Process tool, electronic device manufacturing system, transfer chamber robot and method

Abstract

This document discloses embodiments of a transfer chamber robot and methods of using the same. In one embodiment, a processing tool for an electronic component manufacturing system includes a transfer chamber, a processing chamber coupled to the transfer chamber, and a transfer chamber robot. The transfer chamber robot is configured to transfer a substrate to and from the processing chamber and includes sensors configured to perform measurements inside the processing chamber.

Description

[Technical Field]

[0001] The embodiments disclosed herein are systematically related to methods and mechanisms for contactless characterization of semiconductor processing chambers. [Previous Technology]

[0002] Electronic manufacturing systems generally comprise multiple processing chambers subjected to vacuum during operation. During substrate manufacturing, contaminants and residual deposits are introduced into various components of the processing chambers. Therefore, the processing chambers require periodic inspection and cleaning based on contamination or deposit levels to remove contaminants and residual deposits from the walls and gas distribution plates.

[0003] Traditionally, operators periodically disconnect the vacuum system and remove components of the electronic manufacturing system (such as process chamber doors) to inspect the process chamber and determine if cleaning is necessary. However, this is a time-consuming, expensive, and inefficient process. Alternatively, some electronic manufacturing systems modify the process chamber walls to include sensors for detecting deposit buildup. However, these wall sensors introduce defects into the process chamber and affect plasma uniformity. [Summary of the Invention]

[0004] Certain embodiments of this disclosure relate to a processing tool for an electronic component manufacturing system. The processing tool includes a transfer chamber, a processing chamber coupled to the transfer chamber, and a transfer chamber robot configured to transfer a substrate to and from the processing chamber. The transfer chamber robot includes sensors configured to perform measurements inside the processing chamber.

[0005] Another aspect of this disclosure relates to an electronic component manufacturing system, including a loading gate and a processing tool. The processing tool includes a transfer chamber, a processing chamber coupled to the transfer chamber, and a transfer chamber robot configured to transfer a substrate to and from the processing chamber. The transfer chamber robot includes sensors configured to perform measurements inside the processing chamber.

[0006] Another aspect of this disclosure relates to a transfer chamber robot. The transfer chamber robot includes: an arm assembly including a plurality of links; an end effector coupled to the arm assembly, wherein the end effector is configured to transfer a substrate to and from a processing chamber; and a sensor coupled to the arm assembly and configured to perform measurements inside the processing chamber.

[0007] Another aspect of this disclosure relates to a method comprising: locating a portion of a transfer chamber robot within a processing chamber by means of a processor, the portion including at least one sensor; obtaining sensor data associated with the processing chamber by means of one or more sensors; and removing the portion of the transfer chamber robot from the processing chamber.

[0008] Another aspect of this disclosure includes a method comprising generating a plurality of sensor values ​​by means of a processor and a sensing device at a processing chamber. The method further includes applying a machine learning model to the plurality of sensor values, the machine learning model being trained based on historical sensor data of a subsystem of the processing chamber and task data associated with a formulation for depositing a membrane. The method further includes generating an output of the machine learning model, wherein the output indicates a failure type of the subsystem. The method further includes determining the failure type of the subsystem and generating a corrective action based on the failure type.

Implementation Method

[0019] This document describes techniques relating to contactless characterization methods and mechanisms for semiconductor processing chambers used in manufacturing systems. A film can be deposited on a substrate surface during a deposition process (e.g., CVD process, atomic layer deposition (ALD) process, etc.) performed in the processing chamber of a manufacturing system. For example, in a CVD process, the 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 specific thickness gradient (e.g., a change in thickness along the layers of the deposited film). For example, a first layer can be formed directly on the substrate surface (referred to as the proximal layer or proximal end of the film) and has a first thickness. After the first layer is formed on the substrate surface, a second layer with a second thickness can be formed on the first layer. This process continues until the deposition process is completed and the final layer of the film (referred to as the distal layer or distal end of the film) is formed. The film can include alternating layers of different materials. For example, the film may include alternating layers of oxide and nitride layers (oxide-nitride-oxide-nitride stacks or ONON stacks), alternating layers of oxide and polysilicon (oxide-polysilicon-oxide-polysilicon stacks or OPOP stacks), and so on. The film may then undergo processes such as etching to form patterns on the substrate surface, chemical-mechanical polishing (CMP) to smooth the surface of the film, or any other processes required for the fabrication of the finished substrate.

[0020] During deposition and etching processes, the processing chamber may experience deteriorating conditions, such as the accumulation of contaminants and corrosion of certain components. Failure to capture and repair these deteriorating conditions can lead to defects in the substrate, defective products, reduced manufacturing yield, and significant downtime and repair time.

[0021] Existing systems can modify the processing chamber walls to include sensors for detecting such deterioration conditions. However, these invasive wall sensors introduce defects into the processing chamber and affect plasma uniformity. This can lead to delays in achieving optimal processing chamber pressure and process gas flow rates, potentially causing membrane deformation. Furthermore, these sensors may be difficult to install because modifications to the processing chamber may be required at the consumer site.

[0022] The disclosed state and embodiments address these and other disadvantages of the prior art by equipping a transfer chamber robot with one or more sensors capable of performing measurements and acquiring data from inside the processing chamber. Specifically, an electronic component manufacturing system may employ robotic equipment (e.g., a transfer chamber robot) in a transfer chamber configured to transport substrates between a loading gate and a processing chamber. The transfer chamber, processing chamber, and loading gate may operate under vacuum at certain times. The transfer chamber robot may be equipped with one or more sensors for characterizing, reading, or measuring one or more state of the processing chamber. The sensors may include one or more of the following: accelerometers, distance sensors (e.g., for determining the height, width, or length between two objects), cameras (e.g., high-resolution cameras, high-speed cameras, etc.), capacitance sensors, reflectometers, pyrometers (e.g., remote sensing thermometers, infrared cameras, etc.), laser-induced fluorescence spectrometers, fiber optic elements, etc.

[0023] In some embodiments, the sensor may be coupled to an end effector of the transfer chamber robot or one or more connectors of the transfer chamber robot. In other embodiments, the transfer chamber robot may include additional links and / or more degrees of freedom for manipulating the sensor. Specifically, the transfer chamber robot may include one or more additional links to couple to the sensor, and / or one or more additional degrees of freedom to translate, rotate, and / or position the sensor within the processing chamber. Data acquired by the sensor may be sent to a user interface or database for processing and analysis. Based on the data, the operator of the manufacturing system may decide whether to pause operation and perform maintenance, or continue manufacturing the substrate.

[0024] In some embodiments, the prediction system may train and apply a machine learning model to current sensor values ​​to produce outputs, such as one or more values ​​indicating a failure mode (e.g., anomalous behavior) of the processing chamber subsystem and / or predictive data indicating the type of failure that has occurred (e.g., problem, failure, etc.). In some embodiments, the output indicates a value representing the difference between the desired behavior of the processing chamber subsystem and the actual behavior of the processing chamber subsystem. In some embodiments, the value indicates a failure mode associated with the processing chamber subsystem. In some embodiments, the system may subsequently compare the failure mode with a library of known failure modes to determine the type of failure experienced by the subsystem. In some embodiments, the system performs corrective actions to adjust one or more parameters of the deposition process formulation (e.g., temperature setting of the processing chamber, pressure setting of the processing chamber, flow rate setting of precursors of materials included in the film deposited on the substrate surface, etc.) based on the failure mode.

[0025] The disclosed configuration results in a significant reduction in the time required to perform inspections of the processing chamber. The configuration allows the transfer chamber robot to perform inspections and characterize the processing chamber each time it places a substrate into or retrieves a substrate from the processing chamber. Inspections are performed while maintaining a vacuum environment, thus eliminating the need to disconnect the vacuum system and remove components of the electronic manufacturing system (such as processing chamber doors) associated with manual inspection. The configuration also eliminates defects in the processing chamber and plasma uniformity issues associated with mounting sensors within the processing chamber.

[0026] Figure 1 illustrates an illustrative computer system architecture 100 according to 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 manufacturing system 300 of Figure 3). The computer system architecture 100 includes a client device 120, a manufacturing apparatus 124, a metering device 128, a prediction server 112 (e.g., for generating prediction data, providing model adaptation, using a knowledge base, etc.), and a data storage device 140. The prediction server 112 may be part of the prediction system 110. The prediction system 110 may further include server machines 170 and 180. The manufacturing apparatus 124 may include sensors 126 configured to capture data of the substrates processed at the manufacturing system. In some embodiments, manufacturing equipment 124 and sensor 126 may be part of a sensor system that includes 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, metering equipment 128 may be part of a metering system that includes a metering server (e.g., a metering database, metering document library, etc.) and a meter identifier reader (e.g., a FOUP RFID reader for the metering system).

[0027] Manufacturing equipment 124 can produce products, such as electronic components, over a period of time according to a recipe or by performing operations. Manufacturing equipment 124 may include processing chambers, such as processing chamber 400 described with respect to Figure 4. Manufacturing equipment 124 can perform processes on substrates (e.g., wafers, etc.) at the processing chamber. Examples of substrate processes include deposition processes for depositing one or more layers of film on a substrate surface, etching processes for forming patterns on a substrate surface, etc. 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 the substrate during the process and may include one or more settings associated with each operation. For example, a deposition process recipe may include temperature settings for the processing chamber, pressure settings for the processing chamber, flow rate settings for precursors of materials included in the film deposited on the substrate surface, etc.

[0028] In some embodiments, manufacturing apparatus 124 includes sensors 126 configured to generate data associated with a substrate processed at manufacturing system 100. For example, a processing chamber may include one or more sensors configured to generate spectral or non-spectral data associated with the substrate before, during, and / or after performing a process (e.g., deposition process) on the substrate. In some embodiments, one or more sensors may be coupled to a transfer chamber robot. Specifically, manufacturing apparatus 124 may employ robotic devices (e.g., transfer chamber robots) in a transfer chamber configured to transport substrates between a loading gate and a processing chamber. The processing chamber robot is described in more detail with reference to Figure 3. In one example, the sensors may be attached to an end effector of the transfer chamber robot for supporting the substrate. Further details regarding the attached sensors are provided with reference to Figures 5 and 6.

[0029] In some embodiments, the spectral data generated by sensor 126 can indicate the concentration of one or more materials deposited on the substrate surface. Sensor 126 configured to generate spectral data associated with the substrate may include a reflectance measurement sensor, an elliptic measurement sensor, a thermal spectral sensor, a capacitance sensor, etc. Sensor 126 configured to generate non-spectral data associated with the substrate may include a temperature sensor, a pressure sensor, a flow rate sensor, a voltage sensor, etc. Further details regarding manufacturing apparatus 124 are provided with reference to Figures 3 and 4.

[0030] In some embodiments, sensor 126 provides sensor data (e.g., sensor values, features, trace data) associated with manufacturing equipment 124 (e.g., associated with the production of a corresponding product (such as a wafer) by manufacturing equipment 124). Manufacturing equipment 124 may produce a product over a period of time according to a recipe or by performing a run. Sensor data received over a period of time (e.g., corresponding to at least a portion of a recipe or run) may be referred to as trace data received from different sensors 126 over time (e.g., historical trace data, current trace data, etc.). Sensor data may include one or more values ​​of: temperature (e.g., heater temperature), spacing (SP), pressure, high frequency radio frequency (HFRF), electrostatic chuck (ESC) voltage, current, material flow rate, power, voltage, etc. Sensor data may be associated with or indicate manufacturing parameters, such as hardware parameters, such as the setup or components of manufacturing equipment 124 (e.g., size, type, etc.), or processing parameters of manufacturing equipment 124. Sensor data can be provided during the manufacturing process performed by the manufacturing equipment 124 (e.g., equipment readings when processing products). The sensor data can be different for each substrate.

[0031] The metrology equipment 128 can provide metrology data associated with the substrate processed by the manufacturing equipment 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 ​​such as one or more surface distribution property data (e.g., etch rate, etch rate uniformity, critical dimensions of one or more features included on the substrate surface, critical dimension uniformity across the substrate surface, edge placement error, etc.). The metrology data can be metrology data for a finished or semi-finished product. The metrology data may be different for each substrate. The metrology data can be generated using, for example, reflectance measurement techniques, ellipsometry techniques, TEM techniques, etc.

[0032] In some embodiments, the metering device 128 may be included as part of the manufacturing apparatus 124. For example, the metering device 128 may include or be coupled to a processing chamber and configured to generate metering data of a substrate before, during, and / or after a process (e.g., deposition, etching, etc.) while the substrate remains in the processing chamber. In this case, the metering device 128 may be referred to as an in-situ metering device. In another instance, the metering device 128 may be coupled to another station of the manufacturing apparatus 124. For example, the metering device may be coupled to a transfer chamber (such as transfer chamber 310 of Figure 3), a loading gate (such as loading gate 320), or a factory interface (such as factory interface 306). In this case, the metering device 128 may be referred to as an integrated metering device. In other or similar embodiments, the metering device 128 is not coupled to a station of the manufacturing apparatus 124. In this case, the metering device 128 may be referred to as an in-line metering device or an external metering device. In some embodiments, the integrated metering equipment and / or online metering equipment are configured to generate metering data of the substrate before and / or after the process.

[0033] Client device 120 may include computing devices such as personal computers (PCs), laptops, mobile phones, smartphones, tablets, laptops, network-connected televisions ("smart TVs"), network-connected media players (e.g., Blu-ray players), set-top boxes, over-the-top (OTT) streaming devices, carrier boxes, etc. In some embodiments, metrological data may be received from client device 120. Client device 120 may display a graphical user interface (GUI), wherein the GUI enables a user to provide metrological measurements of a substrate processed at the manufacturing system as input. Client device 120 may include a calibration action component 122. Calibration action component 122 may receive user input (e.g., via the graphical user interface (GUI) displayed via client device 120) indicating a command associated with manufacturing equipment 124. In some embodiments, calibration action component 122 sends an instruction to prediction system 110, receives output (e.g., prediction data) from prediction system 110, determines a calibration action based on the output, and causes the calibration action to be performed. In some embodiments, the correction action component 122 receives an instruction for a correction action from the prediction system 110 and causes the correction action to be performed. Each client device 120 may include an operating system that allows a user to generate, view, or edit data (e.g., instructions associated with the manufacturing equipment 124, correction actions associated with the manufacturing equipment 124, etc.).

[0034] Data storage 140 may be memory (e.g., random access memory), drive (e.g., hard disk, flash drive), database system, or another type of component or device capable of storing data. Data storage 140 may 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 may store data associated with the processing of a substrate at manufacturing equipment 124. For example, data storage 140 may store data (referred to as processing data) collected by sensor 126 at manufacturing equipment 124 before, during, or after the substrate processing. Processing data may refer to historical processing data (e.g., processing data generated for a previous substrate processed at the manufacturing system) and / or current processing data (e.g., processing data generated for a current substrate processed at the manufacturing system). Data storage may also store spectral or non-spectral data associated with a portion of the substrate processed at manufacturing equipment 124. Spectral data may include historical spectral data and / or current spectral data.

[0035] Data storage 140 may also store contextual data associated with one or more substrates processed at the manufacturing system. Contextual data may include recipe name, recipe step number, preventative maintenance instructions, operator, etc. Contextual data may 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 or future process to be performed on a previous substrate). Contextual data may further include sensors that identify specific subsystems associated with the processing chamber.

[0036] The data storage 140 may also store task data. Task data may include one or more sets of operations to be performed on the substrate during the deposition process and may include one or more settings associated with each operation. For example, task data for the deposition process may include temperature settings for the processing chamber, pressure settings for the processing chamber, flow rate settings for precursors of the film material deposited on the substrate, etc. In another example, task data may include controlling the pressure at a defined pressure point for the flow rate value. Task data may 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 the current process or a future process to be performed on a previous substrate).

[0037] In some embodiments, data storage 140 may store a desired distribution, a thickness distribution, and a correction distribution. The desired distribution may include one or more data points associated with a desired film distribution desired to be produced by a particular processing formulation. In some embodiments, the desired distribution may include a desired film thickness. The thickness distribution includes one or more data points associated with a current film distribution produced by manufacturing equipment 124. The thickness distribution may be measured using metering devices 127, 128. The correction distribution may include one or more adjustments or offsets to parameters applied to the processing chamber or the processing formulation. For example, the correction distribution may include adjusting the temperature setting of the processing chamber, the pressure setting of the processing chamber, the flow rate setting of precursors of materials included in the film deposited on the substrate surface, the power supplied to the processing chamber, the ratio of two or more settings, etc. The correction distribution may be generated by comparing the desired distribution (e.g., a desired thickness distribution produced by the processing formulation) and using a library and / or algorithm with known failure modes to determine the parameters applied to the processing formulation to achieve the adjustment of the desired distribution. The correction distribution may be applied to steps associated with deposition processes, etching processes, etc.

[0038] In some embodiments, data storage 140 may be configured to store data inaccessible to users of the manufacturing system. For example, processing data, spectral data, contextual data, etc., obtained for a substrate processed at the manufacturing system are inaccessible to users of the manufacturing system (e.g., operators). In some embodiments, all data stored in data storage 140 may be inaccessible to users of the manufacturing system. In other or similar embodiments, a portion of the data stored in data storage 140 may be inaccessible to users, while another portion of the data stored in data storage 140 may be accessible to users. In some embodiments, one or more portions of the data stored in data storage 140 may be encrypted using a user-unknown encryption mechanism (e.g., the data may be encrypted using a private encryption key). In other or similar embodiments, data storage 140 may include multiple data storage units, wherein user-inaccessible data is stored in one or more first data storage units and user-accessible data is stored in one or more second data storage units.

[0039] In some embodiments, data storage 140 may be configured to store data associated with known failure modes. A failure mode may be one or more values ​​(e.g., vectors, scalars, etc.) associated with one or more problems or failures associated with the processing chamber subsystem. In some embodiments, a failure mode may be associated with corrective actions. For example, a failure mode may include parameter adjustment steps for correcting a problem or failure indicated by the failure mode. For example, a prediction system may compare a determined failure mode with a library of known failure modes to determine the type of failure experienced by the subsystem, the cause of the failure, recommended corrective actions for correcting the failure, etc.

[0040] In some embodiments, the prediction system 110 includes a prediction server 112, a server machine 170, and a server machine 180. The prediction server 112, server machine 170, and server machine 180 may each include one or more computing devices, such as rack servers, router computers, server computers, personal computers, mainframe computers, laptop computers, tablet computers, desktop computers, graphics processing units (GPUs), accelerator application-specific integrated circuits (ASICs) (e.g., tensor processing units (TPUs)), etc.

[0041] Server machine 170 includes a training set generator 172 capable of generating training data sets (e.g., a data input set and a target output set) to train, validate, and / or test machine learning model 190. Machine learning model 190 can be any algorithmic model capable of learning from data. Some operations of the data set generator 172 are described in detail below with reference to Figure 2. In some embodiments, the data set generator 172 can divide the training data into training sets, validation sets, and test sets. In some embodiments, prediction system 110 generates multiple sets of training data.

[0042] Server machine 180 may include training engine 182, verification engine 184, selection engine 185, and / or testing engine 186. An engine may refer to hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, processing device, etc.), software (such as instructions running on a processing device, general-purpose computer system, or dedicated machine), firmware, microcode, or a combination thereof. Training engine 182 may be capable of training one or more machine learning models 190. Machine learning model 190 may refer to model artifacts created by training engine 182 using training data (also referred to herein as a training set) including training inputs and corresponding target outputs (the correct answers to the corresponding training inputs). Training engine 182 may discover patterns in the training data that map training inputs to target outputs (predicted answers) and provide machine learning models 190 that capture these patterns. Machine learning models 190 may use one or more of the following: statistical modeling, support vector machine (SVM), radial basis function (RBF), clustering, supervised machine learning, semi-supervised machine learning, unsupervised machine learning, k-nearest neighbor algorithm (k-NN), linear regression, random forest, neural network (e.g., artificial neural network), etc.

[0043] One type of machine learning model that can be used to perform some or all of the above tasks is an artificial neural network, such as a deep neural network. Artificial neural networks generally include feature representation components with classifier or regression layers that map features to a desired output space. For example, a convolutional neural network (CNN) manages multiple layers of convolutional filters. Pooling is performed at lower layers, typically with multiple layers of classifiers attached on top, and nonlinearity is addressed, thereby mapping the features extracted from the top layers 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 layers of nonlinear processing units for feature extraction and transformation. 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 consist of hierarchical layers, where different layers learn different representation levels 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. In plasma processing tuning, for example, the initial input can be a distribution of the processing results (e.g., a thickness distribution indicating one or more thickness values ​​across the substrate surface); the second layer can constitute feature data associated with the state of one or more regions of the controlled elements of the plasma processing system (e.g., region orientation, plasma exposure duration, etc.); the third layer can include a starting recipe (e.g., a recipe used as a starting point to determine an updated processing recipe that processes the substrate to produce a processing result that meets a threshold criterion). Notably, deep learning processing can learn on its own which features are best placed at which level. The "depth" in "deep learning" refers to the number of layers through which data traverses its transformation. More precisely, deep learning systems have a considerable credit assignment path (CAP) depth. CAP stands for the transformation chain from input to output. CAP describes the underlying causal relationship between input and output. For feedforward neural networks, the depth of CAP can be the network depth and can be the number of hidden layers plus one. For recurrent neural networks where the signal can propagate through more than one layer, the CAP depth is potentially unlimited.

[0044] In one embodiment, one or more machine learning models are recurrent neural networks (RNNs). RNNs are a type of neural network that includes a memory that enables the network to capture temporal dependencies. RNNs can learn an input-output mapping that depends on both current and past inputs. The RNN will resolve past and future flow rate measurements and make predictions based on this continuous measurement information. The RNN can be trained using a training dataset to produce a fixed number of outputs (e.g., to determine a set of substrate processing rates, to determine modifications to a substrate processing formula). One type of RNN that can be used is a long short-term memory (LSTM) neural network.

[0045] Training a neural network can be achieved through supervised learning, which involves feeding the network a training dataset consisting of labeled inputs, observing its outputs, defining the error (by measuring the difference between the output and the labeled value), and using techniques such as deep gradient descent and backpropagation to tune the network's weights across all its layers and nodes to minimize the error. In many applications, this process is repeated over numerous labeled inputs in the training dataset to produce a network that can produce the correct output when presented with inputs different from those present in the training dataset.

[0046] A training dataset containing hundreds, thousands, tens of thousands, hundreds of thousands or more sensor data and / or processing result data (e.g., measurement data, such as one or more thickness distributions associated with sensor data) can be used to form a training dataset.

[0047] To complete training, the processing logic can input the training dataset into one or more untrained machine learning models. The machine learning models can be initialized before the first input is fed into them. 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 the various operations described above. Training can be performed by inputting one or more sensor data into the machine learning models one at a time.

[0048] Machine learning models process inputs to produce outputs. Artificial neural networks consist of an input layer composed of values ​​from data points. The next layer is called a hidden layer, and nodes in the hidden layer each receive one or more input values. Each node contains parameters (e.g., weights) applied to the input values. Each node thus essentially feeds the input values ​​into a multivariate function (e.g., a nonlinear mathematical transformation) to produce an output value. The next layer can be another hidden layer or an output layer. In either case, nodes in the next layer receive output values ​​from nodes in the previous layer, and each node applies weights to those values ​​and subsequently produces its own output value. This can be performed at each layer. The final layer is the output layer, where there is a node for each class, prediction, and / or output that the machine learning model can produce.

[0049] Thus, the output may include one or more predictions or inferences. For example, the output predictions or inferences may include one or more predictions of membrane buildup on a chamber component, corrosion of a chamber component, predicted failure of a chamber component, etc. The processing logic determines the error (i.e., classification error) based on the difference between the output (e.g., prediction or inference) of the machine learning model 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 based on the error. An error term or increment may be determined for each node in the artificial neural network. Based on this error, the artificial neural network adjusts one or more of its parameters (weights for one or more inputs to the node) for one or more of its nodes. The parameters may be updated in a backpropagation manner, such that the nodes at the highest layer are updated first, then the nodes at the next layer are updated, and so on. The artificial neural network contains multiple layers of "neurons", where each layer receives input values ​​from neurons in previous layers. The parameters of each neuron include weights associated with the values ​​received from each neuron in previous layers. Therefore, the adjustment parameters can include adjusting the weights assigned to each input for one or more neurons at one or more layers in an artificial neural network.

[0050] After one or more rounds of training, the processing logic may determine whether a stopping criterion has been met. The stopping criterion may be a target accuracy level, the number of targets processed from the training dataset, the target change in parameters above 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 achieved. The threshold accuracy may be, for example, 70%, 80%, or 90% accuracy. In one embodiment, the stopping criterion is met if improving the accuracy of the machine learning model has stopped. If the stopping criterion has not yet been met, further training is performed. If the stopping criterion has been met, training can be completed. Once the machine learning model has been trained, a reserved portion of the training dataset can be used to test the model.

[0051] Once one or more trained machine learning models 190 are generated, they can be stored in the prediction server 112 as prediction component 114 or as a component of prediction component 114.

[0052] The validation engine 184 can validate the machine learning model 190 using a corresponding set of features from the validation set generated by the training set generator 172. Once the model parameters have been optimized, model validation can be performed to determine whether the model has been improved and to determine the current accuracy of the deep learning model. The validation engine 184 can determine the accuracy of the machine learning model 190 based on the corresponding set of features from the validation set. The validation engine 184 can discard trained machine learning models 190 with accuracy that does not meet a threshold accuracy. In some embodiments, the selection engine 185 can select trained machine learning models 190 with accuracy that meets a threshold accuracy. In some embodiments, the selection engine 185 can select the trained machine learning model 190 with the highest accuracy among the trained machine learning models 190.

[0053] The testing engine 186 can test the trained machine learning model 190 using a corresponding set of features from the test set generated by the data set generator 172. For example, a first trained machine learning model 190 trained using a first set of features from the training set can be tested using a first set of features from the test set. The testing engine 186 can determine, based on the test set, that the trained machine learning model 190 has the highest accuracy among all trained machine learning models.

[0054] As described in detail below, the prediction server 112 includes a prediction component 114 capable of providing data indicating the desired behavior of each subsystem of the processing chamber and running a trained machine learning model 190 on current sensor data input to obtain one or more outputs. The prediction server 112 may further provide data indicating the health and diagnosis of the processing chamber subsystems. This will be explained in more detail below.

[0055] The client device 120, manufacturing equipment 124, sensor 126, metering device 128, prediction server 112, data storage 140, server machine 170, and server machine 180 may be coupled to each other via network 130. In some embodiments, network 130 is a public network that provides the client device 120 with access to the prediction server 112, data storage 140, and other publicly available computing devices. In some embodiments, network 130 is a private network that provides the client device 120 with access to the manufacturing equipment 124, metering device 128, data storage 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), 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.

[0056] It should be noted that in some other embodiments, the functionality of server machines 170 and 180, and prediction server 112, can be provided by a smaller number of machines. For example, in some embodiments, server machines 170 and 180 can be integrated into a single machine, while in some other or similar embodiments, server machines 170 and 180, and prediction server 112 can be integrated into a single machine.

[0057] Generally, the functions described in one embodiment, which are performed by server machine 170, server machine 180, and / or prediction server 112, may also be performed by client device 120. Furthermore, functionality belonging to a particular component may be performed by different or multiple components operating together.

[0058] In this embodiment, "user" may refer to a single individual. However, other embodiments of this disclosure cover an entity controlled by a plurality of users and / or automation sources. For example, a collection of independent users as a group of administrators may be considered a "user".

[0059] Figure 2 is a flowchart of a method 200 for training a machine learning model according to the present disclosure. Method 200 is executed by processing logic, which may include hardware (circuit systems, dedicated logic, etc.), software (such as running on a general-purpose computer system or a dedicated machine), firmware, or some combination thereof. In one embodiment, method 200 may be executed by a computing system (such as computer system architecture 100 of Figure 1). In other or similar embodiments, one or more operations of method 200 may be executed by one or more other machines not depicted in the figures. In some embodiments, one or more operations of method 200 may be executed by server machine 170, server machine 180, and / or prediction server 112.

[0060] For simplicity of explanation, the method is depicted and described as a series of actions. However, the actions according to this disclosure can occur in various sequences and / or simultaneously, and other actions are not presented or described herein. Furthermore, not all the actions shown can be performed to implement the method according to the disclosed object. Moreover, those skilled in the art will understand and appreciate that the method can alternatively be represented by a state diagram or events as a series of interrelated states. Furthermore, it should be understood that the method disclosed in this specification can be stored on an article of writing for transmission and delivery to a computing device. As used herein, the term article of writing is intended to encompass a computer program accessible from any computer-readable device or storage medium.

[0061] In block 210, the processing logic initializes the training set T to an empty set (e.g., {}).

[0062] At block 212, the processing logic obtains sensor data (e.g., sensor values, features, trace data) associated with a previous deposition process performed to deposit one or more layers of film on the surface of a previous substrate. The sensor data may be further associated with subsystems of the processing chamber. A subsystem may be characterized as a set of sensors related to operating parameters of the processing chamber. Operating parameters may be temperature, flow rate, pressure, etc. For example, a pressure subsystem may be characterized by one or more sensors that measure gas flow rate, chamber pressure, control valve angle, foreground (vacuum line between pumps) pressure, pumping speed, etc. Each processing chamber may include multiple different subsystems, such as a pressure subsystem, a flow rate subsystem, a temperature subsystem, etc.

[0063] In some embodiments, the sensor data associated with the deposition process is historical data associated with one or more previous deposition settings of a previous deposition process previously performed on a previous substrate at the manufacturing system. For example, the historical data may be historical context data associated with a previous deposition process stored at data storage 140. In some embodiments, one or more previous deposition settings may include at least one of the following: a previous temperature setting of the previous deposition process, a previous pressure setting of the previous deposition setting, a previous flow rate setting of a precursor of one or more materials of the previous film deposited on the surface of the previous substrate, or any other setting associated with the deposition process. The flow rate setting may refer to the flow rate setting of the precursor at the initial instance of the previous deposition process (referred to as the initial flow rate setting), the flow rate setting of the precursor at the final instance of the previous deposition process (referred to as the final flow rate setting), or the ramp rate of the precursor flow rate during the deposition process. In one example, the precursor of the previous film may include a boron-containing precursor or a silicon-containing precursor. In some embodiments, sensor data may also be associated with a previous etching process performed on a previous substrate, or with any other process performed in a processing chamber.

[0064] At block 214, the processing logic obtains task data associated with the formulation of a film deposited on the surface of a previous substrate. For example, the task data may include required temperature settings, pressure settings, flow rate settings of precursors for the film material deposited on the substrate, etc. The task data may include historical task data of previous films deposited on the surface of the previous substrate. In some embodiments, the historical task data of previous films may correspond to historical task values ​​associated with the formulation of the previous films. The processing logic may obtain task data from data storage 140 according to the previously described embodiments.

[0065] In block 216, the processing logic generates first training data based on sensor data obtained in association with a previous deposition process performed on a previous substrate. In block 218, the processing logic generates second training data based on task data associated with the formulation of a film deposited on the surface of the previous substrate.

[0066] At block 220, the processing logic generates a mapping between first training data and second training data. The mapping refers to first training data that includes or is based on data from a previous deposition process performed on a previous substrate, and second training data that includes or is based on task data associated with a formulation of a film deposited on the surface of the previous substrate, wherein the first training data is associated with (or mapped to) the second training data. At block 224, the processing logic adds the mapping to the training set T.

[0067] At block 226, the processing logic determines whether the training set T contains sufficient training data to train the machine learning model. It should be noted that in some implementations, the sufficiency of the training set T can be determined simply based on the number of mappings in the training set, while in other implementations, in addition to or instead of the number of input / output mappings, the sufficiency of the training set T can be determined based on one or more other criteria (e.g., a measure of the diversity of training instances). In response to the determination that the training set does not contain sufficient training data to train the machine learning model, method 200 returns to block 212. In response to the determination that the training set T contains sufficient training data to train the machine learning model, method 200 continues to block 228.

[0068] At 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 training. In the case of a neural network, for example, the input values ​​of a given input / output mapping are input into 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 in the neural network are then adjusted according to a learning algorithm (e.g., backpropagation, etc.), and the procedure is repeated for other input / output mappings in the training set T.

[0069] In some embodiments, before training the machine learning model, the processing logic may perform an outlier detection method to remove anomalies from the training set T. The outlier detection method may include techniques for identifying values ​​that are significantly different from most of the training data. Such values ​​may be generated by errors, noise, etc.

[0070] At block 230, the processing logic performs a calibration process on the trained machine learning model. In some embodiments, the processing logic may compare the desired behavior of the processing chamber subsystem with the current behavior of the processing chamber subsystem based on the difference between the predicted behavior and the current behavior. For example, the processing logic may compare one or more values ​​associated with predicted data of the pressure subsystem, flow subsystem, or temperature subsystem with one or more values ​​associated with the current measurement behavior of the pressure subsystem, flow subsystem, or temperature subsystem, respectively.

[0071] Following block 230, the machine learning model can be used to generate one or more values ​​indicating the failure mode (e.g., abnormal behavior) of the processing chamber subsystem, generate predictive data indicating the failure type (e.g., problem, failure, etc.), and / or perform corrective actions to correct suspected problems or failures. Predictive data can be generated by comparing the failure mode with a library of known failure modes.

[0072] In some embodiments, the manufacturing system may include more than one processing chamber. For example, the example manufacturing system 300 of Figure 3 illustrates multiple processing chambers 314, 316, 318. It should be noted that in some embodiments, data obtained to train a machine learning model and data collected to be provided as input to the machine learning model may be associated with the same processing chamber of the manufacturing system. In other or similar embodiments, data obtained to train a machine learning model and data collected to be provided as input to the machine learning model may be associated with different processing chambers of the manufacturing system. In other or similar embodiments, data obtained to train a machine learning model may be associated with a processing chamber of a first manufacturing system and data collected to be provided as input to the machine learning model may be associated with a processing chamber of a second manufacturing system.

[0073] Figure 3 is a top schematic diagram of an example manufacturing system 300 according to the present disclosure. The manufacturing system 300 can perform one or more processes on a substrate 302. The substrate 302 can be any suitable rigid, fixed-size planar article, such as, for example, a silicon disk or wafer, a patterned wafer, a glass plate, or the like, which is suitable for manufacturing electronic components or circuit components thereon.

[0074] The manufacturing system 300 may include a processing tool 304 and a factory interface 306 coupled to the processing tool 304. The processing tool 304 may include a housing 308 having a transfer chamber 310 therein. The transfer chamber 310 may include one or more process chambers (also referred to as processing chambers) 314, 316, 318 disposed around and coupled thereto. The process chambers 314, 316, 318 may be coupled to the transfer chamber 310 via corresponding ports 108 (such as slit valves or the like). The transfer chamber 310 may also include a transfer chamber robot 312 configured to transfer a substrate 302 between the process chambers 314, 316, 318, loading gate 320, etc. The transfer chamber robot 312 may include one or more arms, wherein each arm includes one or more links and one or more end effectors at each end of each arm. The end effectors may be configured to handle specific objects, such as wafers. Alternatively or additionally, the end effector is configured to transport objects, such as handling assembly rings. In some embodiments, the transfer chamber robot 312 is a selective compliance assembly robot arm (SCARA) robot, such as a 2-link SCARA robot, a 3-link SCARA robot, a 4-link SCARA robot, and so on.

[0075] The processing chamber robot 312 may further include one or more sensors. The sensors may be used to characterize, read, or measure one or more states of the processing chambers 314, 316, 318. The sensors may include one or more of the following: accelerometers, distance sensors (e.g., for determining the height, width, or length between two objects), cameras (e.g., high-resolution cameras, high-speed cameras, etc.), capacitance sensors, reflectometers, pyrometers (e.g., remote sensing thermometers, infrared cameras, etc.), laser-induced fluorescence spectrometers, fiber optic elements, or any other type of sensor.

[0076] An accelerometer can be used to detect and correct (or calibrate) vibration and position noise of the transmission chamber robot 312. A distance sensor can be used to detect corrosion and / or erosion on the chuck (stage), edge ring, spray head, walls, or any other component of the processing chambers 314, 316, 318. For example, during an etching process, the edge ring can be used to promote uniformity along the substrate surface. However, etching can erode the edge ring. Thus, a position sensor can be used to detect the erosion by measuring the distance between the top surface of the edge ring and, for example, the top plane of the substrate. A camera can record cross-sections of the processing chambers 314, 316, 318 for visual inspection by an operator. A capacitor sensor can be used to detect the position of the spray head used for gas distribution inside the processing chambers 314, 316, 318, determine substrate level, detect corrosion, etc. A reflectometer can be used to detect the quality of the aging film on the walls of the processing chambers 314, 316, 318. For example, a reflectometer can generate light onto the walls of processing chambers 314, 316, and 318 and record the reflectance index of the reflected light. A pyrometer can be used to detect the temperature uniformity of the heaters in processing chambers 314, 316, and 318, detect hot spots inside processing chambers 314, 316, and 318, etc. The transfer chamber robot 312 may include any number or combination of the sensors mentioned above or other sensors.

[0077] One or more sensors may be coupled to the end effector of the transfer chamber robot 312, one or more links of the transfer chamber robot 312, or any other cross-section of the transfer chamber robot 312. In some embodiments, the transfer chamber robot 312 may include additional links and / or more degrees of freedom compared to those required for the transfer substrate. The additional links and / or degrees of freedom may be used to manipulate the sensors. Specifically, the transfer chamber robot 312 may include one or more additional links to be coupled to the sensors, and the links (or the transfer chamber robot 312) may include one or more additional degrees of freedom to translate, rotate, and / or position the sensors within the processing chambers 314, 316, 318. For example, the transfer chamber robot 312 may include additional links coupled to a high-resolution camera capable of rotating the camera within the processing chambers 314, 316, 318.

[0078] In some embodiments, the sensor is coupled to one or more of a power link and / or a data link. The power link can be any wired or wireless (e.g., inductive) connection capable of providing power to the sensor. In some embodiments, the power link is a similar or identical system used to provide power to other functions of the chamber robot 312 (e.g., linkage movement, effector operation, etc.). In some embodiments, the power link is a system independent of another power link used to provide power to other functions of the chamber robot 312. The data link can be any wired or wireless (WiFi, Bluetooth, Internet-based, etc.) connection used to provide or retrieve data from the sensor. For example, the data link can be used to provide instructions to the sensor for measurement or reading, to send collected data to an interface (user interface) or a data storage system, etc. In some embodiments, the data link is a system independent of another data link, which provides instructions and communicates with the transfer chamber robot 312 to enable the transfer chamber robot 312 to transfer and position the substrate between the transfer chambers 314, 316, 318 and the loading gate 320.

[0079] Processing chambers 314, 316, and 318 can be adapted to perform any number of processes on substrate 302. The same or different substrate processes can occur in each processing chamber 314, 316, and 318. 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 similar processes. Other processes can be performed on the substrate within them. Processing chambers 314, 316, and 318 can each include one or more sensors configured to capture data from substrate 302 before, after, or during substrate processes. For example, one or more sensors can be configured to capture spectral and / or non-spectral data of a portion of substrate 302 during substrate processes. In other or similar embodiments, one or more sensors may be configured to capture data associated with the environment within the processing chambers 314, 316, 318 before, after, or during the substrate manufacturing process. For example, one or more sensors may be configured to capture data associated with temperature, pressure, gas concentration, etc., of the environment within the processing chambers 314, 316, 318 during the substrate manufacturing process.

[0080] Load gate 320 may also be coupled to housing 308 and transfer chamber 310. Load gate 320 may be configured to mate with and be coupled to transfer chamber 310 and fab interface 306 on one side. Load gate 320 may have an environmentally controlled atmosphere, which in some embodiments may be changed from a vacuum environment (where substrates may be transferred to and from transfer chamber 310) to an inert gas environment at or near atmospheric pressure (where substrates may be transferred to and from fab interface 306). Fab interface 306 may be any suitable housing, such as, for example, an Equipment Front End Module (EFEM). Fab interface 306 may be configured to receive substrate 302 from substrate carriers 322 (e.g., front-opening wafer transfer cassettes (FOUPs)) located at various loading ports 324 of fab interface 306. The factory interface robot 326 (shown in dashed lines) can be configured to transfer substrate 302 between a carrier (also called a container) 322 and a loading gate 320. The carrier 322 can be a substrate storage carrier or a replacement for a portion of the storage carrier.

[0081] The manufacturing system 300 can 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 provide information via the GUI about the target thickness distribution of films deposited on the surface of the substrate 302 during deposition processes performed in the processing chambers 314, 316, 318. According to the embodiments described herein, the client device may also provide information about modifications to the process formulation, given a corresponding set of deposition settings predicted to correspond to the target distribution.

[0082] The manufacturing system 300 may also include a system controller 328. The system controller 328 may be and / or include computing devices, such as personal computers, server computers, programmable logic controllers (PLCs), microcontrollers, etc. The system controller 328 may include one or more processing devices, which may be general-purpose processing devices, such as microprocessors, central processing units, 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 implementing other instruction sets or combinations thereof. The processing device may 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. System controller 328 may include data storage devices (e.g., one or more disk drives and / or solid-state drives), main memory, static memory, a network interface, and / or other components. System controller 328 may execute instructions to perform any one or more of the methodologies and / or embodiments described herein. In some embodiments, system controller 328 may execute instructions to perform one or more operations at manufacturing system 300 according to a process recipe. Instructions may be stored on a computer-readable storage medium, which may include main memory, static memory, secondary storage, and / or processing devices (during instruction execution).

[0083] System controller 328 may receive data from sensors included on or within various parts of manufacturing system 300, such as processing chambers 314, 316, 318, transfer chamber 310, loading gate 320, etc. In some embodiments, the data received by system controller 328 may include spectral and / or non-spectral data of a portion of substrate 320. In other or similar embodiments, as previously described, the data received by system controller 328 may include data associated with processing substrate 302 at processing chambers 314, 316, 318. For the purposes of this description, system controller 328 is described as receiving data from sensors included within processing chambers 314, 316, 318. However, according to the embodiments described herein, system controller 328 may receive data from any part of manufacturing system 300 and may use the data received from that part. In an illustrative example, system controller 328 may receive data from one or more sensors in processing chambers 314, 316, and 318 before, after, or during substrate fabrication in processing chambers 314, 316, and 318. Data received from sensors in various parts of manufacturing system 300 may be stored in data storage 350. Data storage 350 may be included as a component within system controller 328 or may be a component separate from system controller 328.

[0084] Figure 4 is a schematic cross-sectional side view of a processing chamber 400 according to an embodiment of the present disclosure. In some embodiments, the processing chamber 400 may correspond to the processing chambers 314, 316, 318 described with respect to Figure 3. The processing chamber 400 may be used in processes in which a corrosive plasma environment is provided. For example, the processing chamber 400 may be a chamber used for a plasma etcher or plasma etching reactor, etc. In another example, as previously described, the processing chamber may be a chamber used for a deposition process. In some embodiments, the processing chamber 400 may be any chamber used in an electronic component manufacturing system. As discussed, a transfer chamber robot 312 may enter the processing chamber 400 and perform reading, measurement, and data collection using one or more sensors.

[0085] In one embodiment, the processing chamber 400 includes a chamber body 402 that encloses an internal volume 406 and a spray head 430. The spray head 430 may include a spray head base and a spray head gas distribution plate. Alternatively, the spray head 430 may be replaced by a cover and nozzle in some embodiments, or by a plurality of disc-shaped spray head compartments and a plasma generation unit in other embodiments. The chamber body 402 may be made of aluminum, stainless steel, or other suitable materials such as titanium (Ti). The chamber body 402 generally includes sidewalls 408 and a bottom 410. An exhaust port 426 may be defined in the chamber body 402 and may couple the internal volume 406 to a flow control device 428. The flow control device 428 may include one or more pumps and throttle valves for evacuating and regulating the pressure of the internal volume 406 of the processing chamber 400.

[0086] The spray head 430 may be supported on the sidewall 408 of the chamber body 402. The spray head 420 (or cover) may open to allow access to the internal volume 406 of the processing chamber 400 and may provide a seal for the processing chamber 400 when closed. A gas panel 458 may be coupled to the processing chamber 400 to supply processing and / or cleaning gases to the internal volume 406 via a supply line 412 through the spray head 430 or cover and nozzles (e.g., through holes and nozzles in the spray head or cover). For example, the gas panel 458 may provide a precursor of 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 spray head 430 may include a gas distribution plate (GDP) and may have a plurality of gas delivery orifices 432 (also referred to as channels) throughout the GDP. A substrate support assembly 448 is disposed in the internal volume 406 of the processing chamber 400 below the spray head 430. The substrate support assembly 448 holds the substrate 302 in place during processing (e.g., during the deposition process).

[0087] In some embodiments, the processing chamber 400 may include a metering device (not shown) configured to generate in-situ metering measurements during a process performed at the processing chamber 400. The metering device may be operatively coupled to a system controller (e.g., system controller 328, as previously described). In some embodiments, the metering device may be configured to generate metering measurements (e.g., thickness) of the film 451 during a particular instance of the deposition process. The system controller may generate a thickness distribution of the film 451 based on the metering measurements received from the metering device. In other or similar embodiments, the processing chamber 400 does not include a metering device. In this embodiment, after the deposition process is completed at the processing chamber 400, the system controller may receive one or more metering measurements of the film 451. The system controller may determine a deposition rate based on one or more metering measurements and may correlate the generated thickness distribution of the film 451 based on the determined concentration gradient of the deposition process and the determined deposition rate.

[0088] Figure 5 is a schematic top view of a processing tool 500 according to an embodiment of the present disclosure. In some embodiments, the processing tool 500 may correspond to the processing tool 504 described with respect to Figure 3. The processing tool 500 may include processing chambers 510A-510F, a transfer chamber 515, and a transfer chamber robot 520. The transfer chamber robot 520 may include end effectors 525A and 525B. End effector 525A may include sensors 530A and 530B. Sensors 530A and 530B may include one or more of the following: accelerometer, distance sensor, camera, capacitance sensor, reflectometer, pyrometer, laser-induced fluorescence spectrometer, fiber optic element, etc.

[0089] The transfer chamber robot 520 can locate end effectors 525A, 525B within any of the processing chambers 510A-510F. Figure 5 illustrates, by way of illustrative example, an end effector 525A located within processing chamber 510C. Using sensors 530A and 530B, the transfer chamber robot 520 can read from and / or measure processing chamber 510C. In some embodiments, the sensors and / or the transfer chamber robot 520 include processing devices such as a central processing unit (CPU), microcontroller, programmable logic controller (PLC), system-on-a-chip (SoC), server computer, or other suitable type of computing device. The processing device can be configured to execute programming instructions relating to the operation of the sensors. The processing device can receive feedback signals from the sensor devices and calculate the signals into sensor data (e.g., temperature, video data, position data, etc.). The processing device can further send control signals to the sensors based on the received instructions. In some embodiments, the processing device is configured for high-speed feedback processing and may include, for example, an EPM. In some embodiments, the processing device is configured to transmit or send feedback signals and / or sensor data to an interface (e.g., a user interface), data storage, etc.

[0090] Figure 6 is a schematic top view of a link assembly 600 for a transfer chamber robot according to an embodiment of the present disclosure. The link assembly 600 may include a first link 610, a second link 615, and a sensor 620. The sensor 620 may be coupled to the second link 615. The sensor 620 may include one or more of the following: an accelerometer, a distance sensor, a camera, a capacitance sensor, a reflectometer, a pyrometer, a laser-induced fluorescence spectrometer, a fiber optic element, etc. By way of illustrative example, the second link 615 may be pin-coupled to the first link 610, thereby causing the second link 615 (and the sensor 620) to move in an arcuate motion 625. The first link 610 may be coupled to the transfer chamber robot, an end effector of the transfer chamber robot, etc., via another link of the transfer chamber robot.

[0091] Figure 7 is a flowchart of a method 700 for controlling a transfer chamber robot to perform measurements using sensors, according to the present disclosure. Method 700 is executed by processing logic, which may include hardware (circuit systems, dedicated logic, etc.), software (such as running on a general-purpose computer system or a dedicated machine), firmware, or combinations thereof. In one embodiment, method 700 may be executed by a computer system (such as system controller 128 of Figure 1). In other or similar embodiments, one or more operations of method 700 may be executed by one or more other machines not depicted in the figures.

[0092] At block 710, the processing logic locates one or more sensors within the processing chamber. The one or more sensors may be coupled to the transfer chamber robot. For example, the processing logic may locate the end effector of the transfer chamber robot to which the sensor is attached, the link of the transfer chamber robot to which the sensor is attached, or any combination thereof. The processing logic may locate the sensors in response to user input (e.g., via a user interface), in response to predetermined commands (e.g., scheduling commands), etc. In some embodiments, the processing logic may use a database or library containing data about the location of sensors within the processing chamber based on the type of sensor and / or processing chamber.

[0093] At block 720, the processing logic obtains sensor data from one or more sensors of the transfer chamber robot. For example, one or more sensors may capture spectral and / or non-spectral data of any part of the component associated with the processing chamber. Furthermore, one or more sensors may be configured to capture data associated with the environment within the processing chamber. For example, one or more sensors may be configured to capture data associated with temperature, pressure, gas concentration, etc., of the environment within the processing chamber. In some embodiments, once positioned, the processing logic may move the sensors within the processing chamber (by moving links, end effectors, etc.) to collect sensor data. Movement may be based on automatic movement (e.g., predetermined movement) or manual movement based on user input via a user interface, controller (e.g., joystick, touchscreen, etc.). For example, in embodiments where the sensors are cameras, the user may guide the camera to other locations within the processing chamber to record video and / or audio data. Sensor data may be sent to the user interface, database structure, etc.

[0094] At block 730, the processing logic removes the sensor from the processing chamber. For example, the processing logic may locate the sensor in the transfer chamber or in a different processing chamber.

[0095] Figure 8 is a flowchart of a method 800 for determining the failure type of a processing chamber subsystem using a machine learning model, according to a pattern disclosed herein. Method 800 is executed by processing logic, which may include hardware (circuit systems, dedicated logic, etc.), software (such as running on a general-purpose computer system or a dedicated machine), firmware, or combinations thereof. In one embodiment, method 800 may be executed by a computing system (such as computer system architecture 100 of Figure 1). In other or similar embodiments, one or more operations of method 800 may be executed by one or more other machines not depicted in the figures. In some patterns, one or more operations of method 800 may be executed by server machine 170, server machine 180, and / or prediction server 112.

[0096] At block 810, the processing logic obtains sensor data associated with an operation performed in the processing chamber. In some embodiments, the operation may include a deposition process performed in the processing chamber to deposit one or more films on a substrate surface, an etching process performed on one or more films on a substrate surface, etc. The operation may be performed according to a formulation. The sensor data may include one or more values ​​of the following: temperature (e.g., heater temperature), spacing, pressure, high-frequency radio frequency, voltage of the electrostatic chuck, current, material flow rate, power, voltage, etc. The sensor data may be associated with or indicate manufacturing parameters, such as hardware parameters, such as the setup or components of manufacturing equipment 124 (e.g., size, type, etc.), or processing parameters of manufacturing equipment 124. Sensor data may be obtained using sensor 126.

[0097] At block 812, the processing logic applies a machine learning model (e.g., model 190) to the acquired sensor data. The machine learning model can be used to generate one or more values ​​associated with the desired behavior of the processing chamber subsystem. For example, the machine learning model can use an algorithm to generate predicted behavior of the processing chamber subsystem using a training set T. In some embodiments, the machine learning model is trained using historical sensor data of the processing chamber subsystem and task data associated with a recipe for performing the operation.

[0098] At block 814, the processing logic generates an output based on sensor data via a machine learning model. In some embodiments, the output may be a value indicating a mode (e.g., a failure mode). Specifically, the output may include predicted data indicating whether current data indicates a failure experienced by the processing chamber. In some embodiments, the output is at least one value indicating the difference between the desired behavior of the processing chamber subsystem and the actual behavior of the processing chamber subsystem. Specifically, the value may indicate the difference between the actual value of the sensor set associated with the subsystem and the desired value of the sensor set. Failure may include mechanical failure, high or low pressure, high or low gas flow, high or low temperature, etc.

[0099] At block 816, the processing logic determines whether the processing chamber subsystem has experienced a failure. In some embodiments, failure may include mechanical malfunction, high or low pressure, high or low gas flow rate, high or low temperature, erosion, corrosion, degradation, etc. In some embodiments, the processing logic may determine whether the processing chamber subsystem has experienced a failure by comparing the output with a predetermined threshold. In some embodiments, the processing logic may determine whether the processing chamber subsystem has experienced a failure by determining that the output fails to match the desired behavior. In response to the processing logic determining that the processing chamber subsystem has not experienced a failure (e.g., the output value does not exceed a predetermined threshold), the processing logic may proceed to block 810. In response to the processing logic determining that the processing chamber subsystem is experiencing a failure (e.g., the output value exceeds a predetermined threshold), the processing logic may proceed to block 818.

[0100] At block 818, the processing logic can identify the failure type based on the output. In some embodiments, the processing logic can compare the failure mode with a manufacturing data chart and / or a library of known failure modes to determine the failure type based on the similarity of the failure mode when compared with known failure modes or the manufacturing data chart. In some embodiments, natural language processing can be used to extract the failure type from the manufacturing data chart, and the failure type is then associated with the corresponding failure mode. In some embodiments, the failure type can be displayed on the user interface (to the user).

[0101] At block 820, the processing logic may perform (or suggest) corrective actions based on identified failures. In some embodiments, the corrective actions may be determined based on data obtained from a fault code library. In some embodiments, the corrective actions may include generating an alarm or indication of the determined problem to the client device 120. In some embodiments, the corrective actions may include processing logic indicating the type of fault or failure, the cause of the fault or failure, and / or the suggested corrective actions. In some embodiments, the corrective actions may include processing logic adjusting one or more parameters of the deposition process formulation based on the desired properties of the film (e.g., temperature setting of the processing chamber, pressure setting of the processing chamber, flow rate setting of precursors of materials included in the film deposited on the substrate surface, etc.). In some embodiments, the deposition process formulation may be adjusted before, during (e.g., immediately), or after the deposition process.

[0102] Figure 9 is a block diagram illustrating a computer system 900 according to certain embodiments. In some embodiments, the computer system 900 may be connected (e.g., via a network, such as a local area network (LAN), intranet, extranet, or internet) to other computer systems. The computer system 900 may operate as a server or client computer in a client-server network environment, or as a peer point computer in a peer-to-peer or distributed network environment. The computer system 900 may be executed by a personal computer (PC), tablet PC, set-top box (STB), personal digital assistant (PDA), cellular phone, network device, server, network router, switch or bridge, or any machine capable of executing a set of instructions (continuously or otherwise) that specifies the actions to be taken by that machine. Additionally, the term "computer" should include any set of computers that independently or jointly execute a set of instructions (or multiple sets of instructions) to perform any one or more methods described herein.

[0103] In another embodiment, the computer system 900 may include a processing device 902 that can communicate with each other via a bus 908, volatile memory 904 (e.g., random access memory (RAM)), non-volatile memory 906 (e.g., read-only memory (ROM) or electronically erasable programmable ROM (EEPROM)), and data storage device 916.

[0104] The processing device 902 may be provided by one or more processors, such as general-purpose processors (e.g., complex instruction set computing (CISC) microprocessors, reduced instruction set computing (RISC) microprocessors, very long instruction word (VLIW) microprocessors, microprocessors that implement other types of instruction sets, or microprocessors that implement a combination of various types of instruction sets) or special-purpose processors (e.g., application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), or network processors).

[0105] The computer system 900 may further include a network interface device 922 (e.g., coupled to a network 974). The computer system 900 may also include a video display unit 910 (e.g., an LCD), an alphanumeric input device 912 (e.g., a keyboard), a cursor control device 914 (e.g., a mouse), and a signal generation device 920.

[0106] In some embodiments, the data storage device 916 may include a non-transitory computer-readable storage medium 924 on which instructions 926 encoding any one or more of the methods or functions described herein may be stored, including the instruction encoding components of Figure 1 (e.g., correction action component 122, prediction component 114, etc.) and used to implement the methods described herein.

[0107] Instruction 926 may also reside wholly or partially in volatile memory 904 and / or processing device 902 during its execution by computer system 900. Therefore, volatile memory 904 and processing device 902 may also constitute machine-readable storage media.

[0108] Although computer-readable storage media 924 is illustrated as a single medium in the illustrative examples, the term "computer-readable storage media" should include single or multiple media (e.g., centralized or distributed databases, and / or associated caches and servers) storing one or more sets of executable instructions. The term "computer-readable storage media" should also include any tangible medium capable of storing or encoding a set of instructions for execution by a computer, which causes the computer to perform any or more of the methods described herein. The term "computer-readable storage media" should include, but is not limited to, solid-state memory, optical media, and magnetic media.

[0109] The methods, components, and features described herein may be implemented by discrete hardware components or integrated into the functionality of other hardware components (such as ASICs, FPGAs, DSPs, or similar devices). Furthermore, the methods, components, and features may be implemented by functional circuitry within firmware modules or hardware devices. Additionally, the methods, components, and features may be implemented in any combination of hardware devices and computer program components, or implemented as a computer program.

[0110] Unless otherwise specifically stated, terms such as “receive,” “execute,” “provide,” “obtain,” “cause,” “access,” “determine,” “add,” “use,” “train,” or similar refer to actions and processes performed or implemented by a computer system that manipulate and transform data represented as physical (electronic) quantities in the registers and memory of a computer system into other data similarly represented as physical quantities in the memory or registers or other such information storage, transmission, or display devices of a computer system. Furthermore, as used herein, the terms “first,” “second,” “third,” “fourth,” etc., are designations used to distinguish different elements and their numerical designations may not have ordinal meaning.

[0111] The examples described herein also relate to an apparatus for performing the methods described herein. This apparatus may be specially configured to perform the methods described herein, or may include a general-purpose computer system designed by selective programming of a computer program stored in a computer system. Such a computer program may be stored in a computer-readable physical storage medium.

[0112] The methods and illustrative examples described herein are not inherently related to any particular computer or other device. Various general-purpose systems can be used in accordance with the teachings described herein, or it may be convenient to construct more specialized devices to perform the methods described herein and / or each of their individual functions, routines, subroutines, or operations. Examples of structures for various such systems are set forth in the foregoing description.

[0113] The above description is intended to be illustrative and not restrictive. Although this disclosure has been described with reference to specific illustrative examples and embodiments, it will be appreciated that this disclosure is not limited to the described examples and embodiments. The scope of this disclosure should be determined by referring to the appended claims together with the full scope of the equivalents conferred by such claims.

[0114] The foregoing description sets forth several specific details, such as examples of particular systems, components, methods, etc., to provide a good understanding of several 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 such specific details. In other instances, components or methods that are not described in detail and are well-known are provided in a simple block diagram format to avoid unnecessarily obscuring the present disclosure. Therefore, the specific details set forth are merely exemplary. Specific implementations may be modified from such exemplary details and still contemplated within the scope of the present disclosure.

[0115] Throughout this specification, references to "an embodiment" or "an embodiment" mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Therefore, the phrases "in an embodiment" or "in an embodiment" appearing in various places throughout this specification do not necessarily refer to the same embodiment. Additionally, the term "or" is intended to mean an inclusive "or" rather than an exclusionary "or". When the terms "about" or "approximately" are used herein, it is intended to mean that the provided nominal values ​​are accurate within ±10%. [Simplified Explanation of the Diagram]

[0009] This disclosure is illustrated by way of example in the accompanying drawings and is not intended to be limiting, in which like references indicate similar elements. It should be noted that in this disclosure, different designations for "an" or "one" embodiments do not necessarily refer to the same embodiment, and such designations mean at least one.

[0010] Figure 1 is a block diagram illustrating an exemplary system architecture according to certain embodiments.

[0011] Figure 2 is a flowchart of a method for training a machine learning model according to certain embodiments.

[0012] Figure 3 is a top view of an example manufacturing system according to certain embodiments.

[0013] Figure 4 is a schematic cross-sectional side view of an example processing chamber of an example manufacturing system according to certain embodiments.

[0014] Figure 5 is a schematic top view of a processing tool according to an embodiment of the present disclosure.

[0015] Figure 6 is a schematic top view of a link assembly of a transfer chamber robot according to an embodiment of the present disclosure.

[0016] Figure 7 is a flowchart of a method for controlling a transfer chamber robot to perform measurements using sensors, according to the present disclosure.

[0017] Figure 8 is a flowchart of a method for determining the failure type of a chamber subsystem using a machine learning model, according to certain embodiments.

[0018] Figure 9 is a block diagram illustrating a computer system according to certain embodiments. [Biomaterial Storage]

[0117] Domestic storage information (please note in order of storage institution, date, and number): None. International storage information (please note in order of storage country, institution, date, and number): None.

Claims

1. A processing tool for an electronic component manufacturing system, the processing tool comprising: a transfer chamber; a processing chamber coupled to the transfer chamber; and a transfer chamber robot including an end effector and configured to transfer a substrate to and from the processing chamber, wherein the transfer chamber robot is coupled to a sensor configured to perform measurements within the processing chamber, wherein the sensor can be positioned independently of the end effector via an additional degree of freedom.

2. The processing tool as claimed in claim 1, wherein the sensor is coupled to one end effector of the transfer chamber robot.

3. The processing tool as claimed in claim 1, wherein the sensor is coupled to a link of the transfer chamber robot.

4. The processing tool as claimed in claim 1, wherein the sensor comprises at least one of the following: an accelerometer, a distance sensor, a camera, a capacitance sensor, a reflectometer, a pyrometer, a laser-induced fluorescence spectrometer, or a fiber optic element.

5. The processing tool as claimed in claim 1, wherein the sensor is coupled to a power link capable of providing power to the sensor.

6. The processing tool as claimed in claim 1, wherein the sensor is coupled to a data link capable of transmitting the measurements to a user interface or a data storage system.

7. An electronic component manufacturing system comprising: a loading gate and a processing tool, wherein the processing tool includes: a transfer chamber; a processing chamber coupled to the transfer chamber; and a transfer chamber robot including an end effector and configured to transfer a substrate from the loading gate to the processing chamber and vice versa, wherein the transfer chamber robot is coupled to a sensor configured to perform measurements inside the processing chamber, wherein the sensor can be positioned independently of the end effector via an additional degree of freedom.

8. The electronic component manufacturing system as claimed in claim 7, wherein the sensor is coupled to one end effector of the transfer chamber robot.

9. The electronic component manufacturing system as claimed in claim 7, wherein the sensor is coupled to a link of the transfer chamber robot.

10. The electronic component manufacturing system of claim 7, wherein the sensor comprises at least one of the following: an accelerometer, a distance sensor, a camera, a capacitance sensor, a reflectometer, a pyrometer, a laser-induced fluorescence spectrometer, or a fiber optic element.

11. The electronic component manufacturing system of claim 7, wherein the sensor is coupled to a power link capable of providing power to the sensor.

12. The electronic component manufacturing system of claim 7, wherein the sensor is coupled to a data link capable of transmitting such measurements to a user interface or a data storage system.

13. A transfer chamber robot comprising: an arm assembly including a plurality of links; an end effector coupled to the arm assembly, wherein the end effector is configured to transfer a substrate to and from a processing chamber; and a sensor coupled to the arm assembly and configured to perform measurements inside the processing chamber, wherein the sensor can be positioned independently of the end effector via an additional degree of freedom.

14. The transfer chamber robot as claimed in claim 13, wherein the sensor is coupled to the end effector of the transfer chamber robot.

15. The transfer chamber robot as claimed in claim 13, wherein the sensor is coupled to one link of the plurality of links.

16. The transfer chamber robot of claim 13, wherein the sensor comprises at least one of the following: an accelerometer, a distance sensor, a camera, a capacitance sensor, a reflectometer, a pyrometer, a laser-induced fluorescence spectrometer, or a fiber optic element.

17. The transfer chamber robot as claimed in claim 13, wherein the sensor can be located independently of the end effector coupled to the transfer chamber robot.

18. A method for determining a failure type of a subsystem of a processing chamber, comprising the steps of: locating a portion of a transfer chamber robot within a processing chamber by a processor, the portion including at least one sensor, wherein the portion can be located independently of an end effector coupled to the transfer chamber robot via an additional degree of freedom; obtaining sensor data associated with the processing chamber using the one or more sensors; and removing the portion of the transfer chamber robot from the processing chamber.

Images