry sensors, etc.) configured to detect material in the process chambers 314, 316, 318. For example, one or more sensors of the concentration detection component 460 may be configured to detect a signature of the material (i.e., the wavelength of a set of photons emitted by the plasma), such as an optical signature or acoustic signature, during a process (e.g., a deposition process) in the process chambers 314, 316, 318. The concentration detection component 460 may measure the amplitude of various wavelengths of photons emitted by one or more materials of the film 451 deposited on the surface of the substrate 302. In other or similar embodiments, the concentration detection component 460 may be a device configured to detect a specific wavelength of photons emitted by a single material of the film 451 deposited on the surface of the substrate 302. It should be noted that while the concentration detection component 460 can detect and measure the wavelength of photons emitted by one or more materials of the film 451 deposited on the surface of the substrate 302, the concentration detection component 460 can also detect and measure the wavelength of photons emitted by each material within the process chamber 400 (e.g., a coating deposited on the walls of the process chamber 400).

[0055] In some embodiments, the concentration detection component 460 may be displaced to the outside of the process chamber 400. In such embodiments, the concentration detection component 460 may be configured to detect a signature (e.g., an optical signature, an acoustic signature, etc.) associated with the material inside the process chamber 400 from outside the process chamber 400. In some embodiments, the concentration detection component 460 may be a photodetector (e.g., an emission spectroscopy (OES) device) configured to detect an optical signature through a transparent portion 462 (e.g., a window) embedded in a part of the chamber body 402. For example, the photodetector may be configured to detect an optical signature through a window 462 embedded in the side wall 408, liner 416, bottom 410, and / or showerhead 430. Photons inside the process chamber 400 may be transmitted to the photodetector through the window 462 via a photon transmission cable 464, such as an optical fiber cable. In other or similar embodiments, one or more components of the concentration detection component 460 may be displaced to the inside of the process chamber 400. In some implementations, the process carried out within the process chamber 400 may be carried out in a vacuum environment. In such a case, one or more components of the concentration sensing component 460, which is configured to operate in a vacuum environment, may be displaced inward from the process chamber 400.

[0056] In some embodiments, the concentration detection component 460 may be operably coupled to a system controller, such as the system controller 328 in Figure 3. The concentration detection component 460 may transmit data about detected signatures to the system controller during the deposition process carried out in the process chamber 400 to deposit a film 451 on the surface of the substrate 302. In some embodiments, the system controller may generate concentration gradient data for the film 451 based on the data about detected signatures received from the concentration detection component 460 during the deposition process carried out in the process chamber 400. For example, during the deposition process, various layers of the film 451 are formed on the surface of the substrate 302. At one or more time instances during the deposition process, the concentration detection component 460 may transmit data about detected signatures for a particular material in the deposited film 451 (e.g., a boron-based material, a silicon-based material, etc.). Based on the received signatures, the system controller may determine the concentration of a particular material in the film at a particular instance of the deposition process. The system controller can generate a concentration gradient for the film 451 based on the determined concentration of each specific material in each instance of the deposition process.

[0057] In some embodiments, the processing chamber 400 may include a metrological instrument (not shown) configured to generate in-situ measurements during the process carried out in the process chamber 400. The metrological instrument may be operably coupled to a system controller (e.g., a system controller 328 as described earlier). In some embodiments, the metrological instrument may be configured to generate measurements (e.g., thickness) of the film 451 during a particular instance of the deposition process. The system controller may generate a concentration profile for the film 451 based on the measurements received from the metrological instrument. For example, the system controller may generate a concentration profile by associating a determined concentration of a particular material in the film during a particular instance of the deposition process with measurements generated during the same or similar instances of the deposition process. In other or similar embodiments, the processing chamber 400 does not include a metrological instrument. In such embodiments, the system controller may receive one or more measurements of the film 451 after the completion of the deposition process in the process chamber 400. The system controller can determine the deposition rate based on one or more measurements, and can also associate and generate a concentration profile for the film 451 based on the determined concentration gradient and the determined deposition rate of the deposition process.

[0058] Figure 5 is a flowchart of Method 500 for controlling a concentration profile for a deposited film using machine learning, according to an aspect of the present disclosure. Method 500 is implemented by processing logic which may include hardware (circuitry, dedicated logic, etc.), software (such as a run on a general-purpose computer system or a dedicated machine), firmware, or any combination thereof. In some embodiments, Method 500 may be implemented using the prediction server 112 and trained machine learning model 190 of Figure 1. In other or similar embodiments, one or more blocks of Figure 5 may be implemented by one or more other machines not depicted in Figure 1.

[0059] In block 510, the processing logic optionally receives information indicating the target thickness of the film, the target initial concentration for a particular material in the film, and the target final concentration for the material within the film, for a film to be deposited on the surface of the substrate. In some embodiments, the processing logic may also receive information indicating the target rate of change (e.g., linear change, nonlinear change, etc.) for the concentration of a particular material in various layers between the proximal and distal layers of the film. In some embodiments, the processing logic may receive information indicating the target thickness, target initial concentration, target final concentration, and / or target rate of change from a client device coupled to the manufacturing system. In block 512, the processing logic optionally determines a target concentration profile for the film based on the target thickness, target initial concentration, and target final concentration. In some embodiments, the processing logic may also determine a target concentration profile based on the target rate of change of concentration for a particular material. Further details regarding determining the target concentration profile for the film are provided with reference to Figures 6A–7C.

[0060] In block 514, the processing logic provides the target concentration profile as input to the trained machine learning model. In some embodiments, the processing logic also provides one or more process constraints associated with the deposition process as input to the trained machine learning model. In block 516, the processing logic obtains the output of the machine learning model.

[0061] In block 518, the processing logic determines from one or more outputs process recipe data that identifies one or more sets of deposition process settings, and for each set of deposition process settings, a level of confidence that each set of deposition process settings corresponds to a target concentration profile for the film deposited on the substrate. Each set of deposition process settings may include at least a temperature setting for the process chamber, a pressure setting for the process chamber, and flow rate settings (e.g., initial flow rate, final flow rate, ramping rate, etc.) for one or more material precursors of the film deposited on the surface of the substrate (e.g., silicon-containing precursor, boron-containing precursor, etc.). For example, during a process for depositing one or more boron and silicon-containing layers, the set of deposition process settings may include at least a temperature setting and / or pressure setting for the process chamber, and flow rate settings for the boron-based precursor and / or silicon-based precursor of the one or more boron and silicon-containing layers during each instance of the deposition process. In some embodiments, each set of deposition process settings is associated with a specific concentration profile for the film deposited on the surface of the substrate. The processing logic may determine that each set of deposition process settings corresponds to a target concentration by determining that the difference between a specific profile associated with each set of deposition process settings and a target concentration profile for the film deposited on the substrate surface falls below a differential threshold.

[0062] In block 520, the processing logic determines whether the confidence criterion level is satisfied for each of each set of deposition process settings. In response to a determination that the confidence level exceeds the confidence threshold level, the processing logic may determine that the confidence level of each set of deposition process settings satisfies the confidence criterion level. In some embodiments, the confidence levels of multiple sets of deposition process settings may exceed the confidence threshold level. In such embodiments, the processing logic may determine that the confidence criterion level is satisfied for a particular set of deposition process settings that has the highest confidence level exceeding the confidence threshold level. In response to a determination that the confidence criterion level is not satisfied for any of the sets of deposition settings, method 500 terminates. In response to a determination that the confidence criterion level is satisfied for at least one of one or more sets of deposition process settings, the processing logic identifies each set of deposition process settings that satisfies the confidence criterion level.

[0063] In block 522, the processing logic performs one or more operations of the deposition process according to each set of deposition process settings. In some embodiments, the deposition process for a substrate may be associated with an initial set of deposition process settings. The processing logic may modify one or more of the initial process settings to correspond to one or more of the sets of deposition process settings and perform the deposition process according to the modified set of deposition process settings. In some embodiments, the processing logic may send a request to a client device connected to the manufacturing system (e.g., client device 120) to modify one or more initial deposition settings to correspond to one or more deposition settings in each set of deposition process settings. In response to receiving a command from the client device to modify the initial set of deposition settings according to the request, the processing logic may modify the initial set of deposition settings as described earlier.

[0064] Figures 6A and 6C illustrate the deposition of an example film having a specific concentration profile on the surface of a substrate. Figure 6A illustrates a film 620 deposited on the surface of a substrate 302. The film 620 comprises a series of layers formed on the substrate (e.g., layers 620A, 620B, 620C, and 620D). Layer 620A is the first layer of material formed directly on the surface of the substrate 302 (referred to as the proximal layer). Layer 620D is the final layer formed for the film at the end of the deposition process (referred to as the distal layer). Layers 620B and 620C are layers of material formed between the proximal layer 620A and the distal layer 620D. Figure 6B is a graph showing the concentration of a specific material (e.g., boron, silicon) within the film 620 based on the thickness of the film 620. Each layer 620A-D of the film 620 corresponds to a specific thickness of the film 620. For example, the proximal layer 620A corresponds to a thickness of 1 in the film 620, layer 620B corresponds to a thickness of 2, layer 620C corresponds to a thickness of 3, and the distal layer 620D corresponds to a thickness of 4. As illustrated in Figures 6A and 6B, the concentration of a particular material increases linearly with the thickness of the film 620, and lower concentrations of the particular material are present in the proximal layer 620A than in the distal layer 620D.

[0065] In some embodiments, the concentration profile of the film 620 may be a target concentration profile for the film to be deposited on the surface of the substrate 302. As previously described, a user of the manufacturing system (e.g., an operator) may provide data associated with the target concentration profile for the film 620 via a client device. For example, the user may provide data indicating the target thickness of the film 620 (e.g., thickness 4), the initial concentration of a particular material in the film 620 (e.g., the concentration of a particular material in the proximal layer 620A), and the final concentration for a particular material in the film 620 (e.g., the concentration of a particular material in the distal layer 620D). A processing device of the manufacturing system may provide the data associated with the target concentration profile as input to a trained machine learning model. As previously described, the processing device may obtain one or more outputs of the trained machine learning model and from these one or more outputs may identify a set of deposition settings that have a potential for confidence satisfying confidence criteria.

[0066] Figure 6C depicts a graph illustrating an example set of deposition settings for a target concentration profile for a film 620. In some embodiments, the set of deposition settings illustrated in Figure 6C may be a set of deposition settings that satisfy a level of confidence criterion, as previously described. The deposition process for depositing a film having a target concentration profile may start at time T0 and end at time TN. As illustrated in Figure 6C, the flow rate of the precursor of a particular material for film 620 will increase at a nonlinear rate for the length of the deposition process (e.g., T0 to TN) to achieve the target concentration profile for film 620. The graph illustrates, for a particular instance during the deposition process, a flow rate setting for the precursor of the target material (e.g., a boron-based precursor, a silicon-based precursor, etc.) applied during the deposition process to deposit a film having a concentration profile corresponding to the target concentration profile. For example, the graph shows that the initial flow rate of the precursor may be flow rate FR1 to deposit a film having a concentration profile corresponding to the target concentration profile. Between time T0 and time T1, the flow rate of the precursor may increase from flow rate FR1 to flow rate FR2 at a first ramping rate. Between time T1 and time T2, the precursor flow rate may increase from flow rate FR2 to flow rate FR3 at a second ramping rate, and so on. The processing device may perform a deposition process to deposit a film 620 on the surface of the substrate 302 according to the setup illustrated in Figure 6C, thereby achieving a target concentration profile for the film 620.

[0067] Figure 7 depicts a block diagram of an illustrative computer system 700 operating according to one or more embodiments of this disclosure. In alternative embodiments, the machine may be connected to other machines in a local area network (LAN), intranet, extranet, or the internet (e.g., network connection). The machine may operate as a server or client machine in a client-server network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. The machine may be a personal computer (PC), tablet computer, set-top box (STB), personal digital assistant (PDA), mobile phone, web appliance, server, network router, switch or bridge, or any machine capable of executing a set of instructions (sequential or otherwise) that specify the actions to be taken by that machine. Furthermore, although only a single machine is illustrated, the term “machine” shall be deemed to include any set of machines (e.g., computers) that individually or collectively execute a set of instructions (or sets of instructions) to implement any one or more of the methodologies discussed herein. In this embodiment, the computing device 700 may correspond to the system controller 328 in Figure 3, or another processing device of the computer system architecture 100.

[0068] An example computing device 700 includes a processing device 702, main memory 704 (e.g., read-only memory (ROM), flash memory, dynamic random access memory (DRAM), synchronous DRAM (SDRAM), etc.), static memory 706 (e.g., flash memory, static random access memory (SRAM), etc.), and secondary memory (e.g., data storage device 728), which communicate with each other via a bus 708.

[0069] The processing device 702 may represent one or more general-purpose processors, such as a microprocessor, a central processing unit, or the like. More specifically, the processing device 702 may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor implementing another instruction set, or a processor implementing a combination of instruction sets. The processing device 702 may also be one or more special-purpose processing devices, such as an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), a network processor, or the like. The processing device 802 may also be, or include, a system-on-a-chip (SoC), a programmable logic control unit (PLC), or other types of processing devices. The processing device 702 is configured to execute processing logic for carrying out the operations and steps discussed herein.

[0070] The computing device 700 may further include a network interface device 722 for communicating with the network 764. The computing device 800 may also include a video display device 710 (e.g., a liquid crystal display (LCD) or a cathode ray tube (CRT)), an alphanumeric input device 712 (e.g., a keyboard), a cursor control device 714 (e.g., a mouse), and a signal generation device 720 (e.g., a speaker).

[0071] The data storage device 728 may include a machine-readable storage medium (or more specifically, a non-temporary computer-readable storage medium) 724 in which one or more sets of instructions 726 that embody any one or more of the methodologies or functions described herein are stored. A non-temporary storage medium refers to a storage medium other than a carrier wave. The instructions 726 may also reside entirely or at least partially in the main memory 704 and / or in the processing device 702 while they are being executed by the computer device 700, and the main memory 704 and the processing device 702 also constitute a computer-readable storage medium.

[0072] The computer-readable storage medium 724 may also be used to store Model 190 and data used to train Model 190. The computer-readable storage medium 724 may also store a software library containing methods for calling Model 190. Although the computer-readable storage medium 724 is shown as a single medium in exemplary embodiments, the term “computer-readable storage medium” should be understood to include a single or multiple mediums (e.g., centralized or distributed databases, and / or associated caches and servers) that store one or more sets of instructions. The term “computer-readable storage medium” should also be understood to include any medium that has the ability to encode and store a set of instructions for execution by a machine, and to cause a machine to implement any one or more of the methodologies of this disclosure. Accordingly, the term “computer-readable storage medium” should be understood to include, but are not limited to, solid memory, as well as optical and magnetic media.

[0073] The preceding description specifies numerous specific details, such as examples of particular systems, components, and methods, in order to provide a good understanding of some embodiments of the present disclosure. However, it will be apparent to those skilled in the art that at least some embodiments of the present disclosure can be practiced without these specific details. In other cases, well-known components or methods are not described in detail or are presented in simple block diagram form to avoid unnecessarily obscuring the present disclosure. Thus, the specific details specified are merely illustrative. Certain implementations may differ from these illustrative details and may still be intended to be within the scope of the present disclosure.

[0074] Throughout this specification, any reference to “one embodiment” or “a certain embodiment” means that any particular feature, structure, or characteristic described in relation to that embodiment is included in at least one embodiment. Therefore, the appearance of the expression “one embodiment” or “a certain embodiment” in various places throughout this specification does not necessarily all refer to the same embodiment. In addition, the term “or” is intended to mean inclusive “or” rather than exclusive “or.” Where the terms “about” or “approximately” are used herein, this is intended to mean that the nominal values ​​presented are within 10% accuracy.

[0075] The operations of the methods described herein are shown and described in a specific order, but the order of operations of each method may be modified so that certain operations may be performed in reverse order, and as a result, certain operations may be performed at least partially simultaneously with other operations. In another embodiment, the suboperations of an instruction or separate operation may be intermittent and / or alternating.

[0076] It should be understood that the above description is illustrative and not restrictive. Many other embodiments will be obvious to those skilled in the art when reading and understanding the above description. Accordingly, the scope of this disclosure should be determined by reference to the appended claims, together with the entire scope of the equivalents to which such claims are granted.

Claims

1. During the deposition process for a substrate in the process chamber of a manufacturing system, data associated with the target concentration profile for the film deposited on the surface of the substrate is provided as input to a trained machine learning model. Obtaining one or more outputs of the trained machine learning model, wherein each of the outputs includes process recipe data identifying one or more sets of deposition settings, and for each set of deposition settings, a confidence level indicating that each set of deposition settings corresponds to a target concentration profile for the film deposited on the substrate. Process recipe data identifying one or more sets of deposition process settings, and for each set of deposition process settings, determining from one or more outputs the confidence level corresponding to the target concentration profile for the film deposited on the substrate for each set of deposition process settings, Identifying each set of deposition process settings that has a level of confidence that satisfies the level of confidence criteria, A method comprising: identifying each set of the deposition process settings having a level of confidence that satisfies the level of the confidence criterion, and performing one or more operations of the deposition process according to each set of the deposition process settings.

2. Receiving information indicating the target thickness of the film deposited on the surface of the substrate, the target initial concentration for a specific material of the film, and the target final concentration for the specific material of the film, The method according to claim 1, further comprising determining the target concentration profile for the film based on the target thickness, the initial target concentration, and the final target concentration.

3. The method according to claim 1, further comprising providing a set of one or more process constraints associated with the deposition process as additional input to the trained machine learning model.

4. The method according to claim 1, wherein each set of deposition process settings is associated with a concentration profile for the film to be deposited on the surface of the substrate, and in response to a determination that the difference between the concentration profile associated with each set of deposition process settings and the target concentration profile is below a differential threshold, each set of deposition process settings corresponds to the target concentration.

5. The method according to claim 1, wherein the deposition process for the substrate is associated with an initial set of deposition process settings, and performing one or more operations of the deposition process according to each set of the deposition process settings includes modifying one or more of the initial sets of deposition process settings to correspond to one or more of the respective sets of deposition process settings.

6. Sending a request to a client device connected to the manufacturing system to modify one or more of the initial sets of deposition process settings to correspond to one or more of the sets of deposition process settings, The method of claim 5, further comprising receiving an instruction from the client device to modify one or more of the initial sets of deposition process settings to correspond to one or more of the respective sets of deposition process settings, wherein one or more of the initial sets of deposition process settings are updated in accordance with the received instruction.

7. The method according to claim 1, wherein each set of deposition process settings includes at least one of a temperature setting for the process chamber, a pressure setting for the process chamber, or a flow rate setting for the precursor of one or more materials of the film to be deposited on the surface of the substrate.

8. The method according to claim 7, wherein the precursor of one or more materials comprises at least one of a silicon-containing precursor or a boron-containing precursor.

9. The method according to claim 1, wherein the confidence level of each set of the deposition process settings satisfies the confidence criterion level in response to a determination that the confidence level exceeds a confidence threshold level.

10. It is a system, Memory and A processing device coupled to the memory, A system comprising: a non-temporary computer-readable storage medium coupled to the memory and the processing device, the non-temporary computer-readable storage medium including an instruction causing the processing device to perform the method according to any one of claims 1 to 9.

11. The system according to claim 10, wherein the deposition process performed on the current substrate and the previous deposition process previously performed on the previous substrate are each performed in a specific process chamber of the manufacturing system.

12. The system according to claim 10, wherein the deposition process performed on the current substrate is carried out in a first process chamber of the manufacturing system, and a previous deposition process previously performed on the current substrate is carried out in a second process chamber of the manufacturing system.

Images