Analysis of Multi-Run Periodic Processing Procedure

Abstract

The method includes receiving time trace sensor data associated with a substrate processing procedure. The substrate processing procedure includes two or more sets of processing states. At least a first set of processing states and a second set of processing states each include one or more operations that are repeatedly executed. The method further includes separating first and second portions of the time trace sensor data corresponding to the first and second sets of processing states into first and second pluralities of cycle data. The method further includes processing the first plurality of cycle data and the second plurality of cycle data to generate summary data. The method further includes providing an alert to a user. The alert is based on the summary data.

Description

Technical Field

[0001] The present disclosure relates to a diagnostic method for analyzing sensor data associated with a processing procedure, and more particularly to a diagnostic method for analyzing sensor data associated with a multi-run processing procedure including a cycle and / or a loop operation.

Background Art

[0002] Products can be made by performing one or more manufacturing processes using manufacturing equipment. For example, semiconductor manufacturing equipment can be used to fabricate substrates through semiconductor manufacturing processes. Products having specific characteristics suitable for the target application should be made. Understanding and controlling the characteristics within the manufacturing chamber helps in the consistent fabrication of products.

Summary of the Invention

[0003] The following is a simplified summary of the present disclosure to provide a basic understanding of some aspects of the present disclosure. This summary is not an extensive overview of the present disclosure. It is not intended to identify key or critical elements of the present disclosure, nor to delineate any scope of particular embodiments of the present disclosure or any scope of the claims. The sole purpose of this summary is to present some concepts of the present disclosure in a simplified form as a prelude to the more detailed description that follows.

[0004] In one aspect of the present disclosure, the method includes receiving time trace sensor data associated with a substrate processing procedure. The substrate processing procedure includes two or more sets of processing states. The first set of processing states and the second set of processing states each include one or more operations that are repeatedly executed. The method further includes separating a first portion of the time trace sensor data associated with the first set of processing states into a first plurality of periodic data. Each of the first plurality of periodic data is associated with one or more operations that are repeatedly executed. The method further includes separating a second portion of the time trace sensor data corresponding to the second set of processing states into a second plurality of periodic data. Each of the second plurality of periodic data is associated with one or more operations that are repeatedly executed. The method further includes processing the first plurality of periodic data and the second plurality of periodic data to generate summary data. The method further includes providing an alert to a user. The alert is based on the summary data.

[0005] In another aspect of the present disclosure, the system includes a memory and a processing device coupled to the memory. The processing device is configured to receive time trace sensor data associated with a substrate processing procedure. The substrate processing procedure includes two or more sets of processing states. The first set of processing states and the second set of processing states each include one or more operations that are repeatedly executed. The processing device is further configured to separate a first portion of the time trace data associated with the first set of processing states into a first plurality of periodic data. Each of the first plurality of periodic data is associated with one or more operations that are repeatedly executed. The processing device is further configured to separate a second portion of the time trace sensor data associated with the second set of processing states into a second set of periodic data. Each of the second plurality of periodic data is associated with one or more operations that are repeatedly executed. The processing device is further configured to process the first plurality of periodic data and the second plurality of periodic data to generate summary data. The processing device is further configured to provide an alert to a user based on the summary data.

[0006] In another aspect of the present disclosure, a non-transitory machine-readable storage medium stores instructions. When executed, the instructions cause a processing device to perform operations. The operations include receiving time trace sensor data associated with a substrate processing procedure. The substrate processing procedure includes two or more sets of processing states. The first set of processing states and the second set of processing states each include one or more operations that are repeatedly executed. The operations further include separating a first portion of the time trace sensor data corresponding to the first set of processing states into a first plurality of cycle data. Each of the first plurality of cycle data is associated with one or more operations that are repeatedly executed. The operations further include separating a second portion of the time trace sensor data corresponding to the second set of processing states into a second plurality of cycle data. Each of the second plurality of cycle data is associated with one or more operations that are repeatedly executed. The operations further include processing the first plurality of cycle data and the second plurality of cycle data to generate summary data. The method further includes providing an alert to a user. The alert is based on the summary data.

[0007] The present disclosure is shown by way of example and not limitation in the figures of the accompanying drawings.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

[0009] Techniques related to a diagnostic method for a multi-stage loop manufacturing operation that can be used for diagnosing problems and / or performing corrective actions in manufacturing equipment are described herein. The manufacturing equipment can be used to fabricate products such as substrates (e.g., wafers, semiconductors, displays, photovoltaic devices, etc.). The manufacturing equipment (e.g., manufacturing tool) often includes a processing chamber that isolates the substrate being processed from the environment. The characteristics of the fabricated substrate should meet target characteristic values to facilitate performance, functionality, etc. Abnormalities, drifts, or other differences in the processing environment can result in substrates with sub-optimal performance, e.g., semiconductors that cannot function as intended, and inefficiencies in manufacturing (e.g., additional consumption of time, material energy, etc.). The processing environment can be quantified by various sensors associated with the processing chamber, such as pressure gauges, temperature sensors, sensors indicating power (e.g., voltmeters, etc.), gas flow meters, etc.

[0010] In some systems, the processing procedure can include a series of repetitive (e.g., loop, periodic) operations. For example, the target substrate can include a series of layers stacked on top of each other. Such a structure can be generated by repetitive deposition operations such as staircase deposition operations. In some embodiments, the target substrate configuration can include many layers, such as dozens of layers, hundreds of layers, etc. In such systems (e.g., including loop operations), the analysis of sensor data for anomaly detection, drift detection, equipment or product health assessment, etc. can be very troublesome. Repetitive operations may be indicated by repetitive patterns in the sensor data, which can be difficult to analyze using conventional methods (e.g., statistical metrics). In addition, identifying potentially problematic layers can be very troublesome, even among multiple loop operations reflected in the sensor data.

[0011] In some systems, the processing procedure can include a series of processing runs, such as a series of runs including different processing states, a series of runs during which the substrate is removed from the processing chamber, etc. When separate processing runs are associated with the same substrate, the data analysis procedure becomes complicated. In conventional systems, each processing run may be investigated individually, for example, to discover evidence of errors, defects, insufficient performance, etc. Some systems include multiple processing runs that themselves include loop operations, exacerbating the inefficiency of the analysis.

[0012] In some systems, an investigation into sensor data can be caused by sub-optimal performance, for example, by the production of one or more products having characteristics outside of manufacturing specifications. In some cases, only a portion of the products are subject to performance measurements, such as metrology measurements, to confirm build quality. Performance measurements (e.g., metrology) can be costly, for example, taking a significant amount of time to generate. Manufacturing equipment may continue to be used to produce products while measurements are being performed on other products and / or while products are in a queue for metrology measurements. If the manufacturing equipment has deteriorated (e.g., changed such that the performance of the equipment is sub-optimal due to component aging, drift, faults, etc.), product metrology measurements may not be performed until multiple products are processed using the sub-optimal equipment. As a result, sub-optimal products may be manufactured. Such systems are wasteful with respect to time, energy, and materials wasted in processing sub-optimal products.

[0013] In conventional systems, it is difficult to separate useful sensor data (e.g., identify data indicating corrective actions to be performed in relation to manufacturing equipment from a large amount of sensor data), resulting in measurement-based defect detection. In some cases, sensor data may be observably affected by a drifting, aging, or faulty component before the measurement is observably affected. In such cases, the sensor data can be used to schedule corrective actions to occur concurrently with planned downtime (e.g., preventive maintenance operations) before the measurement is affected, reducing costly unplanned downtime for the manufacturing system. If the sensor data cannot be reliably used, corrective actions may be performed in response to sub-optimal measurement data, resulting in unplanned downtime. In some embodiments, unplanned downtime can incur additional costs, such as shipping by express for replacement components.

[0014] The methods and devices of the present disclosure can address one or more of the above-described deficiencies in conventional solutions. In some embodiments, summary data is enabled and generated that allows for rapid processing times, utilization of standard statistical methods in complex loop procedures, reduction of communication bandwidth, and reduction of the complexity of analyzing all trace data. Generating summary data can include applying statistical methods, machine learning methods, digital twin methods, etc. to trace data (e.g., trace sensor data).

[0015] One or more metrics (e.g., standards of measurement) can be utilized to indicate the health state of a manufacturing equipment system. In some embodiments, summary data can be utilized to generate one or more metric values. The metric values can be used as an indication that further investigation should be performed on a chamber, process, product, component, etc. In some embodiments, metric values (e.g., indicators, quality scores, statistical values, etc.) can be calculated and compared to a second value, such as a golden run (e.g., a process run selected when an acceptable process state is achieved), an average value of several process runs, etc. In some embodiments, multiple metrics (e.g., several statistical measures, several metrics associated with one or more shapes within trace data, etc.) can be generated. In some embodiments, each loop / cycle (or in some embodiments, a group of loops) can be associated with a set of metric values.

[0016] Using the analysis results of the loop procedure, an alarm for the user can be generated. For example, the analysis results can be displayed on an instrument panel (e.g., a graphical user interface). In some embodiments, the graphical user interface can include graphical user interface elements that display data associated with the periodic procedure. Analysis results for indicating potentially defective layers of the substrate can be displayed, for example, metrics (e.g., summary data) selected according to the number of steps / layers in the results can be displayed, results where different steps are shown as different colors on a gradient can be displayed, and so on. The displayed analysis results can include data from steps generated over multiple process runs, can include multiple wafers (e.g., for comparison), and so on.

[0017] Aspects of the present disclosure provide technical advantages compared to conventional solutions. The present disclosure provides a more efficient substrate manufacturing process with minimized waste. If a problem occurs in relation to the processing chamber, the method of the present disclosure can perform corrective measures before the processing of the next product begins, before a sub-optimal product is submitted for quality measurement, before the quality measurement is completed, and so on. In this way, wasteful materials, processing chamber time, and energy supplied to the manufacturing process can be minimized. In addition, the method of the present disclosure can reduce the resolution time, for example, the time elapsed between recognizing that there is a problem associated with the processing chamber and resolving the problem (e.g., by identifying components to be replaced, maintenance to be performed, policy adjustments to be made, etc.). Identifying and correcting the root causes of product quality variations and chamber drift can increase product quality. More precisely adjusting the process parameters to improve material costs, energy, and time can also increase the efficiency of producing acceptable quality products. Identifying aging components and flagging them for replacement or maintenance can reduce costs associated with unplanned downtime, shipping of replacement parts via express delivery, and so on.

[0018] In some embodiments, the present disclosure describes a method that includes receiving time trace sensor data associated with a substrate processing procedure. The substrate processing procedure includes two or more sets of processing states. The first set of processing states and the second set of processing states each include one or more operations that are repeatedly executed. The method further includes separating a first portion of the time trace sensor data corresponding to the first set of processing states into a first plurality of cycle data. Each of the first plurality of cycle data is associated with one or more operations that are repeatedly executed. The method further includes separating a second portion of the time trace sensor data corresponding to the second set of processing states into a second plurality of cycle data. Each of the second plurality is associated with one or more operations that are repeatedly executed. The method further includes processing the first plurality of cycle data and the second plurality of cycle data to generate summary data. The method further includes providing an alert to a user. The alert is based on the summary data.

[0019] In another aspect of the present disclosure, a system includes a memory and a processing device coupled to the memory. The processing device is configured to receive time trace sensor data associated with a substrate processing procedure. The substrate processing procedure includes two or more sets of processing states. The first set of processing states and the second set of processing states each include one or more operations that are repeatedly executed. The processing device is further configured to separate a first portion of the time trace data corresponding to the first set of processing states into a first plurality of cycle data. Each of the first plurality of cycle data is associated with one or more operations that are repeatedly executed. The processing device is further configured to separate a second portion of the time trace sensor data corresponding to the second set of processing states into a second set of cycle data. Each of the second plurality is associated with one or more operations that are repeatedly executed. The processing device is further configured to process the first plurality of cycle data and the second plurality of cycle data to generate summary data. The processing device is further configured to provide an alert to a user based on the summary data.

[0020] In another aspect of the present disclosure, a non-transitory machine-readable storage medium stores instructions. The instructions, when executed, cause a processing device to perform operations. The operations include receiving time trace sensor data associated with a substrate processing procedure. The substrate processing procedure includes two or more sets of processing states. The first set of processing states and the second set of processing states each include one or more operations that are repeatedly executed. The operations further include separating a first portion of the time trace sensor data corresponding to the first set of processing states into a first plurality of cycle data. Each of the first plurality of cycle data is associated with one or more operations that are repeatedly executed. The operations further include separating a second portion of the time trace sensor data corresponding to the second set of processing states into a second plurality of cycle data. Each of the second plurality of cycle data is associated with one or more operations that are repeatedly executed. The operations further include processing the first plurality of cycle data and the second plurality of cycle data to generate summary data. The method further includes providing an alert to a user. The alert is based on the summary data.

[0021] FIG. 1 is a block diagram illustrating an exemplary system 100 (exemplary system architecture) according to some embodiments. System 100 includes a client device 120, manufacturing equipment 124, sensors 126, measurement equipment 128, an analysis server 112, and a data store 140. The analysis server 112 can be part of an analysis system 110.

[0022] Sensor 126 can provide sensor data 142 associated with manufacturing equipment 124 (e.g., associated with the production of corresponding products such as substrates by manufacturing equipment 124). The sensor data 142 can be used to confirm the health status of the equipment and / or the health status of the product (e.g., the quality of the product). The manufacturing equipment 124 can run a run according to a policy or over a period of time to produce a product. In some embodiments, the sensor data 142 can include one or more values such as temperature (e.g., heater temperature), setpoint (SP), pressure, high-frequency radio frequency (HFRF), radio frequency (RF) matching voltage, RF matching current, RF matching capacitor position, electrostatic chuck (ESC) voltage, actuator position, current, flow rate, power, voltage, etc. The sensor data 142 can be associated with manufacturing parameters such as hardware parameters (e.g., settings or components such as size, type, etc.) of the manufacturing equipment 124 or process parameters of the manufacturing equipment 124, or can indicate such manufacturing parameters. Instead, or in addition, data associated with some hardware parameters can be stored as manufacturing parameters 150. The manufacturing parameters 150 can indicate input settings (e.g., heater power, gas flow rate, etc.) for the manufacturing device. When the manufacturing equipment 124 is executing a manufacturing process, the sensor data 142 and / or the manufacturing parameters 150 can be provided (e.g., can be device readings generated during the processing of the substrate). The sensor data 142 can be different for each product (e.g., for each substrate). The substrate can have characteristic values (e.g., film thickness, film strain, etc.) measured by the measuring equipment 128. The measurement data 160 can be of the type of data stored in the data store 140.

[0023] In some embodiments, sensor data 142, measurement data 160, and / or manufacturing parameters 150 can be processed (e.g., by client device 120 and / or analytics server 112). Processing of sensor data 142, measurement data 160, and / or manufacturing parameters 150 can include generating features. In some embodiments, these features can be patterns (e.g., gradients, widths, heights, peaks, etc.) within sensor data 142, measurement data 160, and / or manufacturing parameters 150, or combinations of values from sensor data 142, measurement data 160, and / or manufacturing parameters 150 (e.g., power derived from voltage and current). Sensor data 142 can include features, and those features can be used by analysis component 114 to perform signal processing and / or obtain prediction data 168 for performing corrective actions.

[0024] Each instance (e.g., set) of sensor data 142 can correspond to a product (e.g., a substrate), a set of manufacturing equipment, the type of substrate fabricated by the manufacturing equipment, and so on. Each instance of measurement data 160 and manufacturing parameters 150 can similarly correspond to a product, a set of manufacturing equipment, the type of substrate fabricated by the manufacturing equipment, and so on. Data store 140 can further store information associating sets of different data types, e.g., information indicating that a set of sensor data, a set of measurement data, and a set of manufacturing parameters are all associated with the same product, manufacturing equipment, substrate type, and so on.

[0025] In some embodiments, summary data 162 can be generated using data associated with the processing of one or more products. The summary data 162 can include data representing characteristics of other data. For example, the summary data 162 can be generated from trace sensor data 142. The trace sensor data 142 can include a large amount of data (e.g., data from hundreds of sensors in a tool that obtains hundreds or thousands of measurements per product). The summary data 162 is less cumbersome to operate than the trace sensor data 142 and can be designed to present information (e.g., information indicating a chamber malfunction). In some embodiments, data (e.g., trace sensor data 142) can be provided to a processing device (e.g., analysis server 112, client device 120, etc.) to generate the summary data 162.

[0026] The summary data 162 can include, for example, metadata (e.g., tool ID, recipe name, product ID, product information, etc.), context data (e.g., sensor ID, step number, timestamp, subsystem, etc.), and / or basic statistics (e.g., average, maximum, minimum, quartiles, kurtosis, control limits, etc.). The summary data 162 can include statistical metrics of the loop operation of the processing procedure. For example, the analysis system 110 can separate the trace sensor data into repeating parts (e.g., loops, substrate layers or stages, a set of multiple loops, etc.). The separated trace sensor data can then be used to generate summary data, which can indicate the health or quality of the product or system.

[0027] Summary data 162 can include instructions regarding how the characteristics of the measured data differ from the predictions of a model system such as a golden run (e.g., overshoot, rise time, settling time, steady state value error, etc.). In some embodiments, summary data 162 can be generated based on a portion of the input data, such as only the steady state portion of summary data 162, only the transient portion, etc.

[0028] In some embodiments, analysis system 110 can generate prediction data 168 using machine learning such as supervised machine learning (e.g., the machine learning model can be configured to create labels associated with input data such as measurement predictions, performance predictions, etc.). In some embodiments, analysis system 110 can generate prediction data 168 using unsupervised machine learning (e.g., the machine learning model can be trained with unlabeled data such as a model configured to perform clustering, dimensionality reduction, etc.). In some embodiments, analysis system 110 can generate prediction data 168 using semi-supervised learning (e.g., the machine learning model can be trained using both labeled and unlabeled input data sets).

[0029] Client device 120, manufacturing equipment 124, sensor 126, measurement device 128, analysis server 112, and data store 140 can be coupled to each other via network 130 to generate prediction data 168 and execute corrective actions.

[0030] In some embodiments, network 130 is a public network that provides client device 120 with access to analysis server 112, data store 140, and other publicly available computing devices. In some embodiments, network 130 is a private network that provides client device 120 with access to manufacturing equipment 124, sensors 126, measurement equipment 128, data store 140, and other privately available computing devices. In some embodiments, one or more functions of client device 120 and / or analysis server 112 can be executed by a virtual machine, for example, by utilizing cloud-based services. Network 130 can provide access to such virtual machines. Network 130 can include one or more wide area networks (WANs), local area networks (LANs), wired networks (e.g., Ethernet networks), wireless networks (e.g., 802.11 networks or Wi-Fi networks), cellular networks (e.g., Long Term Evolution (LTE) networks), routers, hubs, switches, server computers, cloud computing networks, and / or combinations thereof.

[0031] The client device 120 can include computing devices such as a personal computer (PC), laptop, mobile phone, smartphone, tablet computer, netbook computer, network-connected television (“smart TV”), network-connected media player (e.g., Blu-ray player), set-top box, over-the-top (OTT) streaming device, operator box, etc. The client device 120 can include a corrective action component 122. The corrective action component 122 can receive user input of instructions associated with the manufacturing equipment 124 (e.g., via a graphical user interface (GUI) displayed via the client device 120). The client device 120 can include a reporting component 123. The reporting component 123 can display warnings (e.g., performance reports) to the user associated with the performance of the manufacturing equipment 124, the quality of the substrate, the quality of the process, etc. In some embodiments, the corrective action component 122 transmits this instruction to the analysis system 110, receives an output (e.g., prediction data 168) from the analysis system 110, determines a corrective action based on this output, and implements the corrective action (e.g., by providing a warning to the user via the reporting component 123). In some embodiments, the corrective action component 122 obtains sensor data 142 associated with the manufacturing equipment 124 (e.g., current sensor data 146) (e.g., from a data store 140, etc.) and provides the sensor data 142 associated with the manufacturing equipment 124 (e.g., current sensor data 146) to the analysis system 110. In some embodiments, the corrective action component 122 stores the sensor data 142 in the data store 140, and the analysis server 112 retrieves the sensor data 142 from the data store 140. In some embodiments, the analysis server 112 can store the output of the model 190 (e.g., prediction data 168) in the data store 140, and the client device 120 can retrieve that output from the data store 140.In some embodiments, the corrective action component 122 receives an instruction for a corrective action from the analysis system 110 and implements the corrective action. Each client device 120 can include an operating system that enables a user to perform one or more of generating, viewing, or editing data (e.g., instructions associated with the manufacturing equipment 124, corrective actions associated with the manufacturing equipment 124, etc.).

[0032] In some embodiments, the measurement data 160 corresponds to past characteristic data of a product (e.g., manufacturing parameters associated with past sensor data 144 and products fabricated using the past manufacturing parameters). The prediction data 168 can include analysis results, such as the output of the analysis system 110, predicted system failures, corrective actions to be performed, maintenance to be performed, etc. In some embodiments, the prediction data 168 is an indication of an anomaly (e.g., an abnormal product, an abnormal component, an abnormal manufacturing equipment 124, abnormal energy usage, etc.), and may also be an indication of one or more causes of those anomalies. In some embodiments, the prediction data 168 is an indication of a change or drift over time in some component such as the manufacturing equipment 124, the sensor 126, the measurement device 128, etc. In some embodiments, the prediction data 168 is an indication of the end of life of a component such as the manufacturing equipment 124, the sensor 126, the measurement device 128, etc.

[0033] Executing a manufacturing process that results in defective products can be costly in terms of time, energy, products, components, manufacturing equipment 124, the cost of identifying defects and discarding defective products, etc. By inputting the sensor data 142 (e.g., manufacturing parameters being used or to be used to manufacture a product) into the analysis system 110, receiving the output of the prediction data 168, and implementing corrective actions based on the prediction data 168, the system 100 can have the technical advantage of avoiding the costs associated with fabricating, identifying, and discarding defective products.

[0034] Executing a manufacturing process that causes a component of manufacturing machine 124 to fail can be costly in terms of downtime, product damage, equipment damage, ordering expedited shipments of replacement components, etc. By inputting sensor data 142 (e.g., indicating manufacturing parameters being used or to be used to manufacture a product) into analysis system 110, receiving an output of prediction data 168, and based on prediction data 168, performing corrective actions (e.g., predicted operational maintenance such as component replacement, processing, cleaning, etc.), system 100 can have the technical advantage of avoiding one or more costs such as unexpected component failures, unplanned downtime, loss of production rate, unexpected equipment failures, product scrap, etc. By monitoring the performance of components, such as manufacturing machine 124, sensor 126, metering device 128, etc. over time, an indication of a deteriorating component can be provided.

[0035] Manufacturing parameters may be sub-optimal for making a product, which can result in costly consequences such as increased consumption of resources (e.g., energy, coolant, gas, etc.), increased amount of time to make a product, increased component failures, increased amount of defective products, etc. By inputting sensor data 142 into analysis system 110, receiving an output of prediction data 168, and performing corrective actions to update (e.g., set optimal manufacturing parameters) the manufacturing parameters (e.g., based on prediction data 168), system 100 can have the technical advantage of avoiding the costly consequences of sub-optimal manufacturing parameters using optimal manufacturing parameters (e.g., hardware parameters, process parameters, optimal design) and / or healthy equipment.

[0036] The corrective measures can be associated with one or more of computational process control (CPC), statistical process control (SPC) (e.g., SPC on electronic components to determine a process in control, SPC to predict the useful life of components, SPC to compare with a 3σ graph, etc.), advanced process control (APC), model-based process control, preventive maintenance, design optimization, updating of manufacturing parameters, updating of manufacturing strategies, feedback control, modification of machine learning, etc.

[0037] In some embodiments, the corrective measures include providing an alert (e.g., a warning to stop or not execute a manufacturing process on an additional substrate if the predicted data 168 indicates a predicted anomaly such as an anomaly in a product, component, or manufacturing equipment 124). In some embodiments, the corrective measures include providing feedback control (e.g., modifying manufacturing parameters in response to predicted data 168 indicating a predicted anomaly). In some embodiments, the execution of the corrective measures includes updating one or more manufacturing parameters.

[0038] The manufacturing parameters can include hardware parameters (e.g., information indicating components included within manufacturing equipment, indication of a most recently replaced component, firmware version or indication of an update, etc.) and / or process parameters (e.g., temperature, pressure, flow rate, current and / or voltage, gas flow rate, ramp rate, etc.). In some embodiments, the corrective measures include performing preventive maintenance (e.g., replacing, processing, cleaning components of the manufacturing equipment 124). In some embodiments, the corrective measures include performing design optimization (e.g., updating manufacturing parameters for an optimized product, updating the manufacturing process, updating the manufacturing equipment 124, etc.). In some embodiments, the corrective measures include updating a strategy (e.g., changing the timing of commands to put the manufacturing equipment 124 into an idle mode, sleep mode, warm-up mode, etc., adjusting set points for temperature, gas flow rate, plasma generation, etc.).

[0039] The analysis server 112 can include one or more computing devices such as a rack-mounted server, a router computer, a server computer, a personal computer, a mainframe computer, a laptop computer, a tablet computer, a desktop computer, a graphics processing unit (GPU), an application specific integrated circuit (ASIC) for accelerators (e.g., a tensor processing unit (TPU)).

[0040] The analysis server 112 can include an analysis component 114. In some embodiments, the analysis component 114 can receive current sensor data 146 and / or current manufacturing parameters (e.g., received from the client device 120, retrieved from the data store 140), and based on the current data, generate an output (e.g., prediction data 168) for executing a corrective action associated with the manufacturing equipment 124. In some embodiments, the analysis component 114 can use one or more trained models 190 to determine an output for executing a corrective action based on the current data.

[0041] In some embodiments, the model 190 can include a trained physics-based digital twin model. The physics-based model can be capable of solving a set of simultaneous equations that describe physical phenomena that can occur within a manufacturing chamber, such as equations governing heat flow, energy balance, gas conduction, mass balance, fluid dynamics, and current flow. In some embodiments, the physics-based model performs calculations of the performance of components within the manufacturing chamber. The manufacturing parameters 150 can be provided to the trained physics-based model. The trained physics-based model can provide, as an output, a modeled characteristic value indicating the state within the chamber corresponding to the sensor 126 disposed within the manufacturing chamber (e.g., the manufacturing equipment 124). The output of the physics-based model can be stored within the data store 140.

[0042] The analysis component 114 of the analysis server 112 can receive sensor data 142 generated from the data collected by the sensor 126. The analysis component 114 can utilize the sensor data 142 to generate summary data 162, prediction data 168, etc. The summary data 162 can include metrics indicating the performance of the device. For example, the analysis component 114 can retrieve trace sensor data (e.g., current sensor data 146) from the data store 140. The analysis component 114 can separate the data from a processing run into shorter portions, such as individual loops, loop operations, etc. The analysis component 114 can then generate summary data indicating the quality of execution of the processing operation (e.g., by providing data to the model 190).

[0043] In some embodiments, the analysis component 114 can generate a series of sets of trace data associated with a loop process. For example, each set of data can be associated with one loop, one operation, etc. In some embodiments, one or more sets of a particular type of trace data (e.g., all oxide deposition operations, one or more nitride deposition operations, one or more post-deposition pump and / or purge operations, etc.) can be grouped together for analysis, display, etc.

[0044] In some embodiments, a set of trace data (e.g., generated continuously by analysis component 114) can include one or more portions of transient data (e.g., associated with a period of ramp-up processing parameters, a period during which a target processing state has not been reached, etc.) and one or more portions of steady-state data (e.g., associated with a period during which a target processing state is to be maintained). The analysis system 110 can separate (e.g., via model 190) a set of trace data into a transient portion and a steady-state portion. The separation into the transient and steady-state portions will be discussed in more detail in connection with FIG. 3. In some embodiments, the analysis system 110 can generate summary data 162 using the steady-state portion. For example, the analysis system 110 can generate statistical metrics from steady-state data such as an average, a median, a standard deviation, etc. In some embodiments, the analysis system 110 can generate summary data 162 using the transient portion. For example, the analysis system 110 can compare transient data metrics to golden run data, physics-based model data, average data, etc. The analysis system 110 can utilize a machine learning model (e.g., model 190) to determine whether there is a difference between the transient portion of the data and past transient data. The analysis system 110 can determine summary data 162 using characteristics of the transient data, such as the shape of the transient data, such as spikes, slopes, gradients, etc., and the scale of the transient data, such as gradients, concavity, etc.

[0045] In some embodiments, the sensor data 142 can include data collected from the sensor 126 during a manufacturing run that produced acceptable products (e.g., measured by the measuring device 128). A manufacturing run that produces acceptable products can be referred to as a golden run. In some embodiments, the golden run can be determined in different ways, such as a run in which an acceptable chamber state is achieved, a run that occurs immediately after chamber maintenance or installation of a new chamber, and the like. Sensor data associated with such a manufacturing run can be stored in the data store 140 as golden run sensor data 148. Analysis components 114 of the analysis server 112, reporting components 123 of the client device 120, etc., can compare the golden run sensor data, the current sensor data 146, and the expected sensor data (e.g., output by a trained physics-based model) to determine whether component failures, drifts, etc. have occurred. In some embodiments, some or all of these operations can be performed instead by different devices, for example, operations originating from the analysis server 112 can be performed instead by the client device 120, and so on.

[0046] In some embodiments, the analysis component 114 receives the current sensor data 146 and / or the current manufacturing parameters, performs signal processing to decompose the current data into a set of current data, provides the set of current data as input to a trained model 190, and obtains an output indicating predicted data 168 from the trained model 190. In some embodiments, the predicted data 168 indicates measurement data 160 (e.g., prediction of substrate quality). In some embodiments, the predicted data 168 indicates the health state of a component. In some embodiments, the predicted data 168 indicates the performance of a component. It will be understood by those skilled in the art that variations in the data flow, which components perform which processes, which data is provided to which models, etc. are within the scope of the present disclosure.

[0047] The data store 140 can be a memory (e.g., random access memory), a drive (e.g., hard drive, flash drive), a database system, or another type of component or device capable of storing data. The data store 140 can include multiple storage components (e.g., multiple drivers or multiple databases) that can span multiple computing devices (e.g., multiple server computers). The data store 140 can store sensor data 142, manufacturing parameters 150, measurement data 160, summary data 162, and prediction data 168. The sensor data 142 can include past sensor data 144, current sensor data 146, and golden run sensor data 148. The sensor data can include a sensor data time trace over the duration of the manufacturing process, the association of data with physical sensors, preprocessed data such as average and composite data, and data indicating sensor performance over time (i.e., for many manufacturing processes). The summary data 162 can include processed sensor data 142. The summary data can include information indicating corrective actions to be taken in relation to the manufacturing equipment 124. The summary data need not be as intensive to operate as the trace sensor data (e.g., has a low computational cost).

[0048] The analysis component 114 can provide the current sensor data 146 and / or summary data 162 to the model 190, execute the model 190 for the input, and obtain one or more outputs. The analysis component 114 may be able to determine (e.g., extract) prediction data 168 from the output of the model 190, and determine (e.g., extract) confidence data from the output indicating a confidence level regarding that the prediction data 168 is an accurate predictor of the process associated with the input data for the product to be made or to be made using the manufacturing equipment 124 with the current sensor data 146 and / or the current manufacturing parameters 154. The analysis component 114 or the corrective action component 122 can use the confidence data to determine whether to trigger a corrective action associated with the manufacturing equipment 124 based on the prediction data 168.

[0049] The confidence data can include or indicate a confidence level regarding that the prediction data 168 is an accurate prediction for the product or component associated with at least a portion of the input data. In one example, the confidence level is generally a real number from 0 to 1, where 0 indicates no confidence that the prediction data 168 is an accurate prediction for the product processed according to the component health state of the input data or the components of the manufacturing equipment 124, and 1 indicates absolute confidence that the prediction data 168 accurately predicts the characteristics of the product processed according to the component health state of the input data or the components of the manufacturing equipment 124. In response to the confidence data indicating a confidence level below a threshold level for a predetermined number of cases (e.g., the ratio of cases, the frequency of cases, the total number of cases, etc.), the analysis component 114 can retrain and / or reconfigure the model 190 (e.g., based on the current sensor data 146, the current manufacturing parameters 154, etc.).

[0050] In some embodiments, the functions of the client device 120 and the prediction server 112 can be provided by a smaller number of machines. For example, in some embodiments, the client device 120 and the prediction server 112 can be integrated into a single machine.

[0051] Generally, the functions described in one embodiment executed by the client device 120 or the prediction server 112 can also, where appropriate, be executed by the other of the two components in other embodiments. Additionally, the functions attributed to a particular component can also be executed by different or multiple components operating together. For example, in some embodiments, the prediction server 112 can determine a corrective action based on the prediction data 168. In another example, the client device 120 can determine the prediction data 168 based on the output from the analysis system 110 or the like.

[0052] Additionally, the functions of a particular component can also be executed by different or multiple components operating together. One or more of the prediction server 112 or the client device 120 can be accessed as a service provided to other systems or devices via a suitable application programming interface (API).

[0053] In an embodiment, a "user" can be represented as a single individual. However, other embodiments of the present disclosure also include a "user" that is an entity managed by multiple users and / or automated sources. For example, a group of individual users integrated as a group of administrators can be regarded as a "user".

[0054] Embodiments of the present disclosure can be applied to data quality evaluation, feature enhancement, model evaluation, virtual metrology (VM), predictive maintenance (PdM), limit optimization, and the like.

[0055] Figure 2 shows an exemplary data flow 200 for generating an alert based on summary data, according to some embodiments. Sensor data is generated by a tool sensor 202. The tool sensor can include sensors disposed within a processing chamber, such as sensor 126 of FIG. 1. The tool sensor 202 can generate time trace sensor data, for example, obtaining readings spaced over the duration associated with the processing procedure of a tool (e.g., a processing chamber).

[0056] In some embodiments, the processing procedure can include one or more repetitive (e.g., loop) operations. For example, the processing procedure can target an output substrate that includes multiple layers and / or a stepped structure. The processing procedure can include, for example, deposition of a first material via a first process gas, removal of the first process gas (e.g., via evacuation, cleaning with an inert gas, etc.), deposition of a second material via a second process gas, and removal of the second process gas. The operations of the processing procedure can be repeated multiple times (e.g., dozens of times, hundreds of times, etc.) to generate a layered structure (e.g., multiple layers can be formed as the first material, the second material, the first material, the second material, etc.). The repetitive operations can be represented in the sensor data. For example, the chamber pressure may repeatedly rise and fall due to introduction of gas into the processing chamber and removal of gas from the processing chamber, and the process gas flow meter can record repetitive patterns of the flow rate, etc.

[0057] In some embodiments, the processing procedure can be separated into processing runs. For example, the target substrate can include a plurality of tiers (e.g., 100 tiers). The first set of tiers (e.g., tiers 1 to 50) can target different characteristics (e.g., layer thickness, etc.) than the second set of tiers (e.g., tiers 51 to 100). In some embodiments, the substrate can be removed from the processing chamber and / or from the processing state between runs. For example, after the first set of tiers have been deposited, the substrate can be rotated, e.g., to manage substrate stress and / or compensate for spatial irregularities in the deposition process.

[0058] Data can flow from the tool sensor 202 to the preprocessing module 203. In some embodiments, the sensor data can be stored in memory and retrieved later for preprocessing. In some embodiments, the preprocessing operations can be performed by different systems (e.g., the analysis system 204) at different locations within the data flow 200 (e.g., after the operation of the loop separation 206, during the operation of the analysis and reporting 212, etc.).

[0059] The preprocessing 203 can include applying operations to the sensor data. For example, the preprocessing 203 can include smoothing, averaging, combining sensor data (e.g., inferring quantities not directly measured using data from one or more sensors), and the like. In some embodiments, the preprocessing 203 can include correlating the sensor data. For example, data from different sensors can be correlated, data from multiple process runs (e.g., a set of operations while the substrate is removed from the process chamber) can be correlated, and so on. In some embodiments, the processing device can correlate a set of data based on the stored file name. For example, the file name can include a substrate ID, and the substrate ID can be used to correlate the files together. In some embodiments, the processing device can correlate a set of data based on the file generation time and / or tool ID.

[0060] Data is provided to the analysis system 204. The analysis system 204 can be correlated to the analysis system 110 of FIG. 1. The analysis system 204 can utilize multiple tools, modules, models, etc. to process the data (e.g., preprocessed time trace sensor data). In some embodiments, the data can be provided to the loop separation module 206. The operation of the loop separation 206 can include splitting the preprocessed sensor data into a series of loops. For example, the loop separation module 206 can split the sensor data into sets of data, with each data set corresponding to a layer of the processed substrate.

[0061] In some embodiments, processing logic (e.g., associated with the loop separation module 206) can classify separated data sets (e.g., associated with a repeated single operation such as deposition of a first material). For example, each deposition of the first material from a processing run, processing procedure, etc. can be classified as the same operation, each deposition of the second material can be classified as a second operation, each evacuation of the first process gas can be classified as a second operation, and so on. In some embodiments, the processing logic can assign classifications based on values of sensor data, e.g., values recorded by a primary sensor. For example, a flow meter reading from a flow meter that measures the flow rate of the first process gas can be used to determine whether a processing operation corresponds to a deposition of the first material associated with the first process gas. Multiple sensor readings can be utilized together to classify an operation, e.g., high-frequency power and gas flow readings can classify an etching operation. Sensor readings and sensor history can be utilized to classify an operation, e.g., a low-pressure period following a period classified as deposition of the first material can be classified as evacuation of the first process gas associated with the first material. In some embodiments, the output from the loop separation module 206 can include a series of time trace data sets collected by multiple sensors, separated into single operations, and classified by operation type.

[0062] In some embodiments, an indicator can be generated and associated with loop data. The indicator can uniquely identify a loop of a processing procedure. For example, the indicator value can continuously increment across processing runs, processing states, and the like. In some embodiments, the target structure can include multiple layers, and each layer has an assigned indicator. The indicator can be utilized in future operations. For example, through a visualization operation, sensor data can be shown according to the loop indicator, data associated with the selected number of loops with indicators of multiple out-of-control substrates can be compared, and so on. In some embodiments, the indicator value can act as a unique identifier for the period of sensor data, the loops of a multi-run process, and the like.

[0063] Data can be received by the temporary separation module 208. The time trace data set received from the loop separation module 206 can include one or more temporary portions and one or more steady-state portions. For example, a deposition operation can start at a low processing chamber pressure, and process gas can be introduced until the processing chamber pressure reaches a target value. The pressure sensor time trace data can include the transition period from the low pressure to the target pressure. The temporary separation module 208 can be configured to separate the temporary portion from the steady-state portion for further analysis. The operation of the temporary separation module 208 will be further described in relation to FIG. 3.

[0064] The output of the temporary separation module 208 can be provided to the summary data generation module 210. The summary data generation module 210 can be configured to receive the processed trace sensor data and generate, as output, one or more summary data associated with the input data. The summary data generation module 210 can utilize one or more models (e.g., machine learning models, physics-based models, statistical models, exemplary model systems including model 190 of FIG. 1) to generate summary data from the processed trace data. In some embodiments, the generation of summary data can include calculating statistical metrics associated with the steady-state data, such as mean, median, range, standard deviation, skewness, etc.

[0065] In some embodiments, a temporary portion of the processed trace data can be utilized to perform the summary generation operation. In some embodiments, a temporary portion of the data can be provided to a trained machine learning model. The trained machine learning model can be configured to distinguish normal temporary data from abnormal temporary data. In some embodiments, the temporary data can be utilized for summary data generation by using physics-based models, exemplary model systems (e.g., golden run data), etc. The characteristics of the temporary portion of the data can be extracted and compared with the model data. For example, characteristics such as rise time (e.g., the time from the start of the temporary portion until a certain portion of the target sensor reading, e.g., 90%, is reached), overshoot (e.g., how much the sensor data exceeds the target value), variation (e.g., whether the sensor value varies before stabilizing at the target value, characteristics of the variation such as frequency and amplitude), settling time (e.g., the time from the start of the temporary portion until the final time when the sensor value exceeds a defined interval from the target value, e.g., ±10%) can be compared with the model system to generate summary data. The techniques described herein for the analysis of the steady-state portion of the data can also be applied to the temporary portion. The techniques described for the analysis of the temporary portion can also be applied to the steady-state analysis.

[0066] Next, data (e.g., including summary data) can be provided to the reporting module 212. The reporting module can be similar to the reporting component 123 of the client device 120 in FIG. 1. In some embodiments, the reporting module 212 includes analytics, e.g., a dashboard (e.g., a graphical user interface) for displaying summary data. An exemplary dashboard is shown in FIG. 4. In some embodiments, the reporting module 212 can receive multiple types of summary data, summary data associated with multiple sensors, etc. The reporting module 212 can include one or more interface tools for, e.g., selecting the summary data to be displayed, selecting the sensor data to be displayed, selecting the substrate data to be displayed, etc.

[0067] FIG. 3 shows a visual representation 300 of the operation of splitting trace data into a transient portion and a steady-state portion according to some embodiments. The visual representation 300 includes a time trace 302. The time trace 302 can be associated with one sensor and one processing operation (e.g., the entire runtime trace has already been split by, e.g., the loop separation module 206 in FIG. 2 to generate the time trace 302). In some embodiments, the values of the time trace 302 can be used to identify the steady-state portion, e.g., the portion of the time trace 302 within a determined threshold range of the target value (e.g., within 10% of the target value) can be classified as the steady-state portion. In some embodiments, the slope of the data included in the time trace 302 can be used to separate the transient portion from the steady-state portion. For example, a best-fit function can be used to approximate the time trace 302. A first derivative describing the slope of the best-fit function can be calculated. The portion of the time trace 302 where the slope (e.g., the magnitude / absolute value of the slope) exceeds a threshold can be classified as the transient portion, and the portion of the time trace 302 where the slope is below the threshold can be classified as the steady-state portion.

[0068] In some embodiments, the window 314 can be utilized to determine whether a set of data points (e.g., data points within the window) belongs to a transient or steady-state portion of the data. Metric values of the points within the window, such as range, standard deviation, variance, etc., can be used to classify the points within the window as transient or steady-state. For example, if the window 314 includes points where the standard deviation of the values exceeds a threshold, the points within the window 314 can be classified as belonging to the transient portion.

[0069] In some embodiments, as shown by the arrow and the dashed-line window to the right of the trace 302, the window 304 is moved through the time trace to classify the data points of the trace as transient or steady-state. In some embodiments, the time trace 302 can be separated into two or more portions. In some embodiments, the time trace 302 can be separated into a transient start portion 306, a steady-state portion 307, and a transient end portion 308.

[0070] Figure 4 shows an exemplary instrument panel 400 for alerting a user about the quality of execution of one or more processing procedures according to some embodiments. The instrument panel 400 can be a graphical user interface (GUI), can include a GUI, can be integrated with a GUI, and so on hereinafter. The instrument panel 400 can include a control panel 402 and a data display 410. The control panel 402 can be utilized by a user to display target data, such as target summary types, target substrates, data associated with target operations, and so on. For example, the control panel 402 can have a plurality of controls for customizing the data display 410, such as menus, selectable lists, and so on, and / or can select data displayed within the data display 410. The exemplary control panel 402 includes three controls 404, 406, and 408. More or fewer controls are also conceivable. Possible controls can include, for example, data file selection 404, sensor selection 406, and processing procedure selection 408. In some embodiments, the controls can include selecting a classification of operations (for example, the data file selected by the data file selection 404 can be separated into classes such as deposition of a first material, evacuation of a first process gas, and so on, and a separate control can be provided for selection of the classification, and so on hereinafter), selecting a type of summary data (for example, the data file can be separated into summary types such as steady state average, transient partial maximum gradient, and so on), and so on.

[0071] The data display 410 can display summary data so as to easily distinguish data associated with different stages, layers, loops, etc. The instrument panel 400 can include a key 412. In some embodiments, data points associated with different layers can be displayed using different colors, for example, using a color gradient to distinguish data from different layers. As shown in FIG. 4, different layers can be distinguished by different patterns. FIG. 4 shows the first layer (e.g., the first one-third) as data points without a pattern, the middle layer as data points with a striped pattern, and the back layer as data points with a hash pattern.

[0072] The data display 410 displays summary data, data sets 414, 415, 416, and 417 associated with four substrates. In some embodiments, one or more data sets can be associated with a model or ideal system, such as data associated with golden run data, a processing procedure for producing a product that meets a production rate threshold, etc. An exemplary data display 410 includes a golden run data set 417.

[0073] The data display 410 can display summary data values associated with a layer (or a group of layers, such as a boxcar average, etc.) and a substrate. For example, the y-axis of the data display 410 can represent the summary data values. Four values of the summary data, a first target value 420, a second target value 422, a third value 424, and a fourth value 426 are shown in FIG. 4. The data display 410 can be used to compare data associated with substrates. For example, the data of the processed substrate can be compared with one or more model data sets. The exemplary data displayed on the instrument panel 400 can target the first target value 420 for the first layer and the second value 422 for the middle and end layers. The data display 410 can display the data so as to facilitate distinguishing the differences between the layers of the substrates. For example, the golden run data represented as the data set 417 can define the target values. In some embodiments, the target values can be defined by the user, can be defined by the average of multiple processing runs, and so on. The data set 416 is similar to the data set 417, which can indicate that the data set 416 is associated with a processing procedure similar to the procedure associated with the data set 417 (for example, it can indicate a product with similar characteristics).

[0074] The data sets 414 and 415 include data points having values that approximately correspond to the third value 424 and the fourth value 426. In some embodiments, the data display 410 can be configured to display data points visually distinguished by the layer. For example, the data set 415 includes an end layer having a summary data value approximately equal to the fourth value 426, and the data set 414 includes an intermediate layer having a summary data value approximately equal to the third value 424 and an end layer having a summary data value approximately equal to the fourth value 426. In order to achieve the target processing state, it is possible to quickly identify which part of the processing procedure can be adjusted.

[0075] FIG. 5 shows a flowchart of a method 500 for generating an alarm based on a loop processing procedure according to some embodiments. At block 502, the processing logic receives time trace sensor data associated with a substrate processing procedure. The processing procedure includes two or more sets of processing states. In some embodiments, the processing procedure can be separated into runs associated with different processing states (e.g., to achieve target characteristics, higher layers of a multi-layer device can be designed in a different form than lower layers and processed in a different form). In some embodiments, the processing procedure can include one or more runs, and between runs, the substrate can be removed from the processing environment, removed from the processing chamber, and so on. In some alternative embodiments, the processing procedure can include multiple processing runs associated with the same or similar processing states. Each of at least two of the processing runs (e.g., two data files, two sets of processing states, etc.) includes one or more operations that are repeatedly executed.

[0076] To generate a target layered structure, such as a 3D NAND memory structure, a repetitive operation can be performed. The repetitive operation can include, for example, introduction of a first process gas (e.g., for deposition of a first material on the surface of a substrate), evacuation of the first process gas, introduction of a second process gas (e.g., for deposition of a second material on the surface of the substrate), evacuation of the second process gas, and the like. In some embodiments, the target structure can include alternating layers of silicon oxide and silicon nitride (e.g., the first process gas can include an oxide precursor and the second process gas can include a nitride precursor). In some embodiments, the target structure can include alternating layers of silicon oxide and polysilicon. In some embodiments, layers of three or more materials can be formed, for example, the target structure can include a layer of silicon oxide, a layer of silicon nitride, and a layer of polysilicon. In some embodiments, the periodic deposition procedure can include multiple depositions of a single material, such as repetitive polysilicon deposition operations. In some embodiments, the periodic procedure can include multiple operations associated with multiple depositions of materials, such as introduction of a first process gas for deposition, evacuation of the process gas, introduction of a second process gas for further layer processing (e.g., plasma treatment of the deposited material), and evacuation of the second process gas. Such multi-step operations can be utilized for periodic deposition of a single material, two materials, or more materials. In some embodiments, the target structure can include a large number of layers, such as 50 or more layers, 80 or more layers, 100 or more layers, 200 or more layers, etc. (e.g., the total number of repetitions of the operation can be 50 or more, 80 or more, etc.).

[0077] At block 504, the processing logic separates time trace sensor data associated with a first set of processing states into first plural periodic data. Each of the first plural is associated with one or more operations that are repeatedly executed. In some embodiments, each of the first plural periodic data can be associated with a processing operation, such as deposition of a first material, evacuation of a first process gas, etc. In some embodiments, sensor data values can be utilized to distinguish operations, cycles, loops, etc. Sensor values from multiple sensors can be utilized to distinguish operations. For example, using the value recorded by a process chamber pressure sensor, a deposition operation can be distinguished from a purge operation, and using the value recorded by a flow meter associated with a first process gas, deposition of a first material can be distinguished from deposition of a second material, and so on. In some embodiments, each of the first plural periodic data can be associated with a set of operations that are each repeated, such as operations associated with a repeated pattern of a processed structure, such as operations associated with deposition of a first material and deposition of a second material. In some embodiments, each of the first plural periodic data can be associated with multiple processing loops. At block 506, the processing logic separates time trace sensor data associated with a second set of processing states into second plural periodic data. The operation of block 506 can share characteristics with the operation of block 504.

[0078] At block 508, the processing logic identifies at least one steady state portion of the time trace sensor data. In some embodiments, the periodic data can be separated into a transient portion and a steady state portion. The separation of the steady state portion and the transient portion was discussed in more detail in relation to FIG. 3. In some embodiments, separate analyses can be performed on the steady state portion and the transient portion. In some embodiments, an analysis can be performed on only one type of portion, such as either the steady state portion or the transient portion.

[0079] In block 510, the processing logic processes the first plurality of periodic data and the second plurality of periodic data to generate summary data. In some embodiments, processing can be performed on a portion of the periodic data, such as a steady-state portion. The summary data can be based on one or more steady-state portions. In some embodiments, the summary data can include one or more statistical metrics, such as mean, median, range, standard deviation, skewness, etc.

[0080] In block 512, the processing logic can generate graphics for display on a graphical user interface (GUI) based on the summary data. The graphics can be included within GUI elements. For example, the GUI can include a plurality of elements, and one or more of the plurality of elements are graphics associated with a periodic procedure. The GUI elements can include an indication of the summary data associated with the periods of the first and second pluralities of periodic data. The graphics for display can include a visual distinction of display data associated with different periods. For example, depending on which stage / loop the data is associated with, the data can be displayed in different colors along a color gradient. In some embodiments, the graphics can include data from one or more substrates. In some embodiments, the graphics can include data associated with the operation of one or more classes, for example, can include only data from an operation associated with the deposition of a first material, and so on. In some embodiments, the graphics can include data associated with a model system, such as the output of a physics-based model, golden run sensor data, etc.

[0081] In block 514, the processing logic provides an alert to the user. The alert can include the graphic of block 512. The alert can be provided via an instrument panel, such as the exemplary instrument panel 400 of FIG. 4. The alert can be provided via a graphical user interface, for example, to enable interaction by the user (such as data selection, customization of visual representation, etc.). In block 516, further corrective actions are performed in consideration of the summary data. Further corrective actions (such as to further provide an alert to the user) can include scheduling maintenance, updating process policies, and the like.

[0082] FIG. 6 is a block diagram showing a computer system 600 according to a particular embodiment. In some embodiments, the computer system 600 can be connected to other computer systems (e.g., via a network such as a local area network (LAN), intranet, extranet, or the Internet). The computer system 600 can operate in the capacity of a server or client computer in a client - server environment, or can operate as a peer computer in a peer - to - peer or distributed network environment. The computer system 600 can be provided by a personal computer (PC), tablet PC, set - top box (STB), personal digital assistant (PDA), cellular phone, web device, server, network router, switch, or bridge, or any device capable of (sequentially or otherwise) executing a set of instructions that specify actions to be taken by that device. Further, the term "computer" shall be taken to include any one or group of computers capable of executing, individually or jointly, one set (or more) of instructions for performing any one or more of the methods described herein.

[0083] In a further aspect, computer system 600 can include a processing device 602, volatile memory 604 (e.g., random access memory (RAM)), non-volatile memory 606 (e.g., read-only memory (ROM) or electrically erasable programmable ROM (EEPROM)), and a data storage device 618, which can communicate with each other via a bus 608.

[0084] The processing device 602 can be provided by one or more processors such as a general-purpose processor (e.g., a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a microprocessor implementing other types of instruction sets, or a microprocessor implementing a combination of types of instruction sets), or a special processor (e.g., an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a digital signal processor (DSP), or a network processor, etc.).

[0085] The computer system 600 can further include a network interface device 622 (e.g., coupled to a network 674). The computer system 600 can also include a video display unit 610 (e.g., an LCD), an alphanumeric input device 612 (e.g., a keyboard), a cursor control device 614 (e.g., a mouse), and a signal generation device 620.

[0086] In some embodiments, the data storage device 618 can include a non-transitory computer-readable storage medium 624 (e.g., a non-transitory machine-readable medium) that can store instructions 626 encoding any one or more of the methods or functions described herein, the instructions 826 encoding components of FIG. 1 (e.g., analysis component 114, corrective action component 122, model 190, etc.) and including instructions for implementing the methods described herein.

[0087] Command 626 can also be stored, in whole or in part, within volatile memory 604 and / or processing device 602 during its execution by computer system 600, and thus volatile memory 604 and processing device 602 can also constitute a machine-readable storage medium.

[0088] In an illustrative example, computer-readable storage medium 624 is shown as a single medium, but the term "computer-readable storage medium" is intended to include a single medium or multiple media (e.g., a centralized or distributed database, and / or associated caches and servers) that store one or more sets of executable instructions. The term "computer-readable storage medium" is also intended to include any tangible medium that can store or encode a set of instructions for causing a computer to perform any one or more of the methods described herein. The term "computer-readable storage medium" includes, but is not limited to, solid state memories, optical media, and magnetic media.

[0089] The methods, components, and features described herein can be implemented by individual hardware components or integrated into the functionality of other hardware components such as ASICs, FPGAs, DSPs, or similar devices. Additionally, the methods, components, and features can be implemented by firmware modules or functional circuits within a hardware device. Further, the methods, components, and features can be implemented in any combination of hardware devices and computer program components or within a computer program.

[0090] Unless otherwise specifically stated, terms such as "receive", "execute", "provide", "obtain", "cause", "access", "determine", "add", "use", "train", "reduce", "generate", "correct", etc. refer to measures and processes executed or performed by a computer system that manipulates and transforms data represented as physical (electronic) quantities in a computer system register and memory into other data similarly represented as physical quantities in a computer system memory or register or other such information storage, transmission, or display device. Also, in this specification, terms such as "first", "second", "third", "fourth", etc. are meant to be labels for distinguishing different elements and may not have the meaning of an order according to a numerical indication.

[0091] The examples described in this specification also refer to an apparatus for executing the methods described in this specification. This apparatus can be specifically constructed to execute the methods described in this specification or can include a general-purpose computer system selectively programmed by a computer program stored in a computer system. Such a computer program can be stored in a computer-readable tangible storage medium.

[0092] The methods and examples described in this specification are not inherently related to any particular computer or other device. According to the teachings described in this specification, various general-purpose systems can be used, or it may prove convenient to construct more specialized devices for executing each of the methods and / or individual functions, routines, subroutines, or operations described in this specification. Examples of structures for various of these systems are described in the above explanation.

[0093] The foregoing description is intended to be illustrative rather than restrictive. Although the present disclosure has been described with reference to specific illustrative examples and embodiments, it will be understood that the present disclosure is not limited to the examples and embodiments described. The scope of the present disclosure should be determined with reference to the following claims, along with the full scope of equivalents given in the claims.

Claims

1. Receiving time-trace sensor data associated with a substrate processing procedure, wherein the substrate processing procedure includes two or more sets of processing states, and a first set of processing states and a second set of processing states among the two or more sets of processing states each include one or more operations that are repeatedly executed; Separating a first portion of the time-trace sensor data corresponding to the first set of processing states into first plural periodic data, wherein each of the first plural periodic data is associated with one or more operations that are repeatedly executed; Separating a second portion of the time-trace sensor data corresponding to the second set of processing states into second plural periodic data, wherein each of the second plural is associated with one or more operations that are repeatedly executed; Processing the first plural periodic data and the second plural periodic data to generate summary data; Providing an alarm based on the summary data to a user A method comprising.

2. Further comprising identifying at least one steady-state portion of the time-trace sensor data, wherein at least a portion of the summary data is based on the steady-state portion, The method according to claim 1.

3. Further comprising executing a period associated with the first plural periodic data, and executing the period associated with the first plural periodic data is Supplying a first process gas to a processing chamber to deposit a first material on a surface of a substrate; Exhausting the first process gas from the processing chamber; Supplying a second process gas to the processing chamber to deposit a second material on the surface of the substrate; The method according to claim 1, comprising exhausting the second process gas from the processing chamber.

4. The method according to claim 3, wherein the first material includes silicon oxide and the second material includes silicon nitride.

5. Assigning a first set of indicator values to each of the first plural periodic data; further comprising assigning a second set of indicator values to each of the second plurality of cycle data, wherein the first set of indicator values and the second set of indicator values include identifiers unique to each cycle data of the first and second plurality of cycle data. The method according to claim 1.

6. The method according to claim 1, wherein the summary data includes one or more statistical metrics.

7. further comprising providing a graphical user interface (GUI) that presents GUI elements, the GUI elements an indication of summary data associated with one or more cycles of the first plurality of cycle data and one or more cycles of the second plurality of cycle data, and a visual distinction of each indication. The method according to claim 1.

8. The method according to claim 1, wherein the substrate processing procedure is to generate a 3D NAND memory device.

9. Separating the first portion of the time trace sensor data associated with the first set of processing states into the first plurality of cycle data includes identifying two or more operations of a cycle based on sensor data values associated with the two or more operations. The method according to claim 1.

10. A system comprising a memory and a processing device coupled to the memory, the processing device receiving time trace sensor data associated with a substrate processing procedure, the substrate processing procedure including two or more sets of processing states, wherein a first set of processing states and a second set of processing states among the two or more sets of processing states each include one or more operations that are repeatedly executed, receiving; separating a first portion of the time trace sensor data corresponding to the first set of processing states into a first plurality of cycle data, each of the first plurality of cycle data being associated with one or more operations that are repeatedly executed, separating; separating a second portion of the time trace sensor data corresponding to the second set of processing states into a second plurality of cycle data, each of the second plurality being associated with one or more operations that are repeatedly executed, separating; processing the first plurality of cycle data and the second plurality of cycle data to generate summary data; A system configured to provide an alarm to a user based on the summary data.

11. The system according to claim 10, wherein the processing device is further configured to identify at least one steady state portion of the time trace sensor data, and at least a portion of the summary data is based on the steady state portion.

12. The period associated with the first plurality of periodic data is Supplying a first process gas to a processing chamber to deposit a first material on a surface of a substrate; Exhausting the first process gas from the processing chamber; Supplying a second process gas to the processing chamber to deposit a second material on the surface of the substrate; The system according to claim 10, comprising exhausting the second process gas from the processing chamber.

13. The system according to claim 10, wherein a total number of repetitions of an operation including the plurality of periodic data is at least 50.

14. The system according to claim 10, wherein the summary data includes one or more statistical metrics.

15. Further comprising providing a graphical user interface (GUI) that presents GUI elements, the GUI elements being An indication of summary data associated with one or more periods of the first plurality of periodic data and one or more periods of the second plurality of periodic data; The system according to claim 10, comprising a visual distinction of each indication.

16. The system according to claim 10, wherein the substrate processing procedure is to generate a three-dimensional NAND memory device.

17. Separating the time trace sensor data associated with the first set of processing states into a first plurality of periodic data, wherein the first and second portions of the time trace sensor data are respectively associated with a first operation and a second operation of a period. Identifying based on sensor data values associated with the first operation and the second operation. The system according to claim 10.

18. A non-transitory machine-readable storage medium storing instructions that, when executed, cause a processing device to perform an operation, the operation being Receiving time trace sensor data associated with a substrate processing procedure, wherein the substrate processing procedure includes two or more sets of processing states, and a first set of processing states and a second set of processing states among the two or more sets of processing states each include one or more operations that are repeatedly executed, and receiving; Separating a first portion of the time trace sensor data corresponding to the first set of processing states into first plural periodic data, wherein each of the first plural periodic data is associated with one or more operations that are repeatedly executed, and separating; Separating a second portion of the time trace sensor data corresponding to the second set of processing states into second plural periodic data, wherein each of the second plural is associated with one or more operations that are repeatedly executed, and separating; Processing the first plural periodic data and the second plural periodic data to generate summary data; A non-transitory machine-readable storage medium including providing an alarm based on the summary data to a user.

19. The operation executed by the processing device further includes identifying at least one steady state portion of the time trace sensor data, and at least a portion of the summary data is based on the steady state portion. The non-transitory machine-readable storage medium according to claim 18.

20. The non-transitory machine-readable storage medium according to claim 18, wherein the summary data includes one or more statistical metrics.

Images