Method and mechanism for adjusting film deposition parameters during substrate manufacturing

Abstract

An electronic device manufacturing system is capable of obtaining metrology data associated with a deposition process performed on a substrate in accordance with a process recipe, where the deposition process produces a plurality of layers on a surface of the substrate. The manufacturing system can further obtain an expected profile associated with the process recipe, where the expected profile includes a plurality of values indicative of a desired thickness of the plurality of layers of the process recipe. The manufacturing system can further generate a correction profile based on the metrology data and the expected profile, where the correction profile includes a deposition time offset value for at least one layer of the plurality of layers. The manufacturing system can further generate an updated process recipe by applying the correction profile to the process recipe, and cause a deposition step to be performed on the substrate in accordance with the updated process recipe.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to electronic components, and more specifically, to methods and mechanisms for adjusting film deposition parameters during substrate manufacturing. BACKGROUND

[0002] Products can be manufactured by performing one or more manufacturing processes using manufacturing equipment. For example, semiconductor manufacturing equipment can be used to manufacture semiconductor devices (e.g., substrates) via semiconductor manufacturing processes. Manufacturing equipment can deposit multiple layers of films on a surface of a substrate according to a process recipe, and can perform etching processes to form complex patterns in the deposited films. For example, manufacturing equipment can perform a chemical vapor deposition (CVD) process to deposit a replacement layer on a substrate. During such substrate manufacturing processes, the thickness of each layer can vary due to changing deposition parameters and variations in process chamber conditions (e.g., accumulation of contaminants, erosion of certain components, etc.). These variations are typically compensated for by manually increasing or decreasing the deposition time of subsequent layers to maintain a desired total thickness of the film stack. However, such processes are prone to error and can result in manufacturing delays and defective products. Accordingly, there is a need for a system that is capable of automatically adjusting film deposition parameters. SUMMARY

[0003] The following is a simplified summary of the disclosure to provide a basic understanding of some aspects of the disclosure. This summary is not an extensive overview of the disclosure. Neither is it intended to identify key or critical elements of the disclosure or to delineate any scope of the particular implementations of the disclosure or any scope of the claims. The sole purpose of the simplified summary is to present some concepts of the disclosure in a simplified form as a prelude to the more detailed description presented later.

[0004] In aspects of the disclosure, an electronic device manufacturing system is capable of obtaining metrology data associated with a deposition process performed on a substrate according to a process recipe, wherein the deposition process produces a plurality of layers on a surface of the substrate. The manufacturing system can further obtain an expected profile associated with the process recipe, wherein the expected profile includes a plurality of values indicative of a desired thickness of the plurality of layers of the process recipe. The manufacturing system can further generate a correction profile based on the metrology data and the expected profile, wherein the correction profile includes a deposition time offset value for at least one layer of the plurality of layers. The manufacturing system can further generate an updated process recipe by applying the correction profile to the process recipe, and cause a deposition step to be performed on the substrate according to the updated process recipe.

[0005] Further aspects of the disclosure include methods in accordance with any of the aspects or embodiments described herein.

[0006] Further aspects of the present disclosure include a non-transitory computer- readable storage medium comprising instructions that, when executed by a processing device operably coupled to a memory, perform operations in accordance with any of the aspects or embodiments described herein. BRIEF DESCRIPTION OF DRAWINGS

[0007] In the drawings accompanying figures of the drawing set, the present disclosure is illustrated by way of example and not limitation, in which like references indicate similar elements.

[0008] Figure 1 is a block diagram illustrating an example system architecture, in accordance with certain embodiments.

[0009] Figure 2 is a top view schematic of an example manufacturing system, in accordance with certain embodiments.

[0010] Figure 3 is a cross-sectional schematic side view of an example processing chamber of an example manufacturing system, in accordance with certain embodiments.

[0011] Figure 4 is a flowchart of a method for adjusting a process recipe based on a correction profile, in accordance with certain embodiments.

[0012] Figure 5 is a flowchart of a method for determining a correction profile of a process recipe using a curve fitting method, in accordance with certain embodiments.

[0013] Figure 6 is a table illustrating an example correction profile, in accordance with certain embodiments.

[0014] Figures 7A-7B is a chart illustrating metrology data from a deposition process, in accordance with aspects of the present disclosure.

[0015] Figure 8 is a block diagram illustrating a computer system, in accordance with certain embodiments. DETAILED DESCRIPTION

[0016] Described herein are techniques related to methods and mechanisms for adjusting film deposition parameters during substrate manufacturing. A film can be deposited on a surface of a substrate during a deposition process (e.g., a deposition (CVD) process, an atomic layer deposition (ALD) process, etc.) that can be performed in a processing chamber of a manufacturing system. For example, in a CVD process, a substrate is exposed to one or more precursors that react on the substrate surface to produce a desired deposit. The film can include one or more layers of material formed during the deposition process, and each layer can include a particular thickness gradient (e.g., a variation in thickness along the layer of the deposited film). For example, a first layer can be formed directly on the surface of the substrate (referred to as a near layer or a proximal end of the film) and have a first thickness. After the first layer is formed on the surface of the substrate, a second layer having a second thickness can be formed on the first layer. This process continues until the deposition process is complete and a final layer of the film is formed (referred to as a far layer or a distal end of the film). The film can include alternating layers of different materials. For example, the film can include alternating oxide and nitride layers (an oxide-nitride-oxide-nitride stack or an ONON stack), alternating oxide and polysilicon layers (an oxide-polysilicon-oxide-polysilicon stack or an OPOP stack), etc. Each set of alternating layers can be referred to as a cycle. For example, the film can include 40 cycles (e.g., 40 sets of oxide-nitride layers).

[0017] The film can be subjected to, for example, an etching process to form a pattern on the surface of the substrate, a chemical mechanical polishing (CMP) process to smooth the surface of the film, or any other process required to manufacture a finished substrate. The etching process can include exposing a high-energy process gas (e.g., a plasma) to the surface of the sample to decompose material at the surface, which can then be removed by a vacuum system.

[0018] The processing chamber can perform each substrate manufacturing process (e.g., a deposition process, an etching process, a polishing process, etc.) according to a process recipe. The process recipe defines a specific set of operations to be performed on the substrate during processing, and can include one or more settings associated with each operation. For example, a deposition process recipe can include a temperature setting for the processing chamber, a pressure setting for the processing chamber, a flow rate setting for a precursor of a material included in the film deposited on the surface of the substrate, etc. Thus, the thickness of each film layer can be related to these processing chamber settings.

[0019] Generally, a processing recipe includes a set of loops (e.g., 40 loops), where the thickness of the layers of some loops can be different than the thickness of the layers of other loops. For example, a film stack can include 40 oxide-nitride loops (e.g., 80 layers, 40 layers of oxide and 40 layers of nitride alternating), where the first loop of the film stack has an oxide layer of a first thickness and a nitride layer of a second thickness, followed by the next nine loops of the film stack having an oxide layer of a third thickness and a nitride layer of a fourth thickness, and the last 30 loops of the film stack having an oxide layer of a fifth thickness and a nitride layer of a sixth thickness.

[0020] During this substrate manufacturing process, the thickness of each loop can vary due to changing deposition parameters and variations in processing chamber conditions (e.g., accumulation of contaminants, erosion of certain components, etc.). Variations in layer thicknesses can cause the gas distribution plate to be closer or further from the surface of the substrate, affecting plasma flow and / or temperature, and causing further distortion of the film. In some manufacturing systems, these variations are compensated for by manually increasing or decreasing the deposition time of subsequent loops to maintain the desired total thickness of the film stack. For example, if the thickness of the first loop is greater than the thickness required by the processing recipe, a technician can manually decrease the deposition time of the second loop in the processing recipe to produce a thinner loop than required by the processing recipe. This manual process of calculating a “step time offset” for each loop and inputting the offset into a table can be a time-consuming and error-prone process, resulting in manufacturing delays, lost output, and / or defects in the film.

[0021] Aspects and implementations of the present disclosure address these and other drawbacks of the prior art by generating a correction profile to adjust film deposition parameters during substrate manufacturing. Specifically, a metrology apparatus can generate metrology data for a substrate prior to, during, and / or after a manufacturing process (e.g., a deposition process) based on a processing recipe. The metrology apparatus can use the metrology data to generate a thickness profile indicating one or more thickness values across a surface of the substrate. The thickness profile can indicate the thickness of a film on the substrate. The metrology apparatus can generate the thickness profile at different times during the manufacturing process. For example, the metrology apparatus can generate metrology data after each layer of a film stack is deposited, after each loop of a film stack is deposited, etc.

[0022] The manufacturing system can obtain an expected profile for the process recipe. The expected profile can include values indicative of a desired thickness of the film, a desired thickness of one or more layers of the film, and / or a desired thickness of one or more cycles of the film. Using the thickness profile and the expected profile, the manufacturing system can generate a correction profile. The correction profile can include one or more adjustments or offsets (e.g., correction actions) to be applied to parameters of the process recipe or the processing chamber. For example, the correction profile can include adjustments to deposition time, to temperature settings of the processing chamber, to pressure settings of the processing chamber, to flow rate settings for precursors, to power supplied to the processing chamber, to ratios of two or more settings, etc., for a particular layer or cycle of the process recipe. In some embodiments, the manufacturing system can generate the correction profile by using one or more formulas or mathematical models. For example, the processing logic can use data values from the expected profile and / or the thickness profile to generate a curve fitting model, and then use the curve fitting model to determine one or more offset time values for one or more steps of the current deposition process. The offsets can be applied to each deposition step to adjust the layer thickness of the step so that the film thickness at the end of the deposition is the same as the film thickness indicated by the process recipe.

[0023] In some embodiments, the processing logic can generate the correction profile using a machine learning model or using an inference engine. The manufacturing system can then use the correction profile to adjust the process recipe parameters (e.g., deposition time) for one or more steps of the process recipe (e.g., one or more layers or cycles of the process recipe). This allows the manufacturing system to generate adjustments for particular processing steps of the process recipe.

[0024] Aspects of the disclosure result in technical advantages of significantly reducing the time required to perform optimization of parameters of a process recipe. Aspects of the disclosure further result in technical advantages of significantly reducing the time required to detect problems or faults experienced by a substrate during a manufacturing process, as well as improving energy consumption, etc. The disclosure can also result in generating diagnostic data and performing correction actions to avoid inconsistent and abnormal products, as well as unplanned user time or downtime.

[0025] Figure 1 An illustrative computer system architecture 100 according to aspects of the disclosure is depicted. In some embodiments, the computer system architecture 100 can be included as a manufacturing system for processing a substrate, such as a semiconductor wafer, a flat panel display, etc. Figure 3The computer system architecture 100 includes a client device 120, a manufacturing equipment 124, a metrology equipment 128, a prediction server 112 (e.g., for generating prediction data, for providing model adaptation, for using a knowledge base, etc.), and a data store 140. The prediction server 112 can be part of a prediction system 110. The prediction system 110 can further include server machines 170 and 180. The manufacturing equipment 124 can include a sensor 126 configured to capture data of a substrate being processed at a manufacturing system. In some embodiments, the manufacturing equipment 124 and the sensor 126 can be part of a sensor system including a sensor server (e.g., a field service server (FSS) at a manufacturing facility) and a sensor identifier reader (e.g., a front opening unified pod (FOUP) radio frequency identification (RFID) reader for the sensor system). In some embodiments, the metrology equipment 128 can be part of a metrology system including 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).

[0026] The manufacturing equipment 124 can produce products, such as electronic devices, according to a recipe or over a period of time performing runs. The manufacturing equipment 124 can include a processing chamber, such as the processing chamber 400 described with reference to Figure 4 The manufacturing equipment 124 can perform a process on a substrate (e.g., a wafer, etc.) at a processing chamber. Examples of substrate processing include a deposition process to deposit one or more layers of film on a surface of a substrate, an etch process to form a pattern on a surface of a substrate, etc. The manufacturing equipment 124 can perform each process according to a process recipe. A process recipe defines a specific set of operations to be performed on a substrate during processing and can include one or more settings associated with each operation. For example, a deposition process recipe can include a temperature setting for a processing chamber, a pressure setting for a processing chamber, a flow rate setting for a precursor of a material included in a film deposited on a surface of a substrate, etc.

[0027] In some embodiments, the manufacturing equipment 124 includes sensors 126 configured to generate data associated with substrates processed at the manufacturing system 100. For example, a processing chamber can include one or more sensors configured to generate spectral or non-spectral data associated with a substrate before, during, and / or after performing a process (e.g., a deposition process) on the substrate. In some embodiments, the spectral data generated by the sensors 126 can be indicative of a concentration of one or more materials deposited on a surface of a substrate. The sensors 126 configured to generate spectral data associated with a substrate can include reflectometer sensors, ellipsometer sensors, thermographic sensors, capacitance sensors, etc. The sensors 126 configured to generate non-spectral data associated with a substrate can include temperature sensors, pressure sensors, flow rate sensors, voltage sensors, etc. Further details regarding the manufacturing equipment 124 are described with reference to Figure 3 and Figure 4 provided.

[0028] In some embodiments, the sensors 126 provide sensor data (e.g., sensor values, characteristics, trace data) associated with the manufacturing equipment 124 (e.g., associated with manufacturing respective products, e.g., wafers, by the manufacturing equipment 124). The manufacturing equipment 124 can produce products according to a recipe or by performing a run over a period of time. Sensor data received over a period of time (e.g., corresponding to at least a portion of a recipe or a run) can be referred to as trace data received over time from different sensors 126 (e.g., historical trace data, current trace data, etc.). The sensor data can include values for one or more of temperature (e.g., heater temperature), spacing (SP), pressure, high frequency radio frequency (HFRF), voltage of electrostatic chuck (ESC), current, material flow, power, voltage, etc. The sensor data can be associated with or indicative of manufacturing parameters, such as hardware parameters, e.g., settings or components of the manufacturing equipment 124 (e.g., dimensions, types, etc.), or processing parameters of the manufacturing equipment 124. The sensor data can be provided as the manufacturing equipment 124 performs a manufacturing process (e.g., equipment readings while processing a product). The sensor data can be different for each substrate.

[0029] Metrology apparatus 128 can provide metrology data associated with substrates processed by fabrication apparatus 124. Metrology data can include values of film property data (e.g., wafer spatial film properties), dimensions (e.g., thickness, height, etc.), dielectric constant, dopant concentration, density, defects, etc. In some embodiments, metrology data can 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 a substrate, critical dimension uniformity across a surface of a substrate, edge placement error, etc.). Metrology data can be of a finished or semi-finished product. Metrology data can be different for each substrate. Metrology data can be generated using, for example, reflectometry techniques, ellipsometry techniques, TEM techniques, etc.

[0030] In some embodiments, metrology apparatus 128 can be included as part of fabrication apparatus 124. For example, metrology apparatus 128 can be included inside or coupled to a processing chamber and configured to generate metrology data of a substrate before, during, and / or after processing (e.g., deposition processing, etch processing, etc.) while the substrate is left in the processing chamber. In some cases, metrology apparatus 128 can be referred to as an in-situ metrology apparatus. In another example, metrology apparatus 128 can be coupled to another station of fabrication apparatus 124. For example, metrology apparatus can be coupled to a transfer chamber, such as transfer chamber 310, a load lock, such as load lock 320, or a factory interface, such as factory interface 306. Figure 3

[0031] ​Client devices 120 can include computing devices such as personal computers (PCs), laptop computers, mobile phones, smart phones, tablet computers, netbook computers, networked televisions ("smart televisions"), networked media players (e.g., Blu-ray players), set-top boxes, over-the-top (OTT) streaming devices, dongles, and the like. In some embodiments, metrology data can be received from client devices 120. Client devices 120 can display a graphical user interface (GUI) in which the GUI enables a user to provide metrology measurements of a substrate processed at a manufacturing system as input. Client devices 120 can include a corrective action component 122. Corrective action component 122 can receive user input indicative of an association with manufacturing equipment 124 (e.g., via a graphical user interface (GUI) displayed by client devices 120. In some embodiments, corrective action component 122 transmits the indication to prediction system 110, receives output (e.g., prediction data) from prediction system 110, determines a corrective action based on the output, and causes the corrective action to be implemented. In some embodiments, corrective action component 122 receives an indication of a corrective action from prediction system 110 and causes the corrective action to be implemented. Each client device 120 can include an operating system that allows a user to one or more of generate, view, or edit data (e.g., indications associated with manufacturing equipment 124, corrective actions associated with manufacturing equipment 124, and the like).

[0032] Data storage 140 can be a memory (e.g., random access memory), a drive (e.g., a hard disk drive, a flash drive), a database system, or another type of component or device capable of storing data. Data storage 140 can include multiple storage components (e.g., multiple drives or multiple databases) that can span multiple computing devices (e.g., multiple server computers). Data storage 140 can store data associated with processing substrates at manufacturing equipment 124. For example, data storage 140 can store data (referred to as processing data) collected by sensors 126 at manufacturing equipment 124 before, during, or after processing of a substrate. Processing data can refer to historical processing data (e.g., processing data generated for a previous substrate processed at a manufacturing system) and / or current processing data (e.g., processing data generated for a current substrate processed at a manufacturing system). Data storage can also store spectral data or non-spectral data associated with a portion of a substrate processed at manufacturing equipment 124. Spectral data can include historical spectral data and / or current spectral data.

[0033] The data store 140 can also store contextual data associated with one or more substrates processed at the manufacturing system. The contextual data can include recipe name, recipe step number, preventative maintenance indicator, operator, etc. The contextual data can refer to historical contextual data (e.g., contextual data associated with a previous process performed on a previous substrate) and / or current processing data (e.g., contextual data associated with a current process or a future process to be performed on a previous substrate). The contextual data can further include identifying sensors associated with a particular subsystem of the processing chamber.

[0034] The data store 140 can also store task data. The task data can include one or more sets of operations to be performed on a substrate during a deposition process, and can include one or more settings associated with each operation. For example, the task data for a deposition process can include a temperature setting for the processing chamber, a pressure setting for the processing chamber, a flow rate setting for a precursor of a material of a film deposited on the substrate, etc. In another example, the task data can include controlling the pressure at defined pressure points of a flow value. The task data can refer to historical task data (e.g., task data associated with a previous process performed on a previous substrate) and / or current task data (e.g., task data associated with a current process or a future process to be performed on a substrate).

[0035] In some embodiments, the data store 140 can store an expected profile, a thickness profile, and a correction profile. The expected profile can include one or more data points associated with an expected film profile expected to be produced by a certain process recipe. In some embodiments, the expected profile can include a desired thickness of a film, a desired thickness of one or more layers of a film, and / or a desired thickness of one or more cycles of a film, etc. The thickness profile includes one or more data points associated with a current film profile produced by the manufacturing apparatus 124. For example, the thickness profile can include a measured thickness of a film, a measured thickness of one or more layers of a film, and / or a measured thickness of one or more cycles of a film, etc. The thickness profile can be measured using the metrology apparatus 128. The correction profile can include one or more adjustments or offsets to be applied to parameters of a processing chamber or a process recipe. For example, the correction profile can include adjustments to a deposition time of a film layer and / or cycle, a temperature setting of a processing chamber, a pressure setting of a processing chamber, a flow rate setting of a precursor of a material included in a film deposited on a substrate surface, adjustments to power provided to a processing chamber, adjustments to a ratio of two or more settings, etc. The correction profile can be generated to achieve the expected profile by comparing the expected profile (e.g., a thickness profile expected to be produced by a process recipe) and determining adjustments to parameters of a process recipe using an algorithm, a known failure mode library, etc. The correction profile can be applied to steps related to a deposition process, an etch process, etc.

[0036] In some embodiments, the data store 140 can be configured to store data that is not accessible to users of the manufacturing system. For example, users (e.g., operators) of the manufacturing system can not have access to process data, spectral data, background data, etc. obtained for substrates processed at the manufacturing system. In some embodiments, users of the manufacturing system can not have access to all data stored at the data store 140. In other or similar embodiments, a portion of the data stored at the data store 140 can be inaccessible to users, while another portion of the data stored at the data store 140 can be accessible to users. In some embodiments, one or more portions of the data stored at the data store 140 can be encrypted using an encryption mechanism unknown to the users (e.g., encrypting the data using a private encryption key). In other or similar embodiments, the data store 140 can include multiple data stores, where data that is not accessible to users is stored in one or more first data stores, and data that is accessible to users is stored in one or more second data stores.

[0037] In some embodiments, the data store 140 can be configured to store data associated with known failure modes. A failure mode can be one or more values (e.g., vectors, scalars, etc.) associated with one or more issues or failures associated with a processing chamber subsystem. In some embodiments, a failure mode can be associated with a corrective action. For example, a failure mode can include a parameter adjustment step to correct an issue or failure indicated by the failure mode. For example, the prediction system can compare a determined failure mode to a library of known failure modes to determine a type of failure experienced by a subsystem, a cause of the failure, a recommended corrective action to correct the failure, etc.

[0038] In some embodiments, the prediction system 110 includes a prediction server 112, a server machine 170, and a server machine 180. Each of the prediction server 112, the server machine 170, and the server machine 180 can include one or more computing devices, such as a rack server, a router computer, a server computer, a personal computer, a mainframe computer, a laptop computer, a tablet computer, a desktop computer, a graphics processing unit (GPU), an accelerator-specific application-specific integrated circuit (ASIC) (e.g., a tensor processing unit (TPU)), etc.

[0039] The server machine 170 includes a training set generator 172 that is capable of generating training data sets (e.g., a set of data inputs and a set of target outputs) to train, validate, and / or test a machine learning model 190. The machine learning model 190 can be any algorithmic model capable of learning from data. In some embodiments, the data set generator 172 can divide the training data into training sets, validation sets, and test sets. In some embodiments, the prediction system 110 generates multiple sets of training data.

[0040] The server machine 180 can include a training engine 182, a validation engine 184, a selection engine 185, and / or a testing engine 186. An engine can refer to hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, processing device, etc.), software (e.g., instructions run on a processing device, general purpose computer system, or a dedicated machine), firmware, microcode, or a combination thereof. The training engine 182 is capable of training one or more machine learning models 190. A machine learning model 190 can refer to a model artifact established by the training engine 182 using training data (also referred to herein as a training set) that includes training inputs and corresponding target outputs (correct answers for the respective training inputs). The training engine 182 can find patterns in the training data that map training inputs to target outputs (answers to be predicted) and provide a machine learning model 190 that captures these patterns. The machine learning model 190 can use one or more of statistical modeling, support vector machines (SVM), Radial Basis Function (RBF), clustering, supervised machine learning, semi-supervised machine learning, unsupervised machine learning, k-Nearest Neighbors algorithm (k-NN), linear regression, random forest, neural networks (e.g., artificial neural networks), etc.

[0041] One type of machine learning model that can be used to perform some or all of the tasks described above is an artificial neural network, such as a deep neural network. Artificial neural networks generally include a feature representation component with a classifier or regression layer that maps features to a desired output space. For example, a convolutional neural network (CNN) hosts multiple layers of convolutional filters. Pooling is performed at lower layers, and can address non-linearities, with a typically attached multi-layer perceptron at the top of the lower layers mapping top-level features extracted by the convolutional layers to a decision (e.g., a classification output). Deep learning is a class of machine learning algorithms that uses a cascade of multiple nonlinear processing units to extract and transform features from input data. Each successive layer uses the output from the previous layer as input. Deep neural networks can learn in a supervised (e.g., classification) and / or unsupervised (e.g., pattern analysis) manner. Deep neural networks include a hierarchy of layers, where different layers learn different levels of representation corresponding to different levels of abstraction. In deep learning, each level learns to transform its input data into a slightly more abstract and composite representation. For example, in plasma processing adjustments, the raw input can be a processing result profile (e.g., a thickness profile indicating one or more thickness values across a surface of a substrate); a second layer can constitute feature data associated with states of one or more regions of a controlled component of a plasma processing system (e.g., orientation of a region, plasma exposure duration, etc.); a third layer can include a starting recipe (e.g., a recipe used as a starting point for a decision update of a processing recipe that processes a substrate to produce a processing result that meets a threshold criterion). It should be noted that deep learning processes can learn on their own which features to place in which level. The “depth” in “deep learning” refers to the number of layers of data transformation. More precisely, deep learning systems have a considerable depth of credit assignment paths (CAPs). A CAP is a chain of transformations from input to output. A CAP describes a potential causal relationship between input and output. For feedforward neural networks, the depth of a CAP can be the depth of the network, and can be the number of hidden layers plus one. For recurrent neural networks, where a signal can propagate through a layer more than once, the CAP depth is potentially infinite.

[0042] In one embodiment, the one or more machine learning models is a recurrent neural network (RNN). An RNN is a type of neural network that includes a memory that enables the neural network to capture temporal dependencies. An RNN is capable of learning an input-output mapping that depends on both current and past inputs. An RNN will process past and future flow rate measurements and make a prediction based on this sequential metering information. The RNN can be trained using a training data set to produce a fixed number of outputs (e.g., a decision set of substrate processing rates, a decision to modify a substrate processing recipe). One type of RNN that can be used is a long short-term memory (LSTM) neural network.

[0043] Training of a neural network can be achieved in a supervised learning fashion, involving feeding a training dataset consisting of label inputs through the network, observing its output, defining an error (by measuring the difference between the output and the label values), and adjusting the weights of the network at all its layers and nodes using techniques such as deep gradient descent and backpropagation to minimize the error. In many applications, repeating this process over many label inputs in the training dataset results in a network that can produce correct outputs when the input is different from the inputs present in the training dataset.

[0044] A training dataset comprising hundreds, thousands, tens of thousands, hundreds of thousands, or more of sensor data and / or processing result data (e.g., metrology data such as one or more thickness profiles associated with the sensor data) can be used to form the training dataset.

[0045] To implement the training, the processing logic can input the training dataset into one or more untrained machine learning models. The machine learning models can be initialized prior to inputting the first input into the machine learning models. The processing logic trains the untrained machine learning models based on the training dataset to produce one or more trained machine learning models that perform various operations as described above. The training can be performed by inputting one or more sensor data into the machine learning models at a time.

[0046] A machine learning model processes inputs to produce outputs. An artificial neural network includes an input layer composed of values in data points. The next layer is called a hidden layer, with each node of the hidden layer receiving one or more input values. Each node contains parameters (e.g., weights) applied to the input values. Thus, each node essentially inputs the input values into a multivariable function (e.g., a non-linear mathematical transformation) to produce an output value. The next layer can be another hidden layer or an output layer. In either case, the nodes of the next layer receive the output values from the nodes of the previous layer, and each node applies weights to these values and then produces its own output value. This can be performed at each layer. The last layer is an output layer, with one node for each class, prediction, and / or output that the machine learning model can produce.

[0047] Accordingly, the output can include one or more predictions or inferences. For example, the output predictions or inferences can include one or more predictions of film buildup on a chamber component, corrosion of a chamber component, predicted failure of a chamber component, etc. The processing logic determines an error (i.e., a classification error) based on a difference between the output of the machine learning model (e.g., the prediction or inference) and the target label associated with the input training data. The processing logic adjusts the weights of one or more nodes in the machine learning model according to the error. An error term or delta can be determined for each node in the artificial neural network. From this error, the artificial neural network adjusts one or more of its parameters (weights of one or more inputs to a node) of one or more of its nodes. The parameters can be updated in a backpropagated manner, such that nodes of the highest layer are updated first, then nodes of the next layer, and so on. The artificial neural network includes multiple layers of "neurons," where each layer receives as input values from neurons of a previous layer. The parameters of each neuron include weights associated with values received from each neuron of the previous layer. Accordingly, adjusting the parameters can include adjusting the weights assigned to each input of one or more neurons of one or more layers in the artificial neural network.

[0048] After one or more rounds of training, the processing logic can determine whether a stopping criterion has been met. The stopping criterion can be a target level of accuracy, a target number of images from the training data set that have been processed, a target amount of change in the parameters of one or more previous data points, a combination thereof, and / or other criteria. In one embodiment, the stopping criterion is met when at least a minimum number of data points have been processed and at least a threshold accuracy has been reached. The threshold accuracy can be, for example, 70%, 80%, or 90% accuracy. In one embodiment, the stopping criterion is met if the accuracy of the machine learning model has stopped improving. If the stopping criterion has not been met, further training is performed. If the stopping criterion is met, the training can be complete. Once the machine learning model is trained, a held-out portion of the training data set can be used to test the model.

[0049] Once one or more trained machine learning models 190 are generated, they can be stored in the prediction server 112 as the prediction component 114 or as a component of the prediction component 114.

[0050] The validation engine 184 can validate the machine learning models 190 using the corresponding feature sets of the validation sets from the training set generator 172. Once the model parameters are optimized, model validation can be performed to determine whether the model has improved and to determine the current accuracy of the deep learning model. The validation engine 184 can determine the accuracy of the machine learning models 190 based on the respective feature sets of the validation sets. The validation engine 184 can discard the trained machine learning models 190 that have accuracy that does not satisfy a threshold accuracy. In some embodiments, the selection engine 185 can select the trained machine learning models 190 that have accuracy that satisfies the threshold accuracy. In some embodiments, the selection engine 185 can select the trained machine learning models 190 that have the highest accuracy among the trained machine learning models 190.

[0051] The testing engine 186 can test the trained machine learning models 190 using the corresponding feature sets of the test sets from the data set generator 172. For example, a first trained machine learning model 190 that is trained using a first set of features of the training sets can be tested using a first set of features of the test sets. The testing engine 186 can determine the trained machine learning model 190 that has the highest accuracy among all the trained machine learning models based on the test sets.

[0052] As described in detail below, the prediction server 112 includes a prediction component 114 that can provide for generating a correction profile using one or more formulas, and / or running a trained machine learning model 190 on current sensor data inputs to obtain one or more outputs indicative of correction or adjustment data (e.g., deposition time adjustment data for each layer and / or cycle of a process recipe).

[0053] The client devices 120, the manufacturing equipment 124, the sensors 126, the metrology equipment 128, the prediction server 112, the data store 140, the server machines 170, and the server machines 180 can be coupled to each other via a network 130. In some embodiments, the network 130 is a public network that provides access to the prediction server 112, the data store 140, and other publicly available computing devices for the client devices 120. In some embodiments, the network 130 is a private network that provides access to the manufacturing equipment 124, the metrology equipment 128, the data store 140, and other privately available computing devices for the client devices 120. The network 130 can 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.

[0054] It should be noted that in some other implementations, the functionality of server machines 170 and 180 and prediction server 112 can be provided by a fewer number of machines. For example, in some embodiments, server machines 170 and 180 can be integrated into a single machine, and in some other or similar embodiments, server machines 170 and 180 and prediction server 112 can be integrated into a single machine.

[0055] Generally speaking, functionality described in one implementation as being performed by server machine 170, server machine 180, and / or prediction server 112 can also be performed on client device 120. Moreover, functionality attributed to a particular component can be performed by different or multiple components operating together.

[0056] In embodiments, a "user" can be represented as a single individual. However, other embodiments of the present disclosure encompass a "user" as an entity controlled by multiple users and / or automated sources. For example, a group of individual users that collectively act as a group of administrators can be considered a "user."

[0057] In some embodiments, a manufacturing system can include more than one processing chamber. For example, Figure 2 Example manufacturing system 200 shows multiple processing chambers 214, 216, 218. It should be noted that in some embodiments, the data obtained for training a machine learning model and the data collected to provide as input to a machine learning model can be associated with the same processing chamber of a manufacturing system. In other or similar embodiments, the data obtained for training a machine learning model and the data collected to provide as input to a machine learning model can be associated with different processing chambers of a manufacturing system. In other or similar embodiments, the data obtained for training a machine learning model can be associated with processing chambers of a first manufacturing system, and the data collected to provide as input to a machine learning model can be associated with processing chambers of a second manufacturing system.

[0058] Figure 2 is a top view schematic of an example manufacturing system 200 according to aspects of the present disclosure. Manufacturing system 200 can perform one or more processes on a substrate 202. Substrate 202 can be any suitable rigid, fixed-size planar article, such as a silicon-containing disc or wafer suitable for manufacturing electronic devices or circuit components thereon, a patterned wafer, a glass plate, etc.

[0059] The manufacturing system 200 can include a process tool 204 and a factory interface 206 coupled to the process tool 204. The process tool 204 can include a housing 208 having a transfer chamber 210 therein. The transfer chamber 210 can include one or more process chambers (also referred to as process chambers) 214, 216, 218 arranged about and coupled thereto. The process chambers 214, 216, 218 can be coupled to the transfer chamber 210 by respective ports, such as slit valves or the like. The transfer chamber 210 can also include a transfer chamber robot 212 configured to transfer the substrate 202 between the process chambers 214, 216, 218, a load lock 220, or the like. The transfer chamber robot 212 can include one or more arms, with each arm including one or more end effectors at an end of each arm. The end effectors can be configured to handle particular objects, such as wafers, sensor disks, sensor tools, or the like.

[0060] The process chambers 214, 216, 218 can be adapted to perform any number of processes on the substrate 202. The same or different substrate processes can be performed in each of the process chambers 214, 216, 218. The substrate processes can include atomic layer deposition (ALD), physical vapor deposition (PVD), chemical vapor deposition (CVD), etching, annealing, curing, pre-cleaning, metal or metal oxide removal, or the like. Other processes can be performed on the substrate therein. The process chambers 214, 216, 218 can each include one or more sensors configured to capture data of the substrate 202 before, after, or during the substrate process. For example, the one or more sensors can be configured to capture spectral and / or non-spectral data of a portion of the substrate 202 during the substrate process. In other or similar embodiments, the one or more sensors can be configured to capture data related to an environment within the process chambers 214, 216, 218 before, after, or during the substrate process. For example, the one or more sensors can be configured to capture data associated with a temperature, a pressure, a gas concentration, or the like of the environment within the process chambers 214, 216, 218 during the substrate process.

[0061] A load lock 220 can also be coupled to the housing 208 and the transfer chamber 210. The load lock 220 can be configured to couple with the transfer chamber 210 on one side and with the factory interface 206. The load lock 220 can have an atmosphere that is controlled, which in some embodiments can change from a vacuum environment, in which substrates can be transferred to and from the transfer chamber 210, to an inert gas environment at or near atmospheric pressure, in which substrates can be transferred to and from the factory interface 206. The factory interface 206 can be any suitable enclosure, such as an equipment front end module (EFEM). The factory interface 206 can be configured to receive substrates 202 from substrate carriers 222 (e.g., front opening unified pods (FOUPs)) that are docked at various load ports 224 of the factory interface 206. A factory interface robot 226 (shown in dashed line) can be configured to transfer substrates 202 between the carriers (also referred to as containers) 222 and the load lock 220. The carriers 222 can be substrate storage carriers or replacement part storage carriers.

[0062] The manufacturing system 200 can also be connected to a client device (not shown) that is configured to provide information to a user (e.g., an operator) regarding the manufacturing system 200. In some embodiments, the client device can provide information to a user of the manufacturing system 200 via one or more graphical user interfaces (GUIs). For example, the client device can provide information regarding a target thickness profile of a film to be deposited on a surface of a substrate 202 during a deposition process performed at the processing chambers 214, 216, 218 via a GUI. In accordance with the embodiments described herein, the client device can also provide information regarding modifications to a processing recipe in view of respective sets of deposition settings that are predicted to correspond to the target profile.

[0063] The manufacturing system 200 can also include a system controller 228. The system controller 228 can be and / or include a computing device such as a personal computer, a server computer, a programmable logic controller (PLC), a microcontroller, or the like. The system controller 228 can include one or more processing devices, which can be general purpose processing devices such as microprocessors, central processing units, or the like. More particularly, the processing devices can be complex instruction set computing (CISC) microprocessors, reduced instruction set computing (RISC) microprocessors, very long instruction word (VLIW) microprocessors, or processors implementing other instruction sets, or processors implementing a combination of instruction sets. The processing devices can also be one or more special-purpose processing devices such as application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), digital signal processors (DSPs), network processors, or the like. The system controller 228 can include data storage devices (e.g., one or more disk drives and / or solid state drives), main memory, static memory, network interfaces, and / or other components. The system controller 228 can execute instructions to perform any one or more of the methods and / or embodiments described herein. In some embodiments, the system controller 228 can execute instructions to perform one or more operations at the manufacturing system 200 according to a processing recipe. The instructions can be stored on a computer-readable storage medium, which can include main memory, static memory, secondary storage, and / or the processing devices (during execution of the instructions).

[0064] The system controller 228 can receive data from sensors included on or within various portions of the manufacturing system 200, such as the processing chambers 214, 216, 218, the transfer chamber 210, the load lock 220, etc. In some embodiments, the data received by the system controller 228 can include spectral and / or non-spectral data of a portion of the substrate 202. In other or similar embodiments, the data received by the system controller 228 can include data associated with processing the substrate 202 at the processing chambers 214, 216, 218, as previously described. For the purposes of the present disclosure, the system controller 228 is described as receiving data from sensors included within the processing chambers 214, 216, 218. However, according to embodiments described herein, the system controller 228 can receive data from and can use data received from any portion of the manufacturing system 200. In illustrative examples, the system controller 228 can receive data from one or more sensors of the processing chambers 214, 216, 218 prior to, after, or during processing of the substrate at the processing chambers 214, 216, 218. Data received from sensors of various portions of the manufacturing system 200 can be stored in the data storage 250. The data storage 250 can be included as a component within the system controller 228, or can be a component separate from the system controller 228. In some embodiments, the data storage 250 can be a component of the data storage 140 described with respect to Figure 1 the data storage 140 described.

[0065] Figure 3 is a cross-sectional schematic side view of a processing chamber 300 according to embodiments of the present disclosure. In some embodiments, the processing chamber 300 can correspond to the processing chambers 214, 216, 218 described with reference to Figure 2 The processing chamber 300 can be used for processing in which a corrosive plasma environment is provided. For example, the processing chamber 300 can be a chamber for a plasma etch machine or plasma etch reactor, etc. In another example, the processing chamber can be a chamber for deposition processing, as previously described. In one embodiment, the processing chamber 300 includes a chamber body 302 and a showerhead 330 that encloses an interior volume 306. The showerhead 330 can include a showerhead base and a showerhead gas distribution plate. Alternatively, in some embodiments, the showerhead 330 can be replaced by a lid and a showerhead, or in other embodiments by a plurality of pie-shaped showerhead compartments and plasma generation units. The chamber body 302 can be made of aluminum, stainless steel, or other suitable materials such as titanium (Ti). The chamber body 302 generally includes sidewalls 308 and a bottom 310. An exhaust 326 can be defined in the chamber body 302 and can couple the interior volume 306 to a pump system 328. The pump system 328 can include one or more pumps and throttle valves for evacuating and regulating the pressure of the interior volume 306 of the processing chamber 300.

[0066] The showerhead 330 can be supported on the sidewall 308 of the chamber body 302. The showerhead 320 (or lid) can be opened to allow access to the interior volume 306 of the processing chamber 300 and can provide a seal for the processing chamber 300 when closed. A gas panel 358 can be coupled to the processing chamber 300 to provide process and / or cleaning gases to the interior volume 306 through the showerhead 330 or lid and nozzles (e.g., through holes of the showerhead or lid and nozzles). For example, the gas panel 358 can provide a precursor for a film 351 deposited on a surface of the substrate 302. In some embodiments, the precursor can include a silicon-based precursor or a boron-based precursor. The showerhead 330 can include a gas distribution plate (GDP) and can have a plurality of gas delivery holes 332 (also referred to as passages) throughout the GDP. A substrate support assembly 348 is disposed in the interior volume 306 of the processing chamber 300 below the showerhead 330. The substrate support assembly 348 holds the substrate 302 during processing (e.g., during a deposition process) using, for example, an electrostatic chuck 350.

[0067] In some embodiments, the processing chamber 300 can include a metrology device (not shown) configured to generate in-situ metrology measurements during processing performed at the processing chamber 300. The metrology device can be operably coupled to a system controller (e.g., the system controller 328, as previously described). In some embodiments, the metrology device can be configured to generate a metrology measurement (e.g., a thickness) of the film 351 during a particular instance of a deposition process. The system controller can generate a thickness profile of the film 351 based on the metrology measurement received from the metrology device. In other or similar embodiments, the processing chamber 300 does not include a metrology device. In such embodiments, the system controller can receive one or more metrology measurements of the film 351 after completion of a deposition process at the processing chamber 300. The system controller can determine a deposition rate based on the one or more metrology measurements, and can correlate a thickness profile of the film 351 based on the determined concentration gradient and the determined deposition rate of the deposition process.

[0068] Figure 4 FIG. 4 is a flow diagram of a method 400 for adjusting a process recipe based on a correction profile in accordance with aspects of the present disclosure. The method 400 is performed by processing logic that can comprise hardware (e.g., circuitry, dedicated logic, etc.), software (such as is run on a general purpose computer system or a dedicated machine), firmware, or a combination thereof. In one implementation, the method 400 can be performed by a computer system architecture 100 such as that of FIG. 1. In other or similar implementations, one or more operations of the method 400 can be performed by one or more other machines not depicted in the figures. In some aspects, one or more operations of the method 400 can be performed by the manufacturing equipment 124 and / or the client device 122. Figure 1 In some aspects, the method 400 can be performed by the computer system architecture 100 of FIG. 1. In other or similar implementations, one or more operations of the method 400 can be performed by one or more other machines not depicted in the figures. In some aspects, one or more operations of the method 400 can be performed by the manufacturing equipment 124 and / or the client device 122.

[0069] At operation 410, the processing logic identifies a process recipe. In some embodiments, the processing logic can receive user input identifying the process recipe. In other embodiments, the processing logic can automatically select the process recipe. For example, the processing logic can identify a process recipe for which at least one process run has ended and for which a thickness profile has been generated. In yet another embodiment, the processing logic can identify a process recipe based on a process recipe currently being executed. For example, the processing logic can execute a deposition process on a substrate according to a process recipe. The deposition process can be executed in one or more process chambers. The process recipe can include one or more setting parameters for the deposition process. For example, the setting parameters can include a deposition time for each layer and / or cycle of the process recipe, a temperature setting for the process chamber, a pressure setting for the process chamber, a flow rate setting for a precursor of a material included in a film deposited on a surface of the substrate, a showerhead height, etc. The deposition process can deposit multiple layers on the substrate. For example, the deposition process can deposit alternating oxide and nitride layers, alternating oxide and polysilicon layers, etc.

[0070] At operation 412, the processing logic obtains a thickness profile for the process recipe. The thickness profile includes one or more data values associated with a film generated by the manufacturing equipment 124. For example, the thickness profile can include a measured thickness of the film, a measured thickness of one or more layers of the film, and / or a measured thickness of one or more cycles of the film, etc. The thickness profile can be measured using the metrology equipment 128. In some embodiments, the thickness profile is retrieved from the data store 140.

[0071] At operation 414, the processing logic obtains an expected profile for the process recipe. The expected profile can include a desired thickness of the film, a desired thickness of one or more layers of the film, and / or a desired thickness of one or more cycles of the film, etc. In some embodiments, the expected profile is retrieved from the data store 140.

[0072] At operation 416, the processing logic generates a correction profile based on the expected profile and the thickness profile. The correction profile can include one or more correction actions to be applied to parameters of the process recipe or the processing chamber during one or more steps of the deposition process. Specifically, the correction profile can include adjustments to a deposition time for one or more layers and / or each of one or more cycles, a temperature setting for the processing chamber, a pressure setting for the processing chamber, a flow rate setting for a precursor of a material included in a film deposited on a surface of the substrate, a power provided to the processing chamber, a ratio of two or more settings, and / or the like. For example, the correction profile can include a deposition time adjustment for a cycle of the process recipe. In some embodiments, the correction profile can include a set of parameter adjustments for each layer and / or cycle of the process recipe. For example, the correction profile can include a deposition time adjustment for a first cycle, for a second cycle, for a third cycle, and so on, up to a final cycle. Each adjustment can be applied to a corresponding deposition step to adjust a thickness of one or more cycles or layers such that the film stack thickness is the same as the expected film thickness indicated by the expected profile. For example, if the expected film thickness after cycle 39 is a first value (e.g., 20,000 nm), the expected film thickness after cycle 40 is a second value (e.g., 20,500 nm), and the actual film thickness during the deposition run and after cycle 39 is a third value (e.g., 20,050), the adjustment profile can indicate a correction to the deposition time of cycle 40 (e.g., reduce the deposition time of cycle 40 by a particular time period) such that the actual film thickness after cycle 40 is equal to the expected film thickness (e.g., 20,500 nm).

[0073] In some embodiments, the processing logic can generate the correction profile using one or more formulas or mathematical models. For example, the processing logic can generate a curve fitting model using data values from the expected profile and / or the thickness profile, and then use the curve fitting model to determine an offset time value for a particular step during the current deposition process. This aspect of the disclosure is explained in more detail in Figure 5 In some embodiments, the processing logic can generate the correction profile using a machine learning model (e.g., machine learning model 190) or using an inference engine.

[0074] At operation 418, the processing logic generates an updated process recipe by applying the correction profile to the process recipe. For example, the correction profile can be applied to one or more steps of the current deposition process. Figure 6 Table 600 is shown to illustrate an example correction profile. As shown, column 610 can include an index of cycles of the deposition process, and column 620 can include a time offset value to be applied to a deposition time for each respective cycle.

[0075] At operation 420, the processing logic performs the deposition steps of the identified process recipe on the substrate according to the updated process recipe. For example, the processing logic can deposit a first set of film layers (or cycles) on the substrate, determine a thickness profile of the deposited film, generate a correction profile to correct for any defects detected during deposition of the first set of film layers, apply the correction profile to the process recipe, and deposit a second set of film layers (or cycles) on the substrate. Thus, the deposition process recipe can be adjusted in real-time or near real-time. This process can be repeated for each deposition step of the process recipe.

[0076] Figure 5 FIG. 5 is a flow diagram of a method 500 for determining a correction profile of a process recipe using a curve fitting method according to aspects of the present disclosure. The method 500 is performed by processing logic that can comprise hardware (circuitry, dedicated logic, etc.), software (such as is run on a general purpose computer system or a dedicated machine), firmware, or some combination thereof. In one implementation, the method 500 can be performed by a computer system architecture 100 such as that shown in FIG. 1. In other or similar implementations, one or more operations of the method 500 can be performed by one or more other machines not depicted in the figures. In some aspects, one or more operations of the method 500 can be performed by the manufacturing equipment 124 and / or the client device 122. Although the method 500 is described below with reference to the computer system architecture 100, persons of ordinary skill in the art will recognize that other computer system architectures can perform the operations of the method 500. Figure 1 Figure 5 While the use of a curve fitting method to determine a correction profile is discussed, persons of ordinary skill in the art will recognize that other methods, formulas, and models can be used to generate a correction profile, including but not limited to, regression analysis, least squares methods, etc.

[0077] At operation 512, the processing logic obtains a thickness profile of the process recipe. The thickness profile includes one or more thickness data values associated with a film generated by the manufacturing equipment 124. For example, the thickness profile can include a measured thickness of the film, a measured thickness of one or more layers of the film, and / or a measured thickness of one or more cycles of the film, etc. The thickness profile can be measured using the metrology equipment 128. In some embodiments, the thickness profile is retrieved from the data store 140.

[0078] At operation 514, the processing logic obtains an expected profile of the process recipe. The expected profile can include a desired thickness of the film, a desired thickness of one or more layers of the film, and / or a desired thickness of one or more cycles of the film, etc. In some embodiments, the expected profile is retrieved from the data store 140.

[0079] At operation 516, the processing logic generates a polynomial equation. For example, a third order polynomial equation can be represented as: y = ax 3 + bx 2 ​+ cx + d, where (x, y) are coordinates, a, b, c, and d are constants. As an example, a polynomial equation with a third order is used, and any order of polynomial equation can be used. In some embodiments, a set of expected chamber wall residual thickness values are used as the x variable (e.g., chamber wall residual thickness after cycle one, chamber wall residual thickness after cycle two, chamber wall residual thickness after cycle three, and so on), and a time value is used as the y coordinate (e.g., expected deposition thickness at different chamber wall residual thicknesses) to generate the polynomial equation. The (x, y) values can be extracted from the expected profile. Using a set of (x, y) coordinates, the constants of the polynomial equation are determined. In some embodiments, the chamber wall residual thickness is a season thickness plus a deposition thickness, where the deposition thickness is equal to the total thickness of all previous cycles. The season thickness can include a layer (e.g., a silicon oxide layer) above the chamber wall before the substrate is introduced into the chamber for processing. The deposition of the season layer reduces the likelihood that contaminants will interfere with subsequent processing steps.

[0080] At operation 518, the processing logic determines the (y) value for a particular cycle using the polynomial equation and the thickness profile. Specifically, the processing logic can receive an input indicating a layer or cycle of deposition processing (e.g., based on user input, automatic input, etc.). The processing logic can then input the actual thickness of the cycle or layer (obtained from the thickness profile) into the polynomial equation to calculate the (y) for the cycle or layer.

[0081] At operation 520, the processing logic generates a correction value based on the (y) value. In one embodiment, the correction value can be generated based on the following equation: correction value = (y[1st cycle] / y[ current cycle number])*t step where t step is the expected time for the selected cycle.

[0082] At operation 522, the processing logic inputs the correction value into the correction profile. The operations of method 500 can be performed for one or more of the remaining cycles or layers of the processing recipe.

[0083] Figures 7A-7B FIG. 7 is a graph showing metrology data from a deposition process according to the same recipe as FIG. 6, but without the correction profile. Specifically, Figure 7A FIG. 7 is a graph showing metrology data from a deposition process according to the same recipe as FIG. 6, but without the correction profile. Specifically, Figure 7A The thickness values for each cycle shown in FIG. 7 are not adjusted according to the correction profile. As shown, the thickness for each cycle gradually increases. Figure 7Bis a graph showing the thickness values for each cycle adjusted according to the correction profile. As shown, the thickness for each cycle remains relatively the same throughout the deposition process and does not gradually increase.

[0084] Figure 8 is a block diagram illustrating a computer system 800, in accordance with certain embodiments. In some embodiments, computer system 800 can be connected (e.g., via a network, such as a local area network (LAN), intranet, extranet, or the Internet) to other computer systems. Computer system 800 can operate in the capacity of a server or a client computer in a client-server environment, or as a peer computer in a peer-to-peer or distributed network environment. Computer system 800 can be provided by a personal computer (PC), a tablet computer, a set-top box (STB), a personal digital assistant (PDA), a cellular telephone, a web appliance, a server, a network router, switch or bridge, or any other device capable of executing a set of instructions (sequential or otherwise) that specify actions to be taken by that device. Further, the term "computer" shall also include any collection of computers or computer components (e.g., a computer cluster) that individually or jointly execute a set (or multiple sets) of instructions to perform any one or more of the methodologies discussed herein.

[0085] In further aspects, computer system 800 can include a processing device 802, volatile memory 804 (e.g., random access memory (RAM)), non-volatile memory 806 (e.g., read-only memory (ROM) or electrically

[0086] Processing device 802 can be provided by one or more processors, such as a general purpose processor (e.g., a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a microprocessor implementing other instruction sets, or a microprocessor implementing a combination of instruction sets) or a special- purpose processor (e.g., a special-purpose application specific integrated circuit (ASIC), a programmable logic gate array (FPGA), a digital signal processor (DSP), or a network processor).

[0087] Computer system 800 can further include a network interface device 822 (e.g., a modem) coupled to the network 874. Computer system 800 also can include a video display unit 810 (e.g., an LCD), an alphanumeric input device 812 (e.g., a keyboard), a cursor control device 814 (e.g., a mouse), and / or a signal generation device 820.

[0088] In some implementations, the data storage device 816 can include a non-transitory computer-readable storage medium 824 on which is stored instructions 826 encoding any one or more of the methods or functions described herein, including instructions encoding components (e.g., the correction action component 122, the prediction component 114, etc.) and for implementing the methods described herein. Figure 1

[0089] The instructions 826 can also reside, completely or at least partially, within volatile memory 804 and / or processing device 802 during execution thereof by the computer system 800, thus, volatile memory 804 and processing device 802 also can constitute machine-readable storage media.

[0090] While the computer-readable storage medium 824 is shown in an illustrative example as a single medium, the phrase "computer-readable storage medium" should be taken to include a single medium or multiple media (e.g., a central or distributed database, and / or associated caches and servers) that store the one or more sets of executable instructions. The phrase "computer-readable storage medium" shall also be taken to include any medium that is capable of storing or encoding a set of instructions for execution by the computer, and that cause the computer to perform any one or more of the methods described herein. The phrase "computer-readable storage medium" shall accordingly be taken to include, but not be limited to, solid-state memories, optical media, and magnetic media.

[0091] The methods, components, and features described herein can be implemented by separate hardware components or integrated in the functionality of other hardware components such as ASICS, FPGAs, DSPs or similar device(s). Also, the methods, components, and features can be implemented by firmware modules or functional circuitry within hardware devices. Further, the methods, components, and features can be implemented in any combination of hardware devices and computer program components or in computer programs.

[0092] ​Unless specifically stated otherwise, the terms "receiving," "performing," "providing," "obtaining," "causing," "accessing," "determining," "increasing," "using," "training," and the like, refer to actions and processes performed or implemented by computer systems that manipulates and transforms data represented as physical (electronic) quantities within the computer system's registers and memories into other data similarly represented as physical quantities within the computer system memories or registers or other such information storage, transmission or display devices. Moreover, the terms "first," "second," "third," "fourth," etc. as used herein is used in its plain, ordinary, and grammatical sense, and is not meant to be construed as having a sequential meaning.

[0093] Examples described herein also relate to apparatus for performing the methods described herein. This apparatus can be specially constructed for performing the methods described herein, or can comprise a general purpose computer system selectively programmed by a computer program stored in the computer system.

[0094] The methods and illustrative examples described herein are not inherently related to any particular computer or other apparatus. Various general purpose systems can be used with or in manner consistent with the teachings described herein, or more specialized apparatus can be constructed to perform the methods and / or each of their respective functions, routines, sub-routines, or operations described herein if such is convenient. Examples of structures for various of these systems are set forth in the description above.

[0095] The above description is intended to be illustrative, and not restrictive. While the disclosure has been described with reference to specific illustrative examples and implementations, it will be recognized that the disclosure is not limited to the examples and implementations described. The scope of the disclosure should be determined, not with reference to the above description, but should instead be determined with reference to the appended claims, along with their full scope of equivalents.

Claims

1. A method comprising: The first deposition operation enables multiple deposition operations to be performed on the substrate according to the processing formula; Obtain metrological data associated with the first set of layers formed through the first deposition operation; Obtain a desired profile associated with the processing formulation, wherein the desired profile includes multiple values ​​indicating the desired thickness of multiple layers of the processing formulation; A correction profile is generated based on the metrological data and the expected profile, wherein the correction profile includes a deposition time offset value of at least one of the plurality of layers; An updated treatment formulation is generated by applying the corrected profile to the treatment formulation; and A second deposition operation is performed on the substrate according to the updated processing formula, wherein the second deposition operation forms a second set of layers on the first set of layers.

2. The method of claim 1, wherein the metering data indicates the actual thickness of one or more deposited layers.

3. The method of claim 1, wherein the correction profile further comprises one or more correction actions to be applied to one or more setting parameters of the processing formulation.

4. The method of claim 1, wherein generating the corrected profile comprises: A polynomial equation is generated based on at least one of the measurement data or the expected profile. and The polynomial equation is used to determine one or more deposition time offset values.

5. The method of claim 1, wherein generating the corrected profile comprises: The measurement data is then input into a trained machine learning model; and Obtain the output value of the trained machine learning model, wherein the output value indicates the corrected contour.

6. The method of claim 1, wherein the correction profile includes a deposition time offset value for a pair of layers comprising different materials.

7. The method of claim 1, wherein the deposition time offset value causes the actual film stack thickness produced according to the treatment formulation to match the expected film stack thickness produced according to the treatment formulation.

8. An electronic device manufacturing system, comprising: Memory devices; and A processing device, operatively coupled to the memory device, is configured to perform the following operations: The first deposition operation enables multiple deposition operations to be performed on the substrate according to the processing formula; Obtain metrological data associated with the first set of layers formed through the first deposition operation; Obtain a desired profile associated with the processing formulation, wherein the desired profile includes multiple values ​​indicating the desired thickness of multiple layers of the processing formulation; A correction profile is generated based on the metrological data and the expected profile, wherein the correction profile includes a deposition time offset value of at least one of the plurality of layers; An updated treatment formulation is generated by applying the corrected profile to the treatment formulation; and A second deposition operation is performed on the substrate according to the updated processing formula, wherein the second deposition operation forms a second set of layers on the first set of layers.

9. The electronic device manufacturing system of claim 8, wherein the metering data indicates the actual thickness of one or more deposited layers.

10. The electronic device manufacturing system of claim 8, wherein the correction profile further includes one or more correction actions to be applied to one or more setting parameters of the processing recipe.

11. The electronic device manufacturing system of claim 8, wherein generating the corrected profile includes the processing device performing the following operations: A polynomial equation is generated based on at least one of the measurement data or the expected profile. and The polynomial equation is used to determine one or more deposition time offset values.

12. The electronic device manufacturing system of claim 8, wherein generating the corrected profile includes the processing device performing the following operations: The measurement data is then input into a trained machine learning model; and Obtain the output value of the trained machine learning model, wherein the output value indicates the corrected contour.

13. The electronic device manufacturing system of claim 8, wherein the correction profile includes a deposition time offset value for a pair of layers comprising different materials.

14. The electronic device manufacturing system of claim 8, wherein the deposition time offset value causes the actual film stack thickness produced according to the processing formulation to match the expected film stack thickness produced according to the processing formulation.

15. A non-transitory computer-readable storage medium comprising instructions that, when executed by a processing means operatively coupled to a memory, perform the following operations: The first deposition operation enables multiple deposition operations to be performed on the substrate according to the processing formula; Obtain metrological data associated with the first set of layers formed through the first deposition operation; Obtain a desired profile associated with the processing formulation, wherein the desired profile includes multiple values ​​indicating the desired thickness of multiple layers of the processing formulation; A correction profile is generated based on the metrological data and the expected profile, wherein the correction profile includes a deposition time offset value of at least one of the plurality of layers; An updated treatment formulation is generated by applying the corrected profile to the treatment formulation; and A second deposition operation is performed on the substrate according to the updated processing formula, wherein the second deposition operation forms a second set of layers on the first set of layers.

16. The non-transient computer-readable storage medium of claim 15, wherein the metering data indicates the actual thickness of one or more deposited layers.

17. The non-transient computer-readable storage medium of claim 15, wherein the correction profile further includes one or more correction actions to be applied to one or more setting parameters of the processing recipe.

18. The non-transitory computer-readable storage medium of claim 17, wherein generating the correction profile includes performing the following operations: A polynomial equation is generated based on at least one of the measurement data or the expected profile. and The polynomial equation is used to determine one or more deposition time offset values.

19. The non-transitory computer-readable storage medium of claim 17, wherein generating the correction profile includes performing the following operations: The measurement data is then input into a trained machine learning model; and Obtain the output value of the trained machine learning model, wherein the output value indicates the corrected contour.

20. The non-transient computer-readable storage medium of claim 17, wherein the correction profile includes deposition time offset values ​​for a pair of layers comprising different materials.

Images