Cleaning process based on deposition thickness

Abstract

The method includes identifying deposition thickness characteristic data relating to an amount of material deposited via one or more substrate processing steps of a process recipe executed in a processing chamber. The method further includes determining cleaning step parameters based on the deposition thickness characteristic data and a variable cleaning time relationship of the process recipe. The method further includes performing a cleaning step in the processing chamber based on the cleaning step parameters.

Description

[Technical Field]

[0001]

[0001] The present disclosure relates to cleaning processes, and more particularly to deposition thickness based cleaning processes. [Background technology]

[0002]

[0002] Products can be manufactured by performing one or more manufacturing processes using manufacturing equipment. For example, substrate processing equipment can be used to manufacture semiconductor substrates through substrate processing steps. Summary of the Invention

[0003]

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

[0004] One aspect of the present disclosure includes a method that includes identifying deposition thickness characteristic data related to an amount of material deposited via one or more semiconductor processing steps of a process recipe executed in a processing chamber. The method further includes determining cleaning step parameters based on the deposition thickness characteristic data and a variable cleaning time relationship of the process recipe. The method further includes performing a cleaning step in the processing chamber based on the cleaning step parameters.

[0005] A further aspect of the present disclosure includes a non-transitory computer-readable storage medium including instructions that, when executed by a processing device operatively coupled to a memory, perform a process including identifying deposition thickness characteristic data related to an amount of material deposited via one or more substrate processing steps of a process recipe executed in a processing chamber. The process further includes determining cleaning process parameters based on the deposition thickness characteristic data and a variable cleaning time relationship of the process recipe. The process further includes performing a cleaning process in the processing chamber based on the cleaning process parameters.

[0006] A further aspect of the present disclosure includes a system including a memory and a processing device coupled to the memory. The processing device identifies deposition thickness characteristic data relating to an amount of material deposited via one or more substrate processing steps of a process recipe executed in a processing chamber. The processing device further determines cleaning step parameters based on the deposition thickness characteristic data and a variable cleaning time relationship of the process recipe. The processing device further causes a cleaning step to be performed in the processing chamber based on the cleaning step parameters.

[0007]

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

[0008] [Figure 1] FIG. 1 is a block diagram illustrating an exemplary system architecture in accordance with certain embodiments. [Figure 2]

[0009] 1 illustrates a dataset generator that creates a dataset for a machine learning model related to a cleaning process based on deposition thickness, according to certain embodiments. [Figure 3]

[0010] FIG. 10 is a block diagram illustrating determining predictive data associated with a cleaning process based on deposition thickness, in accordance with certain embodiments. [Figure 4A]

[0011] FIG. 1 is a flow diagram of a method relating to a cleaning process based on deposition thickness, in accordance with certain embodiments. [Figure 4B] FIG. 1 is a flow diagram of a method relating to a cleaning process based on deposition thickness, in accordance with certain embodiments. [Figure 4C] FIG. 1 is a flow diagram of a method relating to a cleaning process based on deposition thickness, in accordance with certain embodiments. [Figure 5]

[0012] FIG. 1 is a block diagram illustrating a computer system, in accordance with certain embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0009]

[0013] Concerned herein are cleaning processes based on deposition thickness (eg, cleaning based on deposition thickness, optimizing chamber cleaning by utilizing a deposition thickness counter).

[0010]

[0014] Products can be manufactured by performing one or more manufacturing processes using manufacturing equipment. For example, substrate processing equipment can be used to manufacture substrates (e.g., semiconductor devices, semiconductors, wafers, etc.) through substrate processing steps (e.g., semiconductor processing steps, semiconductor manufacturing processes). The substrate processing equipment can deposit multilayer films on the substrate surface according to a process recipe and perform an etching process to form a pattern in the deposited film. For example, the substrate processing equipment can perform a chemical vapor deposition (CVD) process to deposit alternating layers on the substrate.

[0011]

[0015] During a substrate processing step, residues (e.g., deposition residues) may accumulate within a processing chamber (e.g., on the walls of the processing chamber). A processing chamber may have multiple substrate processing regions or slots. After a deposition step, the deposition residual thickness may vary for each individual substrate processing region (e.g., slot) within a single processing chamber. For example, a processing chamber having two substrate processing regions (e.g., slots) may use the first substrate processing region during a deposition step, while the second substrate processing region may not be used during the deposition step. Following such a step, the first substrate processing region may have more accumulated deposition residues therein, and the second substrate processing region may have less (e.g., no) accumulated deposition residues from the deposition step.

[0012]

[0016] Substrate processing recipes traditionally include a fixed cleaning step (e.g., cleaning time, cleaning strength, etc.) with fixed cleaning step parameters for a processing chamber (e.g., after a deposition process). Traditionally, processing recipes include a fixed cleaning time following at least one deposition step. For example, after multiple deposition steps (e.g., CVD), a processing chamber may be cleaned for a fixed time.

[0013]

[0017] These constant cleaning steps with constant cleaning step parameters can result in over-cleaning and / or under-cleaning of the processing chamber. For example, a constant cleaning time can be used to clean both the first and second substrate processing regions of a processing chamber. This constant cleaning time can result in under-cleaning and over-cleaning of the processing chamber and / or the first and second substrate processing regions. Over-cleaning of the processing chamber can result in contamination within the processing chamber (e.g., particles of cleaning agents, such as aluminum fluoride, remaining after the cleaning step is completed), which can cause defects in the substrate. Over-cleaning of the processing chamber can also damage the processing chamber, leading to substrate-to-substrate non-uniformity and damage to the manufacturing equipment. Under-cleaning of the processing chamber can result in substrates being processed in a dirty chamber, resulting in substrate defects and substrate-to-substrate non-uniformity (e.g., substrates processed in an optimally cleaned processing chamber have fewer defects than substrates processed in an under-cleaned chamber).

[0014]

[0018] The devices, systems, and methods disclosed herein provide a cleaning process based on deposition thickness (eg, optimized chamber cleaning by utilizing a deposition thickness counter).

[0015]

[0019] The processing device identifies deposition thickness characteristic data relating to an amount of material deposited (e.g., deposited on a substrate, on walls of a processing chamber, etc.) via one or more substrate processing steps (e.g., semiconductor processing steps) of a process recipe executed in a processing chamber. In some embodiments, the deposition thickness characteristic data includes a material type and / or a thickness counter (e.g., units of deposited thickness, units of thickness of a particular material deposited). In some embodiments, the processing chamber includes a substrate processing region. In some embodiments, the deposition thickness characteristic data is derived from a deposition step recipe (e.g., a deposition thickness equal to an expected deposition thickness for a deposition step).

[0016]

[0020] The processing device determines cleaning operation parameters based on the deposition thickness characteristic data and a variable cleaning time relationship (e.g., an equation, a function, a mathematical relationship, etc.) of the process recipe. In some embodiments, the cleaning operation parameters include an amount of cleaning time. In some embodiments, the processing device further determines cleaning operation parameters based on the deposition thickness characteristic data of at least one of the substrate processing regions and the variable cleaning time relationship of the process recipe. In some embodiments, the processing device determines the cleaning operation parameters by providing the deposition thickness characteristic data as input to a trained machine learning model related to the variable cleaning time relationship and receiving output from the trained machine learning model related to predicted data, where the cleaning operation parameters are based on the predicted data. In some embodiments, the trained machine learning model is trained using data inputs including historical deposition thickness characteristic data and target outputs including historical performance data.

[0017]

[0021] The processing device causes the cleaning process to be performed in the processing chamber based on the cleaning process parameters (e.g., a particular duration, intensity, etc.) In some embodiments, the processing device further resets the thickness counter (e.g., resets the thickness counter to equal zero) after the cleaning process is performed.

[0018]

[0022] Aspects of the present disclosure provide technical advantages. The present disclosure avoids over-cleaning and under-cleaning of processing chambers and / or substrate processing regions. The present disclosure further avoids the generation of contamination within processing chambers, which can lead to substrate defects. The present disclosure further avoids damage to processing chambers, which can lead to substrate-to-substrate non-uniformity and damage to manufacturing equipment. The present disclosure further avoids processing substrates in dirty processing chambers, which can lead to substrate defects and substrate-to-substrate non-uniformity.

[0019]

[0023] Although some embodiments of the present disclosure describe cleaning processes based on deposition thickness in some embodiments, the present disclosure can be used for other processes (e.g., etching processes, maintenance processes, repair processes, etc.) that are based on other types of characteristic data (e.g., image data, defect data, temperature data, etc.).

[0020]

[0024] 1 is a block diagram illustrating an example system 100 (an example system architecture) according to certain embodiments. System 100 (e.g., corrective action component 122 and / or prediction component 114) can perform methods described herein (e.g., methods 400A-C of FIGS. 4A-C). System 100 includes client device 120, manufacturing equipment 124, sensors 126, metrology equipment 128, prediction server 112, and data store 140. In some embodiments, prediction server 112 is part of prediction system 110. In some embodiments, prediction system 110 further includes server machines 170 and 180.

[0021]

[0025] In some embodiments, one or more of client device 120, manufacturing equipment 124, sensor 126, metrology equipment 128, prediction server 112, data store 140, server machine 170, and / or server machine 180 are coupled to one another via network 130 to generate predictive data 160 for performing deposition thickness-based cleaning. In some embodiments, network 130 is a public network that provides client device 120 with access to prediction server 112, data store 140, and other publicly available computing devices. In some embodiments, network 130 is a private network that provides client device 120 with access to manufacturing equipment 124, sensor 126, metrology equipment 128, data store 140, and other privately available computing devices. In some embodiments, network 130 includes 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.

[0022]

[0026] In some embodiments, client device 120 includes a computing device such as a personal computer (PC), a laptop, a mobile phone, a smartphone, a tablet computer, a netbook computer, etc. In some embodiments, client device 120 includes a corrective action component 122. In some embodiments, corrective action component 122 may also be included in prediction system 110 (e.g., a machine learning processing system). In some embodiments, corrective action component 122 is alternatively included in prediction system 110 (e.g., instead of being included in client device 120). Client device 120 includes an operating system that enables a user to one or more of: synthesize, generate, view, or edit data, and provide data to prediction system 110 (e.g., a machine learning processing system).

[0023]

[0027] In some embodiments, the corrective action component 122 receives one or more of user input (e.g., via a graphical user interface (GUI) displayed via the client device 120), characteristic data 142, performance data 152, etc. In some embodiments, the characteristic data 142 can be deposition thickness characteristic data (e.g., deposition thickness, deposition residue thickness, thickness counter, etc.). In some embodiments, the corrective action component 122 transmits data (e.g., user input, characteristic data 142, performance data 152, etc.) to the prediction system 110, receives prediction data 160 from the prediction system 110, determines corrective actions based on the prediction data 160, and executes the corrective actions. In some embodiments, the corrective action component 122 stores the data (e.g., user input, characteristic data 142, performance data 152, etc.) in the data store 140, and the prediction server 112 retrieves the data from the data store 140. In some embodiments, prediction server 112 stores the output of trained machine learning model 190 (e.g., prediction data 160) in data store 140, and client device 120 retrieves the output from data store 140. In some embodiments, corrective action component 122 receives corrective action instructions (e.g., based on prediction data 160) from prediction system 110 and causes the corrective action to be executed.

[0024]

[0028] In some embodiments, the corrective action may be, for example, determining cleaning process parameters, updating a process recipe, updating a cleaning process, adjusting a variable cleaning time based on the deposition thickness characteristic data, etc. In some embodiments, the corrective action may be, for example, training a machine learning model (e.g., using data inputs including historical deposition thickness characteristic data and target outputs including historical performance data), using the trained machine learning model (e.g., to receive outputs associated with predicted data, where the cleaning process parameters are based on the predicted data), etc.

[0025]

[0029] In some embodiments, the predictive data 160 is associated with a corrective action. In some embodiments, the corrective action relates to one or more of cleaning one or more portions of the manufacturing equipment 124 (e.g., processing chambers, substrate processing areas, etc.), repairing one or more portions of the manufacturing equipment 124, replacing one or more portions of the manufacturing equipment 124, computational process control (CPC), statistical process control (SPC) (e.g., SPC for comparison to a three-sigma graph, etc.), advanced process control (APC), model-based process control, preventative maintenance, design optimization, manufacturing parameter updates, cleaning process parameter updates, wafer recipe modifications, feedback control, machine learning modifications, etc.

[0026]

[0030] In some embodiments, the corrective action includes determining cleaning process parameters (e.g., length of time, intensity of cleaning, temperature, pressure, type of cleaning agent used, etc.) In some embodiments, the corrective action includes providing machine learning (e.g., to update cleaning process parameters, cleaning recipes, or process recipes based on predictive data 160).

[0027]

[0031] In some embodiments, prediction server 112, server machine 170, and server machine 180 each 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 accelerator application-specific integrated circuit (ASIC) (e.g., a Tensor Processing Unit (TPU)), or the like.

[0028]

[0032] The prediction server 112 includes a prediction component 114. In some embodiments, the prediction component 114 identifies (e.g., receives from a client device 120, retrieves from a data store 140, etc.) characteristic data 142 (e.g., deposition thickness characteristic data) and generates prediction data 160 related to performing corrective actions (e.g., cleaning steps based on deposition thickness, updating a cleaning step in a recipe based on deposition thickness, determining cleaning step parameters for a cleaning step, etc.). In some embodiments, the prediction component 114 determines the prediction data 160 using one or more trained machine learning models 190. In some embodiments, the trained machine learning models 190 are trained using historical characteristic data 144 and historical performance data 154.

[0029]

[0033] In some embodiments, the prediction system 110 (e.g., prediction server 112, prediction component 114) uses supervised machine learning (e.g., supervised dataset, historical characteristic data 144 labeled with historical performance data 154, etc.) to generate the prediction data 160. In some embodiments, the prediction system 110 uses semi-supervised learning (e.g., semi-supervised dataset, performance data 152 is a predictive percentage, etc.) to generate the prediction data 160. In some embodiments, the prediction system 110 uses unsupervised machine learning (e.g., unsupervised dataset, clustering, clustering based on historical characteristic data 144, etc.) to generate the prediction data 160.

[0030]

[0034] In some embodiments, the manufacturing equipment 124 includes one or more of a processing chamber, a deposition chamber, a cluster tool, a wafer backgrind system, a wafer saw equipment, a die attach machine, a wire bonder, a die overcoat system, a molding equipment, a hermetic sealing equipment, a metal can welder, a deflash / trim / form / singulation (DTFS) machine, a branding equipment, a lead finishing equipment, etc. In some embodiments, the manufacturing equipment 124 is part of a substrate processing system (e.g., an integrated processing system). The manufacturing equipment 124 includes one or more of a controller, an enclosure system (e.g., a substrate carrier, a front-opening unified pod (FOUP), an auto-teach FOUP, a process kit enclosure system, a substrate enclosure system, a cassette, etc.), a side storage pod (SSP), an aligner device (e.g., an aligner chamber), a factory interface (e.g., an equipment front-end module (EFEM)), a load lock, a transfer chamber, one or more processing chambers, a robot arm (e.g., disposed in the transfer chamber, disposed in the front interface, etc.), and / or the like. The enclosure system, SSP, and load lock are attached to the factory interface, and the robot arm disposed in the factory interface transfers contents (e.g., substrates, process kit rings, carriers, verification wafers, etc.) between the enclosure system, SSP, load lock, and factory interface. The aligner device is disposed in the factory interface to align the contents. The load locks and processing chambers are mounted in a transfer chamber, and a robotic arm located within the transfer chamber transfers contents (e.g., substrates, process kit rings, carriers, verification wafers, etc.) between the load locks, processing chambers, and transfer chamber. In some embodiments, the manufacturing tool 124 includes components of a substrate processing system.In some embodiments, the process chamber or substrate characteristic data 142 results from the process chamber performing one or more substrate processing steps (e.g., semiconductor processing steps, deposition, etching, heating, cooling, transport, treatment, flow, etc.).

[0031]

[0035] In some embodiments, the sensor 126 provides characteristic data 142 of the processing chamber (e.g., sensor values ​​such as past and current sensor values) or characteristic data 142 of the substrate being processed by the manufacturing tool 124 (e.g., deposition thickness characteristic data).

[0032]

[0036] In some embodiments, the sensor 126 and / or metrology device 128 includes one or more of the following metrology tools: an ellipsometer (used to determine thin film properties and surfaces by measuring material properties such as layer thickness, optical constants, surface roughness, composition, optical anisotropy, etc.), an ion mill (used to prepare heterogeneous bulk materials for uniformly thinning large areas of material), a capacitance-voltage (CV) system (used to measure the capacitance vs. voltage and capacitance vs. time (Ct) properties of substrates such as semiconductor devices), an interferometer (used to measure distance in wavelengths and determine the wavelength of a particular light source), a source measure unit (SME) magnetometer, optical and imaging systems, a profilometer, a wafer probing device (used to test semiconductor wafers before they are separated into individual dies or chips), etc. These include: imaging stations, critical dimension scanning electron microscopes (CD-SEMs, used to ensure the stability of manufacturing processes by measuring the critical dimensions of substrates), reflectometers (used to measure the reflectivity and radiance from surfaces), resistance probes (used to measure the resistance of thin films), resistive high-energy electron diffraction (RHEED) systems (used to measure or monitor the crystal structure or crystal orientation of epitaxial thin films of silicon or other materials), and X-ray diffractometers (used to clearly determine the crystal structure, crystal orientation, film thickness, and residual stress in silicon wafers, epitaxial films, and other substrates).

[0033]

[0037] In some embodiments, the characteristic data 142 is used for equipment health and / or product health (e.g., product quality). In some embodiments, the characteristic data 142 is received over a period of time.

[0034]

[0038] In some embodiments, the sensor 126 and / or metrology device 128 provides characteristic data 142 including one or more of morphology data, size attribute data, dimensional attribute data, image data, scanning electron microscope (SEM) images, energy dispersive X-ray (EDX) images, defect distribution data, spatial location data, elemental analysis data, wafer signature data, chip layers, chip layout data, edge data, gray level data, signal-to-noise data, temperature data, spacing data, current data, power data, voltage data, and the like.

[0035]

[0039] In some embodiments, characteristic data 142 includes morphology data (e.g., data related to the shape of the substrate, such as the thickness of a deposited layer or the thickness of a residue). In some embodiments, characteristic data 142 includes size attribute data (e.g., data describing the size of an attribute of the substrate). In some embodiments, characteristic data 142 includes dimensional attribute data (e.g., data describing the dimensions of an attribute of the substrate). In some embodiments, characteristic data 142 includes SEM images (e.g., images captured by a scanning electron microscope, which uses a focused beam of electrons to scan the surface of the substrate and create a high-resolution image). In some embodiments, characteristic data 142 includes EDX images (e.g., images generated from data collected using X-ray techniques to identify the elemental composition of a material). In some embodiments, characteristic data 142 includes defect distribution data (e.g., data describing the spatial distribution, temporal distribution, etc. of defects on the substrate). In some embodiments, characteristic data 142 includes spatial location data (e.g., data describing the spatial location of an attribute, defect, element, etc. of the substrate). In some embodiments, characteristic data 142 includes elemental analysis data (e.g., data describing the elemental composition of the substrate). In some embodiments, characteristic data 142 includes wafer signature data (e.g., data describing the distribution of wafer defects in the substrate due to a single manufacturing issue). In some embodiments, characteristic data 142 includes chip layer data (e.g., relating to a layer or step in a substrate manufacturing process). In some embodiments, characteristic data 142 includes chip layout data (e.g., data describing the layout of the substrate in planar geometric shape). In some embodiments, characteristic data 142 includes edge data (e.g., data describing the edge of the wafer). For example, edge data may describe chipped edges, wafer edge thickness, wafer bow, wafer warp, etc.In some embodiments, the characteristic data 142 includes grey level data (e.g., data describing the brightness of pixels in an image of the substrate) and signal-to-noise data (e.g., data describing the signal-to-noise ratio of measurements of the substrate by a spectrometer device).

[0036]

[0040] In some embodiments, characteristic data 142 (e.g., historical characteristic data 144, current characteristic data 146, etc.) is processed (e.g., by client device 120 and / or by prediction server 112). In some embodiments, processing characteristic data 142 includes generating features. In some embodiments, the features are patterns in characteristic data 142 (e.g., slope, width, height, peaks, etc.) or combinations of values ​​from characteristic data 142 (e.g., power derived from voltage and current, etc.). In some embodiments, characteristic data 142 includes features used by prediction component 114 to obtain prediction data 160.

[0037]

[0041] In some embodiments, the metrology tool 128 may be included as part of the fabrication tool 124. For example, the metrology tool 128 may be included within or coupled to a processing chamber and configured to generate metrology data (e.g., characteristic data 142, performance data 152, etc.) of the interior of the processing chamber or of the substrate before, during, and / or after a process (e.g., a deposition process, an etch process, etc.) while the substrate remains within the processing chamber. In some implementations, the metrology tool 128 may be referred to as an in-situ metrology tool. In another example, the metrology tool 128 may be coupled to another station of the fabrication tool 124. For example, the metrology tool may be coupled to a transfer chamber, a load lock, or a factory interface.

[0038]

[0042] In some embodiments, the metrology tool 128 (e.g., an ellipsometry tool, an imaging tool, a spectroscopy tool, etc.) is used to determine metrology data (e.g., inspection data, image data, spectroscopy data, ellipsometry data, material composition data, optical data, structural data, etc.) corresponding to the interior (e.g., surface) of a processing chamber or a substrate fabricated by the fabrication tool 124 (e.g., a substrate processing device). In some examples, the metrology tool 128 is used to inspect a portion (e.g., a layer) of a substrate after the fabrication tool 124 processes the substrate. In some examples, the sensor 126 is used to inspect a portion of the interior of a processing chamber after the fabrication tool 124 processes the substrate. In some embodiments, the metrology tool 128 performs scanning acoustic microscopy (SAM), ultrasonic inspection, x-ray inspection, and / or computed tomography (CT) inspection. In some examples, the metrology tool 128 is used to determine the quality of the processed substrate (e.g., layer thickness, layer uniformity, interlayer spacing, etc.) after the fabrication tool 124 deposits one or more layers on the substrate. In some embodiments, metrology equipment 128 includes an imaging device (e.g., a SAM device, an ultrasound device, an X-ray device, a CT device, and / or the like). In some embodiments, characteristic data 142 includes sensor data from sensors 126 and / or metrology data from metrology equipment 128.

[0039]

[0043] In some embodiments, the characteristic data 142 includes sensor data from the sensors 126 and / or metrology data from metrology tools 128 located in situ (inside the process chamber). In some embodiments, the performance data 152 includes user input via the client device 120 and / or metrology data from the metrology tools 128. The characteristic data 142 may include metrology data from a first subset of the metrology tools 128. The performance data 152 may include metrology data from a second subset of the metrology tools 128.

[0040]

[0044] In some embodiments, the deposition thickness characteristic data may be derived from metrology data and / or sensor data. The metrology data may be data describing measurements of the substrate. The sensor data may be data describing conditions and characteristics inside the process chamber. In some embodiments, the deposition thickness characteristic data may include a deposition thickness value (e.g., an actual or expected amount of material deposited on the substrate). In some embodiments, the deposition thickness characteristic data may include a residue deposition thickness value (e.g., an actual or expected amount of material remaining deposited on the chamber walls). In some embodiments, the deposition thickness value is derived from a deposition process recipe (e.g., the deposition thickness is equal to the expected deposition thickness of the deposition process).

[0041]

[0045] In some embodiments, the actual deposition thickness value or actual residue thickness value may refer to the amount of material actually deposited on the substrate or remaining deposited on the process chamber walls after a deposition process. The actual deposition thickness value or actual residue thickness value may be measured using a metrology device or sensor.

[0042]

[0046] In some embodiments, the expected deposition thickness value or expected residue thickness value may refer to the amount of material expected to be deposited on a substrate or remaining deposited on a processing chamber wall after a deposition process. In some embodiments, the expected deposition thickness value or actual residue thickness value may be derived from a process recipe (e.g., deposition process parameters). In some embodiments, the expected deposition thickness value or actual residue thickness value may be derived from past actual deposition thickness values ​​or actual residue thickness values ​​corresponding to the same deposition process.

[0043]

[0047] In some embodiments, data store 140 is memory (e.g., random access memory), a drive (e.g., a hard drive, a flash drive), a database system, or other type of component or device capable of storing data. In some embodiments, data store 140 includes multiple storage components (e.g., multiple drives or multiple databases) spread across multiple computing devices (e.g., multiple server computers). In some embodiments, data store 140 stores one or more of characteristic data 142, performance data 152, and / or prediction data 160.

[0044]

[0048] In some embodiments, data store 140 can be configured to store data that is inaccessible to users of the manufacturing system. For example, process data, spectral data, contextual data, etc. acquired for substrates being processed in the manufacturing system are inaccessible to users (e.g., operators) of the manufacturing system. In some embodiments, all data stored in data store 140 can be inaccessible to users of the manufacturing system. In some embodiments, some of the data stored in data store 140 can be inaccessible to users, while other portions of the data stored in data store 140 can be accessible to users. In some embodiments, one or more portions of the data stored in data store 140 can be encrypted using an encryption mechanism unknown to the users (e.g., the data is encrypted using a private encryption key). In some embodiments, data store 140 can include multiple data stores, where data that is inaccessible to users is stored in one or more first data stores and data that is accessible to users is stored in one or more second data stores.

[0045]

[0049] Characteristic data 142 includes historical characteristic data 144 and current characteristic data 146. In some embodiments, characteristic data 142 (e.g., sensor data) may include temperature data, temperature ranges, power data, comparison parameters for comparing test data to threshold data, threshold data, cooling rate data, cooling rate ranges, etc. In some embodiments, at least a portion of characteristic data 142 is from sensors 126 and / or measurement devices 128.

[0046]

[0050] Performance data 152 includes historical performance data 154 and current performance data 156. Performance data 152 may indicate whether a substrate is properly designed, properly manufactured, consistent with other substrates, and / or functioning properly. Performance data 152 may indicate whether a substrate processing step (e.g., semiconductor processing step) is being performed accurately. For example, performance data 152 may indicate the actual thickness deposited (on a wafer or in a processing chamber) during a deposition step. Performance data 152 may indicate whether a substrate processing step (e.g., semiconductor processing step, cleaning step) was performed effectively. For example, performance data 152 may indicate the cleanliness of a processing chamber (e.g., deposition thickness on the walls of the processing chamber) before, during, or after a cleaning step, and may indicate the thickness of deposition residue, cleaning agent (e.g., aluminum fluoride), residual particle count, etc.

[0047]

[0051] In some embodiments, at least a portion of the performance data 152 relates to the quality of substrates produced by the manufacturing tool 124. In some embodiments, at least a portion of the performance data 152 is based on metrology data from the metrology tool 128 (e.g., the historical performance data 154 includes metrology data indicative of successfully processed substrates, substrate characteristic data, yield, etc.). In some embodiments, at least a portion of the performance data 152 is based on inspection of substrates or processing chamber interiors (e.g., the current performance data 156 is based on actual inspection). In some embodiments, the performance data 152 includes user input (e.g., via the client device 120) indicative of the quality of the substrates or the cleanliness of the processing chamber / substrate processing area. In some embodiments, the performance data 152 includes an indication of absolute values ​​(e.g., the substrate inspection data indicates that the substrate is below the threshold data by a calculated value, and the deformation value is below the threshold deformation value by a calculated value), or a indication of relative values ​​(e.g., the substrate inspection data indicates that the substrate is below the threshold data by 5%, and the deformation is 5% below the threshold deformation, and the process chamber cleanliness is 5% below the threshold cleanliness). In some embodiments, the performance data 152 indicates meeting a threshold amount of error (e.g., at least a 5% error in process chamber cleanliness after a cleaning step, at least a 5% error in production, at least a 5% error in flow rate, at least a 5% error in deformation, a specification limit, etc.).

[0048]

[0052] In some embodiments, the historical data includes one or more of historical characteristic data 144 and / or historical performance data 154 (e.g., at least a portion for training machine learning model 190). The current data includes one or more of current characteristic data 146 and / or current performance data 156 (e.g., at least a portion that is input to trained machine learning model 190 after training model 190 using historical data). In some embodiments, the current data is used to retrain trained machine learning model 190.

[0049]

[0053] In some embodiments, the predictive data 160 is used to cause corrective actions to be taken on a process recipe, cleaning process parameters of a cleaning recipe / process, a manufacturing tool, a substrate processing system, or components of a substrate processing apparatus.

[0050]

[0054] Performing multiple metrology types on multiple product layers or process chambers to determine whether to implement corrective action is costly in terms of time used, metrology tools 128 used, energy consumed, bandwidth used to transmit the metrology data, processor overhead to process the metrology data, etc. By providing characteristic data 142 to model 190 and receiving prediction data 160 from model 190, system 100 has the technical advantage of avoiding the costly process of using multiple types of metrology tools 128 on multiple layers of products and process chambers, avoiding wasted time and scrapped substrates.

[0051]

[0055] Performing a manufacturing process (e.g., deposition) using manufacturing equipment 124 and / or manufacturing parameters (e.g., cleaning process parameters) can result in defective products or damage to manufacturing equipment, resulting in significant losses in time, energy, product, manufacturing equipment 124, and costs of identifying corrective actions to avoid the defective products. By providing characteristic data 142 to model 190, receiving predictive data 160 from model 190, and performing corrective actions based on predictive data 160, system 100 has the technical advantage of avoiding the costs of manufacturing, identifying, and discarding defective substrates.

[0052]

[0056] In some embodiments, the prediction system 110 further includes a server machine 170 and a server machine 180. The server machine 170 includes a dataset generator 172 capable of generating datasets (e.g., a set of data inputs and a set of target outputs) for training, validating, and / or testing one or more machine learning models 190. The dataset generator 172 has functionality for collecting, editing, reducing, and / or splitting data to prepare the data for machine learning. In some embodiments (e.g., for small datasets), splitting for post-training validation (e.g., explicit splitting) is not used. Repeated cross-validation (e.g., five-fold cross-validation, leave-one-out cross-validation) may be used during training. In this case, a given dataset is effectively split repeatedly into different training and validation sets during training. A model (e.g., the best model, the model with the highest accuracy, etc.) is selected from the vector of models on the automatically separated subset of combinations. In some embodiments, the dataset generator 172 may explicitly divide the historical data (e.g., historical characteristic data 144 and corresponding historical performance data 154) into a training set (e.g., 60 percent of the historical data), a validation set (e.g., 20 percent of the historical data), and a test set (e.g., 20 percent of the historical data). Some steps of the dataset generator 172, according to some embodiments, are described in detail below with respect to FIG. 2. In some embodiments, the prediction system 110 (e.g., via the prediction component 114) generates multiple feature sets (e.g., training features).In some examples, the first feature set corresponds to a first set of types of characteristic data (e.g., a first sensor set, a first combination of values ​​from the first sensor set, a first pattern in values ​​from the first sensor set) corresponding to each dataset (e.g., a training set, a validation set, and a test set), and the second feature set corresponds to a second set of types of characteristic data (e.g., a second sensor set different from the first sensor set, a second combination of values ​​different from the first combination, a second pattern different from the first pattern) corresponding to each dataset.

[0053]

[0057] Server machine 180 includes a training engine 182, a validation engine 184, a selection engine 185, and / or a test engine 186. In some embodiments, engines (e.g., training engine 182, validation engine 184, selection engine 185, and test engine 186) refer to hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, processing device, etc.), software (e.g., instructions executing on a processing device, general-purpose computer system, or dedicated machine), firmware, microcode, or a combination thereof. Training engine 182 can train machine learning model 190 using one or more feature sets associated with a training set from dataset generator 172. In some embodiments, training engine 182 generates multiple trained machine learning models 190, each corresponding to a distinct set of parameters of the training set (e.g., characteristic data 142) and corresponding response (e.g., performance data 152). In some embodiments, multiple models are trained with the same parameters with different targets for the purpose of modeling multiple effects. In some examples, a first trained machine learning model was trained using feature data 142 from all sensors 126 (e.g., sensors 1-5), a second trained machine learning model was trained using a first subset of feature data (e.g., data from sensors 1, 2, and 4), and a third trained machine learning model was trained using a second subset of feature data that partially overlaps with the first subset of features (e.g., data from sensors 1, 3, 4, and 5).

[0054]

[0058] The validation engine 184 can validate the trained machine learning models 190 using corresponding feature sets of the validation set from the dataset generator 172. For example, a first trained machine learning model 190 trained using a first feature set of the training set is validated using the first feature set of the validation set. The validation engine 184 determines the accuracy of each of the trained machine learning models 190 based on the corresponding feature sets of the validation set. The validation engine 184 evaluates and flags (e.g., discards) trained machine learning models 190 that have an accuracy that does not meet a threshold accuracy. In some embodiments, the selection engine 185 can select one or more trained machine learning models 190 that have an accuracy that meets the 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.

[0055]

[0059] The testing engine 186 can test the trained machine learning models 190 using the corresponding feature sets of the test set from the dataset generator 172. For example, a first trained machine learning model 190 trained using a first feature set of the training set is tested using the first feature set of the test set. The testing engine 186 determines the trained machine learning model 190 with the highest accuracy among all the trained machine learning models based on the test set.

[0056]

[0060] In some embodiments, machine learning model 190 (e.g., used for classification) refers to a model artifact created by training engine 182 using a training set containing data inputs and corresponding target outputs (e.g., correctly classifying states or ordinal levels for each training input). Patterns are found in the dataset that map data inputs to target outputs (correct classifications or levels). Machine learning model 190 is provided with mappings that capture these patterns. In some embodiments, machine learning model 190 uses one or more of Gaussian process regression (GPR), Gaussian process classification (GPC), Bayesian neural networks, neural network Gaussian processes, deep belief networks, Gaussian mixture models, or other probabilistic learning methods. Non-probabilistic methods may also be used, including one or more of support vector machines (SVMs), radial basis functions (RBFs), clustering, nearest neighbor algorithms (k-NNs), linear regression, random forests, neural networks (e.g., artificial neural networks), etc. In some embodiments, the machine learning model 190 is a multivariate analysis (MVA) regression model.

[0057]

[0061] The prediction component 114 provides the current characteristic data 146 (e.g., as input) to the trained machine learning model 190 and executes the trained machine learning model 190 (e.g., runs it on the input and obtains one or more outputs). The prediction component 114 can determine (e.g., extract) predicted data 160 from the trained machine learning model 190 and determine (e.g., extract) uncertainty data that indicates a level of confidence that the predicted data 160 corresponds to the current performance data 156. In some embodiments, the prediction component 114 or the corrective action component 122 uses the uncertainty data (e.g., an uncertainty function or a derived function derived from the uncertainty function) to determine whether to use the predicted data 160 to perform corrective action or whether to further train the model 190.

[0058]

[0062] For purposes of illustration and not limitation, aspects of the present disclosure describe training one or more machine learning models 190 using historical data (i.e., prior data, historical characteristic data 144, and historical performance data 154) and providing current characteristic data 146 to one or more trained probabilistic machine learning models 190 to determine predicted data 160. In other implementations, heuristic or rule-based models are used to determine predicted data 160 (e.g., without using a trained machine learning model). In other implementations, non-probabilistic machine learning models may be used. The prediction component 114 monitors the historical characteristic data 144 and the historical performance data 154. In some embodiments, any of the information described with respect to data input 210 in FIG. 2 is monitored or otherwise used in the heuristic or rule-based models.

[0059]

[0063] In some embodiments, the functionality of client device 120, prediction server 112, server machine 170, and server machine 180 is provided by fewer machines. For example, in some embodiments, server machines 170 and 180 are combined into a single machine, while in some other embodiments, server machine 170, server machine 180, and prediction server 112 are combined into a single machine. In some embodiments, client device 120 and prediction server 112 are combined into a single machine.

[0060]

[0064] In general, functions described in one embodiment as being performed by client device 120, prediction server 112, server machine 170, and server machine 180 may be performed by prediction server 112 in other embodiments, where appropriate. Additionally, functionality attributed to a particular component may be performed by a different component or multiple components operating together. For example, in some embodiments, prediction server 112 determines corrective actions based on prediction data 160. In another example, client device 120 determines prediction data 160 based on data received from a trained machine learning model.

[0061]

[0065] Furthermore, the functionality of a particular component may be performed by a different component or multiple components working together. In some embodiments, one or more of prediction server 112, server machine 170, or server machine 180 are accessed as a service offered to other systems or devices through an appropriate application programming interface (API).

[0062]

[0066] In some embodiments, a film may be deposited on the surface of the substrate and the surface of the processing chamber during a deposition process (e.g., a chemical vapor deposition (CVD) process, an atomic layer deposition (ALD) process, etc.) performed in a processing chamber of a manufacturing system. For example, in a CVD process, the substrate is exposed to one or more precursors, which react on the substrate surface to produce the desired deposit. A film may also be deposited on the interior surfaces of the processing chamber.

[0063]

[0067] The manufacturing system can perform one or more processes on a substrate, which can be any planar article of fixed dimensions and suitable rigidity suitable for fabricating electronic devices or circuit components thereon, such as, for example, a silicon-containing disk or wafer, a patterned wafer, a glass sheet, a plate, or the like.

[0064]

[0068] The processing chambers can perform any number of processes on a substrate. The same or different substrate processes can be performed in each individual processing chamber. The substrate processes can include atomic layer deposition (ALD), physical vapor deposition (PVD), chemical vapor deposition (CVD), etching, annealing, curing, pre-cleaning, metal or metal oxide removal, etc. Other processes can be performed on the substrate therein. The processing chambers can include one or more sensors configured to capture data on the substrate before, after, or during substrate processing. For example, the one or more sensors can be configured to capture deposition thickness characteristic data (e.g., chamber residue thickness) of either the substrate or the processing chamber. In other or similar embodiments, the one or more sensors can be configured to capture data related to the environment within the processing chamber before, after, or during substrate processing. For example, the one or more sensors can be configured to capture data related to the temperature, pressure, gas concentration, particle count (e.g., cleaning agent particle count), etc. of the environment within the processing chamber during substrate processing.

[0065]

[0069] In some embodiments, sensors may not be used to capture deposition thickness profile data or either the substrate or the processing chamber. In some embodiments, the deposition thickness profile is determined based on deposition process or deposition recipe parameters. For example, the deposition process may be configured to deposit a 30 angstrom film. The deposition thickness profile data is derived from such deposition process parameters.

[0066]

[0070] The process may use a processing chamber in which a corrosive plasma environment is provided. For example, the processing chamber may be a chamber such as a plasma etcher or a plasma etch reactor. In another example, the processing chamber may be a chamber for a deposition process, as described above. The chamber body may be fabricated from aluminum, stainless steel, or other suitable materials, such as titanium (Ti). The chamber body generally includes a sidewall and a bottom (e.g., a processing chamber surface).

[0067]

[0071] In some embodiments, the processing chamber may include a metrology device configured to generate in-situ metrology measurements during a process (e.g., a deposition process) performed in the processing chamber. In some embodiments, the metrology device may be configured to generate metrology measurements (e.g., thickness) of a film or deposition residue during a particular instance of a deposition process. In other or similar embodiments, the processing chamber may not include a metrology device. In such embodiments, the system controller may receive one or more metrology measurements of the film or deposition residue after completion of a deposition process in the processing chamber. In some embodiments, the thickness of the deposition residue may be equal to the thickness of the deposited material. The system controller may determine a deposition rate based on the one or more metrology measurements and may generate an associated thickness profile of the film or deposition residue thickness based on the determined concentration gradient and the determined deposition rate of the deposition process.

[0068]

[0072] In some embodiments, the processing chamber may include a sensor configured to generate in-situ sensor data before, during, and / or after a process (e.g., a deposition process) performed in the processing chamber. In some embodiments, the sensor may be configured to generate sensor data values ​​(e.g., thickness) of a film or deposition residue during a particular instance of the deposition process. In other or similar embodiments, the processing chamber may not include a sensor. In such embodiments, the system controller may instead receive one or more metrology measurements for the film or deposition residue after completion of the deposition process in the processing chamber. In some embodiments, the thickness of the deposition residue may be equal to the thickness of the deposited material. The system controller may determine a deposition rate based on the one or more sensor data values ​​and may generate an associated thickness profile of the film or deposition residue thickness based on the determined concentration gradient and the determined deposition rate of the deposition process.

[0069]

[0073] The processing chamber can perform each substrate manufacturing process (e.g., deposition process, etching process, polishing process, etc.) according to a process recipe. The process recipe defines a particular set of steps, including a cleaning step, to be performed during the process and can include one or more settings or parameters associated with each step. For example, a cleaning step can include a setting for the amount of cleaning time, a setting for the temperature of the processing chamber, a setting for the pressure of the processing chamber, a setting for cleaning intensity, etc.

[0070]

[0074] In some embodiments, a "user" is represented as a single individual. However, other embodiments of the present disclosure encompass a "user" being an entity controlled by multiple users and / or automated sources. In some examples, a collection of individual users working together as a group of administrators is considered a "user."

[0071]

[0075] Although embodiments of the present disclosure are described in terms of determining predictive data 160 for a cleaning process based on deposition thickness associated with substrate processing in a manufacturing facility (e.g., a substrate processing facility), in some embodiments the present disclosure may also be applied to corrective actions in manufacturing facilities generally. Embodiments may be applied generally to determining part quality based on different types of data.

[0072]

[0076] 2 illustrates a dataset generator 272 (e.g., dataset generator 172 of FIG. 1 ) for creating a dataset for a machine learning model (e.g., associated with a cleaning process based on deposition thickness, methods 400A-C, etc.) (e.g., model 190 of FIG. 1 ), according to certain embodiments. In some embodiments, dataset generator 272 is part of server machine 170 of FIG. 1 . The dataset generated by dataset generator 272 of FIG. 2 can be used to train a machine learning model (e.g., see FIG. 4B ) that performs corrective actions (e.g., see FIG. 4C ).

[0073]

[0077] A dataset generator 272 (e.g., dataset generator 172 in FIG. 1 ) creates a dataset for a machine learning model (e.g., model 190 in FIG. 1 ). The dataset generator 272 uses historical characteristics 244 (e.g., historical characteristic data 144 in FIG. 1 ) and historical performance data 254 (e.g., historical performance data 154 in FIG. 1 ) to create the dataset. The system 200 in FIG. 2 shows the dataset generator 272, a data input 210, and a target output 220 (e.g., target data).

[0074]

[0078] In some embodiments, the dataset generator 272 generates a dataset (e.g., a training set, a validation set, a test set) that includes one or more data inputs 210 (e.g., training inputs, validation inputs, test inputs). In some embodiments, the dataset generator 272 does not generate a target output (e.g., for unsupervised learning). In some embodiments, the dataset generator generates one or more target outputs 220 (e.g., for supervised learning) that correspond to the data inputs 210. The dataset may also include mapping data that maps the data inputs 210 to the target outputs 220. The data inputs 210 are also referred to as “features,” “attributes,” or “information.” In some embodiments, the dataset generator 272 provides the dataset to the training engine 182, the validation engine 184, or the test engine 186, where the dataset is used to train, validate, or test a machine learning model 190 (e.g., related to a deposition thickness-based cleaning process, methods 400A-C, etc.).

[0075]

[0079] In some embodiments, the data set generator 272 generates the data input 210 and the target output 220. In some embodiments, the data input 210 includes one or more sets of historical characteristic data 244 (e.g., associated with a cleaning process based on deposition thickness, methods 400A-C, etc.). In some embodiments, the historical characteristic data 244 includes one or more of characteristic data from one or more types of sensors and / or metrology devices, combinations of characteristic data from one or more types of sensors and / or metrology devices, patterns from characteristic data from one or more types of sensors and / or metrology devices, etc.

[0076]

[0080] In some embodiments, the dataset generator 272 generates a first data input corresponding to a first set of historical characteristic data 244A for training, validating, or testing a first machine learning model, and the dataset generator 272 generates a second data input corresponding to a second set of historical characteristic data 244B for training, validating, or testing a second machine learning model (e.g., associated with a cleaning process based on deposition thickness, methods 400A-C, etc.).

[0077]

[0081] In some embodiments, the dataset generator 272 discretizes (e.g., segments) one or more of the data inputs 210 or the target outputs 220 (e.g., for use in a classification algorithm for a regression problem). Discretizing the data inputs 210 or the target outputs 220 (e.g., segmenting by a sliding window) converts continuous values ​​of variables into discrete values. In some embodiments, the discrete values ​​of the data inputs 210 represent discrete historical characteristic data 144 (e.g., discrete historical performance data 154 associated with a cleaning process based on deposition thickness, methods 400A-C, etc.) for deriving the target outputs 220.

[0078]

[0082] The data input 210 and target output 220 for training, validating, or testing a machine learning model include information about a particular facility (e.g., a particular substrate manufacturing facility). In some examples, the historical characteristic data 244 and the historical performance data 254 are for the same manufacturing facility (e.g., associated with a cleaning process based on deposition thickness, methods 400A-C, etc.).

[0079]

[0083] In some embodiments, the information used to train the machine learning model is from a particular type of manufacturing equipment 124 at a manufacturing facility having particular characteristics, allowing the trained machine learning model (e.g., associated with a cleaning process based on deposition thickness, methods 400A-C, etc.) to determine an outcome for a particular group of manufacturing equipment 124 based on input of current parameters (e.g., current characteristic data 146) associated with one or more components that share the characteristics of the particular group. In some embodiments, the information used to train the machine learning model is for components from more than one manufacturing facility, allowing the trained machine learning model to determine an outcome for a component based on input from one manufacturing facility.

[0080]

[0084] In some embodiments, after generating a dataset and using the dataset to train, validate, or test a machine learning model 190 (e.g., associated with a cleaning process based on deposition thickness, methods 400A-C, etc.), the machine learning model 190 is further trained, validated, or tested (e.g., current performance data 156 of FIG. 1 ) or adjusted (e.g., adjusting weights associated with the input data of the machine learning model 190, such as connection weights of a neural network).

[0081]

[0085] A machine learning model processes inputs to generate outputs (e.g., associated with a cleaning process based on deposition thickness, methods 400A-C, etc.). An artificial neural network includes an input layer consisting of data point values. The next layer is called the hidden layer, and each node in the hidden layer receives one or more input values. Each node contains parameters (e.g., weights) to apply to the input values. Thus, each node essentially inputs the input values ​​into a multivariate function (e.g., a nonlinear mathematical transformation) to generate an output value. The next layer can be another hidden layer or an output layer. In either case, the nodes in the next layer receive output values ​​from the nodes in the previous layer, and each node applies a weight to the value before generating its own output value. This can be done at each layer. The final layer is the output layer, where there is one node for each class, prediction, and / or output that the machine learning model can generate.

[0082]

[0086] Thus, the output may include one or more predictions or inferences (e.g., associated with a cleaning process based on deposition thickness, methods 400A-C, etc.). For example, the output predictions or inferences may include one or more predictions of film buildup on chamber components, process chamber cleanliness, residue deposition thickness after a cleaning process, erosion of a chamber component, chamber component failure prediction, etc. Processing logic determines an error (i.e., classification error) based on the difference between the output (e.g., prediction or inference) of the machine learning model and a target label associated with the input training data. Processing logic adjusts weights of one or more nodes in the machine learning model based on the error. An error term or delta may be determined for each node of the artificial neural network. Based on the error, the artificial neural network adjusts one or more of its own parameters (weights for one or more inputs of the node) of one or more of its own nodes. The parameters may be updated in a backpropagation manner, where the nodes in the top layer are updated first, followed by the nodes in the next layer, and so on. An artificial neural network includes multiple layers of "neurons," each of which receives as input values ​​from neurons in the previous layer. The parameters for each neuron include weights associated with the values ​​received from each neuron in the previous layer. Adjusting the parameters may therefore include adjusting the weights assigned to each of the inputs for one or more neurons of one or more layers in the artificial neural network.

[0083]

[0087] After one or more rounds of training, processing logic may determine whether a stopping criterion has been met. The stopping criterion may be a target level of accuracy, a target number of processed images from the training dataset, a target amount of change in a parameter relative to one or more previous data points, combinations thereof, and / or other criteria. In one embodiment, A 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 when the accuracy of the machine learning model stops improving. If the stopping criterion is not met, further training is performed. Once the stopping criterion is met, training may be complete. Once the machine learning model is trained, a reserved portion of the training dataset may be used to test the model.

[0084]

[0088] 3 is a block diagram illustrating a system 300 for generating predictive data 360 (e.g., predictive data 160 of FIG. 1 ), according to certain embodiments. System 300 is used to determine predictive data 360 via a trained machine learning model (e.g., model 190 of FIG. 1 ) for deposition thickness-based cleaning (e.g., chamber cleaning optimized by utilizing a deposition thickness counter).

[0085]

[0089] In block 310, the system 300 (e.g., the prediction system 110 of FIG. 1 ) performs data partitioning (e.g., via the dataset generator 172 of the server machine 170 of FIG. 1 ) of historical data (e.g., the historical characteristic data 344 and / or the historical performance data 354 of the model 190 of FIG. 1 ) to generate a training set 302, a validation set 304, and a test set 306 (e.g., associated with a cleaning process based on deposition thickness, methods 400A-C, etc.). In some examples, the training set is 60% of the historical data, the validation set is 20% of the historical data, and the test set is 20% of the historical data. The system 300 generates multiple feature sets for each of the training set, validation set, and test set. In some examples, if the historical data includes features from 20 sensors (e.g., sensor 126 of FIG. 1 , sensors of manufacturing equipment and / or metrology equipment) and 100 products (e.g., products each corresponding to characteristic data from the 20 sensors), the first feature set would be sensors 1-10, the second feature set would be sensors 11-20, the training set would be products 1-60, the validation set would be products 61-80, and the test set would be products 81-100. In this example, the first feature set in the training set would be parameters from sensors 1-10 of products 1-60.

[0086]

[0090] At block 312, the system 300 performs model training (e.g., via the training engine 182 of FIG. 1 associated with a cleaning process based on deposition thickness, methods 400A-C, etc.) using the training set 302. In some embodiments, the system 300 trains multiple models using multiple feature sets of the training set 302 (e.g., a first feature set of the training set 302, a second feature set of the training set 302, etc.). For example, the system 300 trains machine learning models to generate a first trained machine learning model using the first feature set in the training set (e.g., characteristic data from sensors 1-10 of products 1-60) and to generate a second trained machine learning model using the second feature set in the training set (e.g., characteristic data from sensors 11-20 of products 1-60). In some embodiments, the first trained machine learning model and the second trained machine learning model are combined to generate a third trained machine learning model (e.g., in some embodiments, which is itself a better predictor than the first or second trained machine learning model). In some embodiments, feature sets are used when comparing model overlap (e.g., a first feature set is feature data from sensors 1-15, and a second feature set is feature data from sensors 5-20). In some embodiments, hundreds of models are generated, including models with various feature permutations and model combinations.

[0087]

[0091] At block 314, system 300 performs model validation (e.g., via validation engine 184 of FIG. 1 ) using validation set 304. System 300 validates each of the trained models (e.g., associated with a cleaning process based on deposition thickness, methods 400A-C, etc.) using the corresponding feature set in validation set 304. For example, system 300 validates a first trained machine learning model using a first feature set in the validation set (e.g., parameters from sensors 1-10 of products 61-80) and validates a second trained machine learning model using a second feature set in the validation set (e.g., parameters from sensors 11-20 of products 61-80). In some embodiments, system 300 validates hundreds of models (e.g., models with various permutations of features, combinations of models, etc.) generated in block 312. In block 314, the system 300 determines the accuracy of each of the one or more trained models (e.g., via model validation) and determines whether one or more of the trained models have an accuracy that meets the threshold accuracy. In response to a determination that none of the trained models have an accuracy that meets the threshold accuracy, flow returns to block 312, where the system 300 performs model training using a different feature set from the training set. In response to a determination that one or more of the trained models have an accuracy that meets the threshold accuracy, flow continues to block 316. The system 300 discards trained machine learning models that have an accuracy below the threshold accuracy (e.g., based on a validation set).

[0088]

[0092] In block 316, the system 300 performs model selection (e.g., via selection engine 185 of FIG. 1 ) to determine the one or more trained models that meet the threshold accuracy that has the highest accuracy (e.g., model 308 selected based on the validation of block 314). In response to a determination that two or more trained models that meet the threshold accuracy have the same accuracy, flow returns to block 312, where the system 300 performs model training using a further refined training set corresponding to the further refined feature set to determine the trained model with the highest accuracy.

[0089]

[0093] At block 318, the system 300 performs model testing (e.g., via the test engine 186 of FIG. 1 ) using the test set 306 to test the selected model 308. The system 300 tests the first trained machine learning model using a first feature set of the test set (e.g., characteristic data from sensors 1-10 of products 81-100) to determine (e.g., based on the first feature set of the test set 306) that the first trained machine learning model meets a threshold accuracy. In response to the accuracy of the selected model 308 not meeting the threshold accuracy (e.g., the selected model 308 is overfitted to the training set 302 and / or the validation set 304 and is not applicable to other datasets, such as the test set 306), flow continues to block 312, where the system 300 performs model training (e.g., retraining) using a different training set corresponding to a different set of features (e.g., characteristic data from a different sensor). In response to determining that the selected model 308 has an accuracy that meets the threshold accuracy based on the test set 306, flow continues to block 320. At least in block 312, the model learns patterns in the historical data to make predictions, and in block 318, the system 300 applies the model to the remaining data (e.g., the test set 306) to test the predictions (e.g., associated with a cleaning process based on deposition thickness, methods 400A-C, etc.).

[0090]

[0094] In block 320, the system 300 receives current characteristic data 346 (e.g., current characteristic data 146 of FIG. 1 ) using the trained model (e.g., selected model 308) and determines (e.g., extracts) from the trained model predicted data 360 (e.g., predicted data 160 of FIG. 1 ) for the cleaning process based on deposition thickness to perform corrective actions (e.g., modify cleaning process parameters, cleaning recipe, process recipe, etc.). In some embodiments, the current characteristic data 346 corresponds to the same feature types as the historical characteristic data 344. In some embodiments, the current characteristic data 346 corresponds to the same feature types as a subset of the feature types of the historical characteristic data 344 used to train the selected model 308 (e.g., associated with the cleaning process based on deposition thickness, methods 400A-C, etc.).

[0091]

[0095] In some embodiments, current data is received. In some embodiments, the current data includes current performance data 356 (e.g., current performance data 156 of FIG. 1 ) and / or current characteristic data 346 (e.g., associated with a cleaning process based on deposition thickness, methods 400A-C, etc.). In some embodiments, at least a portion of the current data is received from a metrology tool (e.g., metrology tool 128 of FIG. 1 ) or via user input. In some embodiments, a model is retrained based on the current data. In some embodiments, a new model is trained based on the current performance data 356 and the current characteristic data 346.

[0092]

[0096] In some embodiments, one or more of blocks 310-320 are performed in various orders and / or with other steps not presented and described herein. In some embodiments, one or more of blocks 310-320 are not performed. For example, in some embodiments, one or more of data partitioning of block 310, model validation of block 314, model selection of block 316, and / or model testing of block 318 are not performed.

[0093]

[0097] 4A-C are flow diagrams of methods 400A-C relating to deposition thickness-based cleaning, according to certain embodiments. In some embodiments, methods 400A-D are performed by processing logic including hardware (e.g., circuitry, dedicated logic, programmable logic, microcode, processing device, etc.), software (e.g., instructions executed on a processing device, a general-purpose computer system, or a dedicated machine), firmware, microcode, or a combination thereof. In one implementation, method 400A may be performed by a computer system such as computer system architecture 100 of FIG. 1. In other or similar implementations, one or more steps of method 400A may be performed by one or more other machines not depicted in the figures. In some embodiments, methods 400A-C are performed, at least in part, by prediction system 110. In some embodiments, method 400A is performed by client device 120 (e.g., corrective action component 122) and / or prediction system 110 (e.g., prediction component). In some embodiments, method 400B is performed by server machine 180 (e.g., training engine 182, etc.). In some embodiments, method 400C is performed by prediction server 112 (e.g., prediction component 114) and / or client device 120 (e.g., corrective action component 122). In some embodiments, a non-transitory storage medium stores instructions that, when executed by a processing device (e.g., a processing device such as prediction system 110, server machine 180, prediction server 112, client device 120, etc.), cause the processing device to perform one or more of methods 400A-C.

[0094]

[0098] For ease of explanation, methods 400A-C are shown and described as a series of steps. However, steps in accordance with the present disclosure may occur in various orders and / or simultaneously with and in conjunction with other steps not shown and described herein. Furthermore, in some embodiments, not all illustrated steps are performed to implement methods 400A-C in accordance with the disclosed subject matter. Additionally, those skilled in the art will understand and appreciate that methods 400A-C may alternatively be represented as a series of interrelated states via a state diagram or events.

[0095]

[0099] FIG. 4A is a flow diagram of a method relating to cleaning based on deposition thickness, according to an embodiment of the present disclosure.

[0096]

[0100] Referring to FIG. 4A , in some embodiments, at block 402, processing logic performing method 400A identifies deposition thickness characteristic data related to the amount of material deposited via one or more substrate processing steps (e.g., semiconductor processing steps) of a process recipe executed in a processing chamber. In some embodiments, processing logic may identify the deposition thickness characteristic data via a sensor that collects the deposition thickness characteristic data (e.g., by measuring the thickness of deposition residue on the processing chamber walls). In some embodiments, processing logic may identify the deposition thickness characteristic data based on an expected thickness added to the substrate (e.g., semiconductor) (e.g., thickness parameters of the deposition step, a measured thickness from a previous run of the same deposition step, etc.). In some embodiments, processing logic may identify the deposition thickness characteristic data based on the material deposited and the time the material was deposited (e.g., process recipe, deposition step parameters, etc.). In some embodiments, processing logic may identify the deposition thickness characteristic data based on metrology data of a substrate (e.g., semiconductor) that has undergone a substrate processing step (e.g., a deposition step, semiconductor processing step).

[0097]

[0101] At block 404, processing logic determines cleaning process parameters (e.g., duration, intensity, cleaning agent, cleaning type, number of cycles, etc.) based on the deposition thickness characteristic data and the variable cleaning time relationship of the process recipe. In some embodiments, processing logic may use one or more mathematical formulas or models to generate the updated cleaning process parameters. In some embodiments, the variable cleaning time relationship is a mathematical relationship, equation, function, etc. In some embodiments, the input of the formula or function is the deposition thickness (e.g., deposition thickness counter), and the output of the formula is the cleaning process parameter (e.g., cleaning duration).

[0098]

[0102] In some embodiments, for example, the mathematical equation is a third order polynomial equation, expressed as follows: y=ax 3 +bx 2 +cx+d where (x,y) are coordinates and a, b, c, and d are constants. A third-order polynomial equation is used here as an example, but any order polynomial equation can be used. In some embodiments, "x" is replaced by the current value of the deposition thickness counter for the slot running the recipe. For example, if the deposition thickness counter is equal to 10 angstroms, then 10 would be substituted as the "x" value into the above equation, and the resulting output would be a variable cleaning time.

[0099]

[0103] In some embodiments, the cleaning time endpoint can be determined using an input equation (e.g., a variable cleaning time relationship). In some embodiments, if a cleaning time endpoint is used in a process, the process will run for an amount of time calculated based on the input equation. This equation can be applied to each substrate processing region within the processing chamber.

[0100]

[0104] At block 406, processing logic causes a cleaning process to be performed in the processing chamber based on the cleaning process parameters. In some embodiments, the cleaning process can be a dry cleaning (e.g., gas phase cleaning, fluorine-containing gas cleaning, plasma dry cleaning, oxygen plasma cleaning, etc.). In some embodiments, the cleaning process can be a wet cleaning (e.g., hydrogen fluoride (HF) cleaning, acetone / water / isopropanol wipe cleaning, etc.).

[0101]

[0105] In some embodiments, the cleaning step of block 406 may over-clean or under-clean the processing chamber. In some embodiments, following block 406, performance data related to the cleaning step may be identified. In some embodiments, certain portions of method 400A may be updated based on the performance data (e.g., updating deposition thickness characteristic data related to the amount of material deposited through one or more substrate processing steps (e.g., semiconductor processing steps), updating variable cleaning time relationships, updating cleaning step parameters, etc.). In some embodiments, the updated method 400A may be repeated to more accurately perform the cleaning step.

[0102]

[0106] In some embodiments, the deposition thickness characteristic data may include at least one of a material type or a thickness counter. In some embodiments, the processing logic may further reset the thickness counter after the cleaning step is performed. In some embodiments, the cleaning step parameters may include an amount of cleaning time. In some embodiments, the thickness counter is an expected deposition thickness based on the deposition process and the number of times the process is repeated. For example, the deposition step may be expected to deposit a 20 angstrom film. After the first iteration of the deposition step, the deposition thickness counter is equal to 20 angstroms. After the second iteration of the deposition step, the deposition thickness counter is equal to 40 angstroms, and so on.

[0103]

[0107] In some embodiments, the processing chamber may include a substrate processing region, and in some embodiments, the determination of the cleaning process parameters may be based on at least one deposition thickness characteristic data of the substrate processing region and a variable cleaning time relationship of the process recipe.

[0104]

[0108] In some embodiments, determining the cleaning process parameters may include providing the deposition thickness characteristic data as input to a trained machine learning model associated with a variable cleaning time relationship and receiving an output from the trained machine learning model associated with predicted data, wherein the cleaning process parameters are based on the predicted data. In some embodiments, the trained machine learning model may be trained using data inputs including historical deposition thickness characteristic data and target outputs including historical performance data.

[0105]

[0109] FIG. 4B is a flow diagram of a method for training a machine learning model (e.g., model 190 of FIG. 1 ) to determine predictive data (e.g., predictive data 160 of FIG. 1 ) associated with a cleaning process based on deposition thickness, according to an embodiment of the present disclosure.

[0106]

[0110] 4B, at block 410 of method 400B, processing logic identifies past deposition thickness characteristic data for the substrate (e.g., past characteristic data 144 of FIG. 1). The past characteristic data may include data from past substrates, past processing chamber characteristic data, etc.

[0107]

[0111] In some embodiments, at block 412, the processing logic identifies historical performance data (e.g., historical performance data 154 of FIG. 1 ) for substrates, processing chambers (e.g., processing chamber cleanliness), process recipes, cleaning step parameters, etc. The historical performance data may include data from past processing chambers, such as one or more values ​​for cleanliness, deposit residue thickness, particle counts, etc. (e.g., after a cleaning step). Performance data including historical performance data may include metrology data or user input indicative of substrate performance in meeting particular parameters or achieving a particular performance level (e.g., ability to pass a probe test that measures voltage). Performance data including historical performance data may include metrology data or user input indicative of processing chamber performance in meeting particular parameters or reaching a particular performance level (e.g., ability to pass a cleanliness test). At least a portion of the historical characteristic data and historical performance data may be associated with new substrate processing equipment parts (e.g., used for benchmarking). At least a portion of the historical characteristic data and historical performance data may be associated with manufactured substrates. At least a portion of the historical characteristic data and historical performance data may be associated with a processing chamber.

[0108]

[0112] At block 414, processing logic trains a machine learning model using data inputs including historical characteristic data 144 and / or target outputs including historical performance data 154 to generate a trained machine learning model.

[0109]

[0113] In some embodiments, the historical characteristic data is of a past substrate or processing chamber, and / or the historical performance data corresponds to a past substrate or processing chamber. In some embodiments, the historical characteristic data includes past metrology of a past substrate or processing chamber, and / or the historical performance data corresponds to a past substrate or processing chamber. The historical performance data may relate to substrate quality, such as substrate metrology data, substrate throughput, substrate defects, etc. The historical performance data may relate to processing chamber quality, such as cleanliness. The historical performance data may relate to process recipe quality or cleaning process parameters, such as the ability to properly clean a processing chamber after a deposition process. The historical performance data may relate to the quality of components of a substrate processing equipment, such as test data, substrate metrology data, substrate downtime, etc.

[0110]

[0114] In block 414, a machine learning model may be trained using target outputs including historical deposition thickness characteristic data and / or historical performance data to generate a trained machine learning model configured to determine cleaning process parameters and perform a cleaning process based on the characteristic data (e.g., the characteristic data of block 402 of FIG. 4A ). In some embodiments, the trained machine learning model may be configured to predict performance data 152 (e.g., performance data of an updated process recipe, updated cleaning process parameters, etc.) based on the characteristic data 142 (e.g., the deposition thickness characteristic data of blocks 402 and 404 of FIG. 4A ). In response to the predicted performance data meeting a first threshold (e.g., the processing chamber is over-cleaned), processing logic may cause a corrective action (e.g., updating the cleaning process parameters, updating the process recipe, etc.). In response to the predicted performance data meeting a second threshold (e.g., the processing chamber is under-cleaned), processing logic may cause a corrective action (e.g., updating the cleaning process parameters, updating the process recipe, etc.). In response to the predicted performance data meeting both the first threshold and the second threshold, the processing logic may prevent corrective action from being taken (e.g., causing the process recipe to remain the same, causing the cleaning step parameters to remain the same, etc.).

[0111]

[0115] In some embodiments, the historical deposition thickness characteristic data in block 410 is for a past substrate and / or a past processing chamber, and the historical performance data in block 412 corresponds to a past substrate and / or a past processing chamber. In some embodiments, the historical characteristic data in block 410 relates to processing of a past substrate, and the historical performance data in block 412 corresponds to a past cleaning step following processing of a past substrate.

[0112]

[0116] FIG. 4C is a method 400C for performing a cleaning process using a trained machine learning model (e.g., model 190 of FIG. 1) for cleaning based on deposition thickness.

[0113]

[0117] 4C, in block 420 of method 400C, processing logic identifies deposition thickness characteristic data. In some embodiments, the deposition thickness characteristic data in block 420 includes a deposition residue thickness, a deposition thickness counter, etc. In some embodiments, block 420 is similar to block 402 of FIG. 4A.

[0114]

[0118] At block 422, processing logic provides the deposition thickness characteristic data as data input to a trained machine learning model (e.g., trained via block 414 of FIG. 4B) associated with a variable cleaning time relationship.

[0115]

[0119] At block 424, processing logic receives output from the trained machine learning model related to predicted data, where the wash process parameters are based on the predicted data.

[0116]

[0120] At block 426, processing logic causes a cleaning operation to be performed in the processing chamber based on the prediction data. In some embodiments, the characteristic data 142 is images of substrates, and the trained machine learning model at block 422 was trained using data inputs including historical deposition thickness characteristics and data of past substrates and past deposition operations, and target outputs including historical performance data 154 (e.g., substrate quality using past substrate processing equipment parts, process chamber cleanliness, etc.).

[0117]

[0121] 4A includes training a machine learning model (e.g., using data inputs including historical characteristic data 144 and / or target outputs including historical performance data 154 to generate the trained machine learning model) to identify deposition thickness characteristic data associated with an amount of material deposited via one or more substrate processing steps (e.g., semiconductor processing steps) of a process recipe executed in the processing chamber. In some embodiments, block 402 of FIG. 4A includes using the trained machine learning model (e.g., using data inputs including deposition thickness characteristic data and / or target outputs including deposition thickness characteristic data) to identify deposition thickness characteristic data associated with an amount of material deposited via one or more substrate processing steps (e.g., semiconductor processing steps) of a process recipe executed in the processing chamber.

[0118]

[0122] 4A includes training a machine learning model (e.g., using data inputs including historical characteristic data 144 and / or target outputs including historical performance data 154 to generate the trained machine learning model) to determine cleaning process parameters based on the deposition thickness characteristic data and the variable cleaning time relationship of the process recipe. In some embodiments, block 402 of FIG. 4A includes using the trained machine learning model (e.g., using data inputs including deposition thickness characteristic data and / or target outputs including cleaning process parameters) to determine cleaning process parameters based on the deposition thickness characteristic data and the variable cleaning time relationship of the process recipe.

[0119]

[0123] In some embodiments, the characteristic data 142 is expected or actual deposition thickness characteristic data (e.g., expected or actual deposition thickness associated with a deposition process), and the trained machine learning model of block 422 was trained using data inputs including historical expected or actual deposition thicknesses and target outputs including historical performance data 154 (e.g., historical substrate quality using substrate processing equipment component or process chamber cleanliness). In some embodiments, the cleanliness of a process chamber may indicate that the process chamber is over-cleaned or under-cleaned.

[0120]

[0124] In some embodiments, the characteristic data 142 is deposition thickness characteristic data, and the trained machine learning model of block 422 was trained using a data input including historical deposition thickness characteristic data and a target output including historical performance data 154, which includes historical sensor data (e.g., thickness of deposition residue in a processing chamber after a previous deposition operation). The predicted data 160 of block 424 may be associated with predicted performance data (e.g., performance data for a substrate or performance data for a cleaning recipe or process) based on the deposition thickness characteristic data. In response to the predicted performance data not meeting a first threshold (e.g., the processing chamber is over-cleaned), processing logic may cause corrective action (e.g., updating the process recipe, updating cleaning process parameters, etc.). In response to the predicted performance data not meeting a second threshold (e.g., the processing chamber is under-cleaned), processing logic may cause corrective action (e.g., updating the process recipe, updating cleaning process parameters, etc.). In response to the substrate satisfying both the first threshold and the second threshold, the processing logic may prevent corrective action from being taken (e.g., causing the process recipe to remain the same, causing the cleaning step parameters to remain the same, etc.).

[0121]

[0125] In some embodiments, the thresholds may correspond to the processing chamber being under-cleaned. For example, a first threshold may correspond to a residue buildup thickness below a certain value (e.g., 1 Angstrom). In some embodiments, meeting the first threshold may correspond to the processing chamber being sufficiently cleaned, and not meeting the first threshold may correspond to the processing chamber being insufficiently cleaned. In some embodiments, the thresholds may correspond to the processing chamber being over-cleaned. For example, a second threshold may correspond to a particle count (e.g., cleaning agent particles) below a certain value. In some embodiments, meeting the second threshold may correspond to the processing chamber being sufficiently cleaned, and not meeting the first threshold may correspond to the processing chamber being over-cleaned.

[0122]

[0126] 5 is a block diagram illustrating a computer system 500, according to certain embodiments. In some embodiments, computer system 500 is one or more of client device 120, prediction system 110, server machine 170, server machine 180, prediction server 112, and / or the like.

[0123]

[0127] In some embodiments, computer system 500 is connected to other computer systems (e.g., via a network such as a local area network (LAN), an intranet, an extranet, or the Internet). In some embodiments, computer system 500 operates as a server or a client computer in a client-server environment, or as a peer computer in a peer-to-peer or distributed network environment. In some embodiments, computer system 500 is provided by a personal computer (PC), a tablet PC, a set-top box (STB), a personal digital assistant (PDA), a mobile phone, a web appliance, a server, a network router, switch, or bridge, or any device capable of executing a set of instructions (sequential or otherwise) that specify operations to be performed by that device. Furthermore, the term "computer" is intended to include any collection of computers that individually or collectively execute a set (or sets) of instructions to perform any one or more of the methodologies described herein.

[0124]

[0128] In a further embodiment, the computer system 500 includes a processing device 502, a volatile memory 504 (e.g., random access memory (RAM)), a non-volatile memory 506 (e.g., read-only memory (ROM) or electrically erasable programmable ROM (EEPROM)), and a data storage device 518, which communicate with each other via a bus 508.

[0125]

[0129] In some embodiments, the processing device 502 is 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 instruction set types), or a special-purpose 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.).

[0126]

[0130] In some embodiments, computer system 500 further includes a network interface device 522 (e.g., connected to a network 574). In some embodiments, computer system 500 also includes a video display unit 510 (e.g., a liquid crystal display (LCD)), an alphanumeric input device 512 (e.g., a keyboard), a cursor control device 514 (e.g., a mouse), and a signal generating device 520.

[0127]

[0131] In some implementations, the data storage device 518 includes a non-transitory computer-readable storage medium 524 that stores instructions 526 encoding any one or more of the methods or functions described herein, including instructions encoding the components of FIG. 1 (e.g., the corrective action component 122, the prediction component 114, etc.) and instructions for performing the methods described herein (e.g., one or more of methods 400A-C).

[0128]

[0132] In some embodiments, the instructions 526 also reside, completely or partially, within the volatile memory 504 and / or within the processing device 502 during execution by the computer system 500; and thus, in some embodiments, the volatile memory 504 and the processing device 502 also constitute machine-readable storage media.

[0129]

[0133] Although the computer-readable storage medium 524 is shown as a single medium in the illustrated example, the term "computer-readable storage medium" is intended to include a single medium or multiple media (e.g., centralized or distributed databases and / or associated caches and servers) that store one or more executable sets of 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 execution by a computer that cause the computer to perform any one or more of the methods described herein. The term "computer-readable storage medium" is intended to include, but is not limited to, solid-state memory, optical media, and magnetic media.

[0130]

[0134] The methods, components, and features described herein may be implemented by discrete hardware components or may be integrated into the functionality of other hardware components, such as application specific integrated circuits (ASICS), FPGAs, DSPs, or similar devices. Additionally, the methods, components, and features may be implemented by firmware modules or functional circuits within a hardware device. Additionally, the methods, components, and features may be implemented in any combination of hardware devices and computer program components, or in a computer program.

[0131]

[0135] Unless otherwise specified, terms such as "receive," "identify," "execute," "provide," "obtain," "cause," "access," "determine," "add," "use," "train," and the like refer to operations and processes performed or implemented by a computer system that manipulate and transform data represented as physical (electronic) quantities in the computer system's registers and memory into other data similarly represented as physical quantities in the computer system's memory or registers or other such information storage, transmission, or display devices. Also, terms such as "first," "second," "third," "fourth," and the like, as used herein, are meant as symbols to distinguish between different elements and may not have a hierarchical meaning according to their numerical designations.

[0132]

[0136] The embodiments described herein also relate to apparatus for performing the methods described herein. The apparatus may be specially configured to perform the methods described herein, or may include a general-purpose computer system selectively programmed by a computer program stored on the computer system. Such a computer program may be stored on a computer-readable tangible storage medium.

[0133]

[0137] The methods and illustrative embodiments described herein are not inherently related to any particular computer or other apparatus. A wide variety of general-purpose systems can be used in accordance with the teachings described herein, or it may prove convenient to construct more specialized apparatus to perform the methods described herein and / or each of their individual functions, routines, subroutines, or steps. Examples of structures for a wide variety of these systems are set forth above.

[0134]

[0138] The above description is intended to be illustrative, not limiting. While the present disclosure has been described with reference to certain exemplary examples and embodiments, it will be recognized that the disclosure is not limited to the described examples and embodiments. The scope of the present disclosure should be determined with reference to the following claims, along with the full scope of equivalents to which such claims are entitled.

Claims

1. Identifying deposition thickness characteristic data relating to an amount of material deposited via one or more semiconductor processing steps of a process recipe executed in a processing chamber; determining cleaning process parameters based on the deposition thickness characteristic data and a variable cleaning time relationship of the process recipe; performing a cleaning process in the processing chamber based on the cleaning process parameters; A method comprising:

2. The method of claim 1 , wherein the deposition thickness characteristic data includes at least one of a material type or a thickness counter.

3. The method of claim 2 , further comprising resetting the thickness counter after the cleaning step is performed.

4. The method of claim 1 , wherein the cleaning process parameters include an amount of cleaning time.

5. the processing chamber includes a plurality of substrate processing regions; 2. The method of claim 1, wherein the determining the cleaning process parameters is based on the deposition thickness characteristic data of at least one of the plurality of substrate processing regions and the variable cleaning time relationship of the process recipe.

6. determining the cleaning process parameters providing the deposition thickness characteristic data as input to a trained machine learning model related to the variable cleaning time relationship; receiving an output from the trained machine learning model related to predicted data, wherein the cleaning process parameters are based on the predicted data; and The method of claim 1 , comprising:

7. 7. The method of claim 6, wherein the trained machine learning model is trained using data inputs including historical deposition thickness characteristic data and target outputs including historical performance data.

8. A non-transitory computer-readable storage medium storing instructions that, when executed, cause a processing device to: Identifying deposition thickness characteristic data relating to an amount of material deposited via one or more substrate processing steps of a process recipe executed in a processing chamber; determining cleaning process parameters based on the deposition thickness characteristic data and a variable cleaning time relationship of the process recipe; performing a cleaning process in the processing chamber based on the cleaning process parameters; A non-transitory computer-readable storage medium for causing a computer to perform steps including:

9. The non-transitory computer-readable storage medium of claim 8 , wherein the deposition thickness characteristic data includes at least one of a material type or a thickness counter.

10. The non-transitory computer-readable storage medium of claim 9 , wherein the process further comprises resetting the thickness counter after the cleaning process is performed.

11. The non-transitory computer-readable storage medium of claim 8 , wherein the cleaning process parameters include an amount of cleaning time.

12. the processing chamber includes a plurality of substrate processing regions; 10. The non-transitory computer-readable storage medium of claim 8, wherein the determining the cleaning process parameters is based on the deposition thickness characteristic data of at least one of the plurality of substrate processing regions and the variable cleaning time relationship of the process recipe.

13. determining the cleaning process parameters providing the deposition thickness characteristic data as input to a trained machine learning model related to the variable cleaning time relationship; receiving an output from the trained machine learning model related to predicted data, wherein the cleaning process parameters are based on the predicted data; and 9. The non-transitory computer-readable storage medium of claim 8, comprising:

14. 14. The non-transitory computer-readable storage medium of claim 13, wherein the trained machine learning model is trained using data inputs including historical deposition thickness characteristic data and target outputs including historical performance data.

15. Memory and a processing device coupled to the memory, the processing device comprising: Identifying deposition thickness characteristic data relating to an amount of material deposited via one or more substrate processing steps of a process recipe executed in a processing chamber; determining cleaning process parameters based on the deposition thickness characteristic data and a variable cleaning time relationship of the process recipe; performing a cleaning process in the processing chamber based on the cleaning process parameters; a processing device; A system comprising:

16. the deposition thickness characteristic data includes at least one of a material type or a thickness counter; The system of claim 15 , wherein the processing device further resets the thickness counter after the cleaning step is performed.

17. The system of claim 15 , wherein the cleaning process parameters include an amount of cleaning time.

18. the processing chamber includes a plurality of substrate processing regions; 16. The system of claim 15, wherein the processing device further determines the cleaning step parameters based on the deposition thickness characteristic data of at least one of the plurality of substrate processing regions and the variable cleaning time relationship of the process recipe.

19. the processing device providing the deposition thickness characteristic data as input to a trained machine learning model related to the variable cleaning time relationship; receiving an output from the trained machine learning model related to predicted data, wherein the cleaning process parameters are based on the predicted data; and 16. The system of claim 15, wherein the cleaning process parameters are determined by:

20. 20. The system of claim 19, wherein the trained machine learning model is trained using data inputs including historical deposition thickness characteristic data and target outputs including historical performance data.

Images