Residual thickness compensation

Abstract

The method includes identifying materials associated with a substrate processing step of a recipe. The method further includes determining an expected total residual thickness value after the substrate processing step. The method further includes determining an expected material thickness value for the materials associated with the substrate processing step based on the expected total residual thickness value. The method further includes updating the recipe based on the materials and the expected material thickness value for the materials to generate an updated recipe. The method further includes processing the substrate based on the updated recipe.

Description

Technical Field

[0001] The present disclosure relates to compensation, and more particularly, to residual thickness compensation during substrate manufacturing.

Background Art

[0002] Products can be manufactured by performing one or more manufacturing processes using manufacturing equipment. For example, it is possible to manufacture a substrate through a substrate processing step using a substrate processing device.

Summary of the Invention

[0003] The following is a simplified summary of the present disclosure to provide a basic understanding of some aspects of the present disclosure. This summary is not an exhaustive summary of the present disclosure. It is neither for identifying the main points or important elements of the present disclosure, nor for indicating any scope of specific embodiments of the disclosure or any scope of the claims. The sole purpose of this summary is to present some concepts of the present disclosure in a simplified form as an introduction to the more detailed description presented later.

[0004] One aspect of the present disclosure includes a method for identifying materials associated with a recipe's substrate processing step. The method further includes determining a value for the expected total residual thickness after the substrate processing step. The method further includes determining a value for the expected material thickness of the material associated with the substrate processing step based on the value of the expected total residual thickness. The method further includes updating the recipe based on the material and the value of the expected material thickness of the material to generate an updated recipe. The method further includes processing the substrate based on the updated recipe.

[0005] Further aspects of the present disclosure include a non-transient computer-readable storage medium containing instructions, which, when executed by a processing device operably connected to memory, perform a process. The process includes identifying a material associated with a substrate processing process of a recipe. The process further includes determining an expected total residual thickness value after the substrate processing process. The process further includes determining an expected material thickness value for the material associated with the substrate processing process based on the expected total residual thickness value. The process further includes updating the recipe based on the material and the expected material thickness value for said material to generate an updated recipe. The process further includes processing a substrate based on the updated recipe.

[0006] Other aspects of the present disclosure include a system comprising a memory and a processing device connected to the memory. The processing device identifies a material associated with a substrate processing step of a recipe. The processing device further determines the expected total residual thickness value after the substrate processing step. Based on the expected total residual thickness value, the processing device further determines the expected material thickness value of the material associated with the substrate processing step. The processing device further updates the recipe based on the material and the expected material thickness value of said material, and generates an updated recipe. The processing device further processes the substrate based on the updated recipe.

[0007] The figures in the attached drawings are provided as examples, not to limit, to this disclosure. [Brief explanation of the drawing]

[0008] [Figure 1] This is a block diagram illustrating an exemplary system structure according to a specific embodiment. [Figure 2] A dataset generator associated with residual thickness compensation, according to a specific embodiment, is shown. [Figure 3] This is a block diagram showing the determination of predictive data related to residual thickness compensation according to a specific embodiment. [Figure 4A]This is a flowchart of a method related to residual thickness compensation according to a specific embodiment. [Figure 4B] This is a flowchart of a method related to residual thickness compensation according to a specific embodiment. [Figure 4C] This is a flowchart of a method related to residual thickness compensation according to a specific embodiment. [Figure 5] This is a block diagram of a computer system according to a specific embodiment. [Modes for carrying out the invention]

[0009] This specification describes techniques for residual thickness compensation, such as adjusting film deposition parameters based on residual thickness during substrate manufacturing, scalable run-time software methods for compensating for deposition thickness drift based on chamber residual thickness, and chamber residual-based loop time adjustments.

[0010] A manufacturing apparatus can deposit films on the surface of a substrate according to a process recipe. The apparatus can deposit multiple layers of films on the substrate surface and perform etching processes to form patterns on the deposited films. For example, the apparatus can perform a chemical vapor deposition (CVD) process to deposit alternating layers on a substrate. The film may include one or more material layers formed during the deposition process, each layer may include a specific thickness gradient (e.g., a change in thickness along a certain layer of the deposited film). For example, a first layer (referred to as the proximal layer or proximal edge of the film) may be formed directly on the substrate surface and may have a first thickness. After the first layer is formed on the substrate surface, a second layer having a second thickness may be formed on the first layer. This process continues until the deposition process is complete and the final layer of the film (referred to as the distal layer or distal edge of the film) is formed.

[0011] The film may be subjected to, for example, an etching process to form a pattern on the surface of a substrate, a chemical-mechanical polishing (CMP) process to smooth the surface of the film, or other processes to manufacture a finished substrate. The etching process may involve applying a high-energy process gas (e.g., plasma) to the sample surface to decompose the surface material, which can then be removed by a vacuum system.

[0012] The processing chamber can perform each substrate manufacturing process (e.g., deposition, etching, polishing, etc.) according to a process recipe. A recipe for a particular process may define a specific set of steps performed for the substrate during that process and may include one or more settings associated with each step. For example, a recipe for a deposition process may include the temperature setting of the processing chamber, the pressure setting of the processing chamber, and the flow rate setting of the precursor for the material to be contained in the film deposited on the substrate surface. Thus, the thickness of each film layer can be correlated with these processing chamber settings.

[0013] A film can contain alternating layers of various materials. For example, a film can contain alternating layers of oxide and nitride (an oxide-nitride-oxide-nitride stack, i.e., an ONON (oxide-nitride-oxide-nitride) stack), or alternating layers of oxide and polysilicon (an oxide-polysilicon-oxide-polysilicon stack, i.e., an OPOP (oxide-polysilicon-oxide-polysilicon) stack). Each set of alternating layers can be called a loop. For example, a film may contain 40 loops (e.g., 40 sets of oxide-nitride layers), where the thickness of some loops may differ from the thickness of others. For example, a film stack may contain 40 oxide-nitride loops (e.g., 80 layers alternating between 40 oxide layers and 40 nitride layers), where the first loop of the film stack has an oxide layer of first thickness and a nitride layer of second thickness, the next nine loops of the film stack have an oxide layer of third thickness and a nitride layer of fourth thickness, and the last 30 loops of the film stack have an oxide layer of fifth thickness and a nitride layer of sixth thickness.

[0014] The film may also contain layers of different materials with variable (non-alternating) patterns (e.g., oxide-nitride-nitride-oxide stacks, i.e., ONNO (oxide-nitride-nitride-oxide), oxide-nitride-oxide-oxide stacks, i.e., ONOO (oxide-nitride-oxide-oxide), etc.). During this substrate manufacturing process, the thickness of each loop may vary (drift) due to intermittently changing deposition parameters and variations in processing chamber conditions (e.g., accumulation of contaminants, residual thickness on the processing chamber walls, erosion of specific components, etc.). Variations in layer thickness may cause the gas distribution plate to move closer to or further away from the substrate surface, thus affecting the plasma flow and / or temperature, which may lead to further deformation of the film.

[0015] To maintain the desired overall thickness of the film stack, some manufacturing systems compensate for these variations by manually increasing or decreasing the deposition time of subsequent loops. For example, if the thickness of the first loop is greater than required by the process recipe, the technician can manually shorten the deposition time of the second loop in the process recipe to produce a thinner loop as required by the process recipe. A processing chamber may have multiple substrate processing areas or slots. After the deposition process, deposition drift (partially caused, for example, by varying residual thicknesses on the walls of each substrate processing area) can vary for each individual substrate processing area (e.g., slot) within a single processing chamber. Compensating for the above variations between substrate processing areas can also generally be done by manually increasing or decreasing the deposition time of subsequent layers to maintain the desired overall thickness of the film stack. However, such processes are not scalable, are prone to errors, and are time-consuming. Such processes can also result in manufacturing delays, throughput losses, film defects, inconsistent and abnormal products, unscheduled user time or downtime, and defective products. Such processes also significantly increase the time required to perform optimization of process recipe parameters.

[0016] Aspects and embodiments of the present disclosure address the aforementioned and other shortcomings of the existing technology by performing residual thickness compensation, for example, by adjusting deposition parameters based on residual thickness during substrate manufacturing (for example, by compensating for deposition thickness drift based on chamber residual thickness).

[0017] The processing device identifies the material associated with the substrate processing step in the recipe. In some examples, the processing device determines that the substrate processing step is attempting to deposit a nitride onto the substrate. In some examples, the processing device determines that the substrate processing step is attempting to deposit an oxide onto the substrate. In some examples, the processing device determines that the substrate processing step is attempting to deposit a conductor (e.g., copper, tungsten, etc.) onto the substrate.

[0018] The processing device determines a value of the total residual thickness expected after a substrate processing step. The value of the total residual thickness expected can be the value of the total residual thickness expected on the substrate and / or on the walls of the processing chamber, depending on the substrate processing steps of the recipe until the end of the current substrate processing step.

[0019] The processing device determines a value of the expected material thickness of the material associated with the substrate processing step (e.g., of the current substrate processing step) based on the value of the total residual thickness expected. In some embodiments, the value of the expected material thickness is the difference between the value of the desired material thickness and the value of the actual material thickness. In some embodiments, to determine the value of the expected material thickness, the processing device provides the value of the total residual thickness expected as an input to a trained machine learning model. In some embodiments, to determine the value of the expected material thickness, the processing device receives an output associated with the prediction data from a trained machine learning model, and the value of the material thickness is associated with the prediction data. In some embodiments, the trained machine learning model is trained with a data input including past values of the total residual thickness and a target output of past values of the material thickness.

[0020] The processing device updates the recipe based on the material and the value of the expected material thickness of the material, and generates an updated recipe. In some embodiments, to update the recipe, the processing device determines an updated time value associated with the substrate processing step. In some embodiments, the processing device determines an updated time value associated with the substrate processing step based on the time value associated with the substrate processing step, the value of the total residual thickness expected, and the value of the expected material thickness. In some embodiments, the update of the recipe includes determining at least one of an updated radio frequency (RF) power of the substrate processing step, an updated interval value of the substrate processing step, an updated gas flow rate value of the substrate processing step, or an updated chamber pressure value of the substrate processing step.

[0021] The processing device processes the substrate based on the updated recipe.

[0022] Aspects of the present disclosure provide technical advantages. By aspects of the present disclosure, a time-consuming and error-prone process of manually calculating an “operation time offset” for each loop and entering the offset into a table is avoided. Aspects of the present disclosure are scalable. By aspects of the present disclosure, resulting manufacturing delays, throughput losses, and / or film defects are prevented. By aspects of the present disclosure, as a result, the time required to perform optimization of process recipe parameters is significantly reduced. Also by the present disclosure, diagnostic data is generated and corrective actions can be performed to avoid inconsistent and abnormal products, and unscheduled user time or downtime. By aspects of the present disclosure, deposition drift compensation based on the type of material is made possible.

[0023] FIG. 1 is a block diagram showing an exemplary system 100 (exemplary system structure) according to a particular embodiment. System 100 can perform the methods described herein (e.g., methods 400A-400C of FIGS. 4A-4C), e.g., via correction component 122 and / or prediction component 114. System 100 includes client device 120, manufacturing apparatus 124, sensor 126, measurement device 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.

[0024] In some embodiments, one or more of the client device 120, manufacturing equipment 124, sensor 126, measuring device 128, prediction server 112, data store 140, server machine 170, and / or server machine 180 are connected to each other via a network 130 to generate prediction data 160 for performing residual-based adjustments of film deposition parameters during substrate manufacturing. In some embodiments, the network 130 is a public network that provides the client device 120 with access to the prediction server 112, data store 140, and other publicly available computing devices. In some embodiments, the network 130 is a private network that provides the client device 120 with access to the manufacturing equipment 124, sensor 126, measuring device 128, data store 140, and other privately available computing devices. In some embodiments, the 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., LTE (Long Term Evolution) networks), routers, hubs, switches, server computers, cloud computing networks, and / or combinations thereof.

[0025] In some embodiments, the client device 120 includes computing devices such as personal computers (PCs), laptops, mobile phones, smartphones, tablet computers, and netbook computers. In some embodiments, the client device 120 includes a corrective action component 122. In some embodiments, the corrective action component 122 may also be included in the prediction system 110 (e.g., a machine learning processing system). In some embodiments, the corrective action component 122 is alternatively included in the prediction system 110 (e.g., instead of being included in the client device 120). The client device 120 includes an operating system that enables the user to perform one or more of the following: integrating, generating, viewing, editing data, and providing instructions to the prediction system 110 (e.g., a machine learning processing system).

[0026] In some embodiments, the corrective action component 122 receives one or more of the following: user input (e.g., via a graphical user interface (GUI) displayed by a client device 120), characteristic data 142, performance data 152, etc. In some embodiments, the characteristic data 142 may be the expected total residual thickness value, the expected material thickness value, etc. In some embodiments, the corrective action component 122 transmits the 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 a corrective action based on the prediction data 160, and has the corrective action executed. In some embodiments, the corrective action component 122 stores the data (e.g., user input, characteristic data 142, performance data 152, etc.) in a data store 140, and the prediction server 112 retrieves the data from the data store 140. In some embodiments, the prediction server 112 stores the output of the trained machine learning model 190 (e.g., prediction data 160) in the data store 140, and the client device 120 retrieves the output from the data store 140. In some embodiments, the corrective action component 122 receives instructions for corrective action (e.g., based on the prediction data 160) from the prediction system 110 and triggers the execution of the corrective action.

[0027] The manufacturing apparatus 124 is capable of manufacturing products such as substrates, wafers, semiconductors, and electronic devices by performing processes according to a recipe or over a certain period of time. The manufacturing apparatus 124 may include a processing chamber. The processing chamber may be adapted to perform any number of processes on a substrate. The same or different substrate processes may be performed in each processing chamber or each substrate processing area. Substrate processing processes may include atomic layer deposition (ALD), physical vapor deposition (PVD), or chemical vapor deposition (CVD), etching, annealing, curing, pre-cleaning, or removal of metal or metal oxides. Other processes may be performed on the substrate inside. The processing chamber may include one or more sensors configured to capture data on the substrate before, after, or during the substrate processing processes. For example, one or more sensors may be configured to acquire spectral and / or non-spectral data on a portion of the substrate during the substrate processing process. In other embodiments or similar embodiments, one or more sensors may be configured to acquire data associated with the environment inside the processing chamber before, after, or during the substrate processing process. For example, one or more sensors may be configured to acquire data associated with the temperature, pressure, gas concentration, etc., of the environment inside the processing chamber during the substrate processing process.

[0028] A processing chamber can be used for a process in which material is deposited onto a substrate. For example, the processing chamber can be a chamber for a deposition process, as previously described. In some embodiments, the processing chamber includes a chamber body and a showerhead that closes the internal space. The showerhead may include a showerhead base and a showerhead gas distribution plate. Alternatively, the showerhead can be replaced in some embodiments with a lid and nozzle, and in other embodiments with a plurality of pie-shaped showerhead sections and a plasma generating unit. The chamber body can be manufactured from aluminum, stainless steel, or other suitable material such as titanium (Ti). The chamber body generally includes side walls and a bottom. An exhaust port may be defined in the chamber body and the internal space may be connected to a pump system. The pump system may include one or more pumps and throttle valves, which are used to exhaust the internal space of the processing chamber and to regulate the pressure of the internal space.

[0029] The showerhead may be supported on the side wall of the chamber body. The showerhead (or lid) may be open to allow access to the internal space of the processing chamber and, when closed, can provide a seal for the processing chamber. A gas panel may be connected to the processing chamber to supply process gases and / or cleaning gases to the internal space via the showerhead, or lid and nozzles (e.g., through openings in the showerhead or lid and nozzles). For example, the gas panel can provide a precursor for the material of a film deposited on the surface of a substrate. In some embodiments, the precursor may include a silicon-based precursor or a boron-based precursor. The showerhead may include a gas distribution plate (GDP), which may have multiple gas supply holes (also referred to as channels) throughout the GDP. A substrate support assembly is positioned in the internal space of the processing chamber below the showerhead. The substrate support assembly holds the substrate during processing (e.g., during the deposition process), for example, using an electrostatic chuck.

[0030] In some embodiments, the processing chamber may include measuring devices (e.g., measuring device 128) and / or sensors (e.g., sensor 126) configured to generate in-situ measurements (e.g., measurement data) and / or sensor measurements (e.g., sensor data) during processes performed in the processing chamber. In some embodiments, the measurements and / or sensor measurements may be subsets of characteristic data 142 and / or performance data 152. The measuring devices and / or sensors may be operably connected to a system controller. In some embodiments, the measuring devices may be configured to generate measurements (e.g., thickness) of the film during a particular instance of the deposition process. In some embodiments, the sensors may be configured to generate sensor measurements (e.g., thickness) of the film during a particular instance of the deposition process. The system controller may generate a thickness profile for the film based on the measurements received from the measuring devices. The system controller may generate a thickness profile for the film based on sensor measurements received from the sensors. In other or similar embodiments, the processing chamber does not include measuring devices. In such embodiments, the system controller can receive one or more measurements of the film after the deposition process in the processing chamber is completed. The system controller can determine the deposition rate based on the one or more measurements, and can generate a thickness profile for the film based on the determined concentration gradient and the determined deposition rate of the deposition process.

[0031] The manufacturing apparatus 124 can perform processes on a substrate (e.g., a wafer) in a processing chamber. Examples of substrate processes include deposition processes that deposit one or more layers of film on the surface of the substrate, and etching processes that form patterns on the surface of the substrate. The manufacturing apparatus 124 can perform each process according to a process recipe. A process recipe defines a specific set of steps to be performed on the substrate during that process and may include one or more settings associated with each step. For example, a recipe for a deposition process may include setting the temperature of the processing chamber, setting the pressure of the processing chamber, and setting the flow rate of the precursor for the material to be contained in the film deposited on the substrate surface.

[0032] In some embodiments, the manufacturing apparatus 124 includes sensors 126 configured to generate data associated with the substrate being processed in the manufacturing system 100. For example, the processing chamber may include one or more sensors configured to generate a residual thickness profile (e.g., the thickness of the material on the walls of the processing chamber) associated with the processing chamber before, during, and / or after a process (e.g., a deposition process). For example, the processing chamber may include one or more sensors configured to generate spectral or non-spectral data associated with the substrate before, during, and / or after a process (e.g., a deposition process) is performed for the substrate. In some embodiments, the spectral data generated by sensors 126 may indicate the concentration of one or more materials deposited on the surface of the substrate. Sensors 126 configured to generate spectral data associated with the substrate may include reflectance sensors, ellipsometry sensors, thermal spectral sensors, capacitive sensors, etc. Sensors 126 configured to generate non-spectral data associated with the substrate may include residual thickness sensors, temperature sensors, pressure sensors, flow sensors, voltage sensors, etc.

[0033] The measuring device 128 can provide measurement data associated with the substrate processed by the manufacturing device 124. In some embodiments, the measurement data may be a subset of characteristic data 142 and / or performance data 152. The measurement data may include values ​​such as film characteristic data (e.g., wafer space film characteristics), dimensions (e.g., thickness, height, etc.), dielectric constant, dopant concentration, density, and defects. In some embodiments, the measurement data may further include values ​​of one or more surface profile characteristic data (e.g., etching rate, etching rate uniformity, critical dimensions of one or more features contained on the substrate surface, uniformity of critical dimensions across the substrate surface, edge placement error, etc.). The measurement data may be for a finished product or an unfinished product. The measurement data may differ from substrate to substrate. The measurement data may be generated using, for example, reflectivity measurement techniques, ellipsometry techniques, transmission electron microscopy (TEM) techniques, etc.

[0034] In some embodiments, the prediction server 112, server machine 170, and server machine 180 each include one or more computing devices such as a rack-mount server, router computer, server computer, personal computer, mainframe computer, laptop computer, tablet computer, desktop computer, GPU (Graphics Processing Unit), and accelerator application-specific integrated circuit (ASIC: for example, TPU (Tensor Processing Unit)).

[0035] The prediction server 112 includes a prediction component 114. In some embodiments, the prediction component 114 identifies characteristic data 142 (e.g., expected total residual thickness value, expected material thickness value, etc.) (e.g., received from client device 120 and retrieved from data store 140) and generates prediction data 160 associated with the execution of corrective actions (e.g., updating recipes, updating deposition process parameters, updating processing process parameters, etc.). In some embodiments, the prediction component 114 uses one or more trained machine learning models 190 to determine the prediction data 160. In some embodiments, the trained machine learning models 190 are trained using historical characteristic data 144 and historical performance data 154.

[0036] For example, deposition process parameters may include deposition time per layer and / or per loop of the processing recipe, temperature setting of the processing chamber, pressure setting of the processing chamber, flow rate setting of the precursor for the material contained in the film to be deposited on the substrate surface, showerhead height, etc. In some embodiments, updating the recipe includes updating the deposition process parameters. For example, deposition process parameters may include time value, updated time value, recipe, updated recipe, RF power for the substrate processing process, interval value for the substrate processing process, gas flow rate value for the substrate processing process, or chamber pressure value for the substrate processing process, updated RF power for the substrate processing process, updated interval value for the substrate processing process, updated gas flow rate value for the substrate processing process, updated chamber pressure value for the substrate processing process, etc.

[0037] In some embodiments, the prediction system 110 (e.g., prediction server 112, prediction component 114) generates prediction data 160 using supervised machine learning (e.g., supervised dataset, historical performance data 154, labeled historical characteristic data 144, etc.). In some embodiments, the prediction system 110 generates prediction data 160 using semi-supervised learning (e.g., semi-supervised dataset, performance data 152 are prediction percentages, etc.). In some embodiments, the prediction system 110 generates prediction data 160 using unsupervised machine learning (e.g., unsupervised dataset, clustering, clustering based on historical characteristic data 144, etc.).

[0038] In some embodiments, the manufacturing apparatus 124 (e.g., deposition chamber, cluster tool, wafer backgrinding system, wafer saw machine, die attach machine, wire bonder, die overcoat system, molding apparatus, hermetically sealed apparatus, metal can welding machine, DTFS (deflash / trim / form / singulation) machine, branding apparatus, and / or packaging apparatus) is part of a substrate processing system (e.g., integrated processing system). The manufacturing apparatus 124 includes one or more of the following: a controller, an enclosure system (e.g., a substrate carrier, a front-opening unified pod (FOUP), an auto-teaching FOUP, a process kit enclosure system, a substrate enclosure system, a cassette, etc.), an SSP (side storage pod), an aligner device (e.g., an aligner chamber), a factory interface (e.g., an EFEM (equipment front end module)), a load lock, a transfer chamber, one or more processing chambers, and / or a robotic arm (e.g., located within the transfer chamber, located within the front interface, etc.). The enclosure system, SSP, and load lock are mounted to the factory interface, and a robotic arm positioned within 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. An aligner device is positioned within the factory interface to align the contents. The load lock and processing chamber are mounted to the transfer chamber, and a robotic arm positioned within the transfer chamber transfers contents (e.g., substrates, process kit rings, carriers, verification wafers, etc.) between the load lock, processing chamber, and transfer chamber. In some embodiments, the manufacturing apparatus 124 includes components of a substrate processing system.In some embodiments, the characteristic data 142 of the processing chamber or substrate is obtained from subjecting the processing chamber or substrate to one or more processes (e.g., deposition, etching, heating, cooling, transfer, processing, fluidization, etc.) performed by the components of the manufacturing apparatus 124.

[0039] In some embodiments, the sensor 126 provides characteristic data 142 (e.g., sensor values ​​such as past and current sensor values), namely, characteristic data 142 of the processing chamber (e.g., expected total residual thickness), or characteristic data 142 of the substrate to be processed by the manufacturing apparatus 124 (e.g., expected material thickness).

[0040] In some embodiments, the sensor 126 includes one or more measuring tools, which may include, for example, an ellipsometer (used to determine the surface properties of a thin film by measuring material properties such as layer thickness, optical constants, surface roughness, composition, and optical anisotropy), an ion mill (used to prepare non-uniform bulk material when a large area of ​​material is uniformly thinned), a capacitance versus voltage (CV) system (used to measure the CV and capacitance versus time (Ct) properties of semiconductor devices), an interferometer (used to measure distance in terms of wavelength and to determine the wavelength of a particular light source), a light source measuring unit (SME), a magnetometer, an optical and imaging system, a surface shape measuring device, a wafer prober (used to test semiconductor wafers before separating them into individual dies or chips), an imaging station, and a critical-dimension scanning electron microscope (CD-SEM). These include microscopes (used to ensure the stability of the manufacturing process by measuring the critical dimensions of the substrate), reflectometers (used to measure reflectance and radiance from a surface), resistance probes (used to measure the resistivity of thin films), resistance 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 / or X-ray diffractometers (used to clearly determine the crystal structure, crystal orientation, film thickness, and residual stress of silicon wafers, epitaxial films, or other substrates).

[0041] In some embodiments, characteristic data 142 is used for the health of the apparatus and / or the health of the product (e.g., product quality). In some embodiments, characteristic data 142 is received over a period of time.

[0042] In some embodiments, the sensor 126 and / or measuring device 128 provides characteristic data 142, which includes one or more of the following: morphological data, size attribute data, dimensional attribute data, image data, scanning electron microscope (SEM) images, energy dispersive X-ray (EDX) images, defect distribution data, spatial position data, elemental analysis data, wafer signature data, chip layer, chip layout data, edge data, gradation data, signal-to-noise data, temperature data, interval data, current data, power data, and / or voltage data.

[0043] In some embodiments, the characteristic data includes morphological data (e.g., data relating to the morphology of the substrate, such as the thickness of the deposited layer or residual thickness). In some embodiments, the characteristic data 142 includes size attribute data (e.g., data representing the size of the substrate's attributes). In some embodiments, the characteristic data 142 includes dimensional attribute data (e.g., data representing the dimensions of the substrate's attributes). In some embodiments, the characteristic data 142 includes SEM images (e.g., images captured by a scanning electron microscope using a focused beam of electrons to scan the surface of the substrate and generate high-resolution images). In some embodiments, the characteristic data 142 includes EDX images (e.g., images generated from data collected using X-ray techniques to identify the elemental composition of the material). In some embodiments, the characteristic data 142 includes defect distribution data (e.g., data representing the distribution of defects on the substrate, such as spatial and temporal distribution). In some embodiments, the characteristic data 142 includes spatial location data (e.g., data representing the spatial location of substrate attributes, defects, elements, etc.). In some embodiments, the characteristic data 142 includes elemental analysis data (e.g., data representing the elemental composition of the substrate). In some embodiments, the characteristic data 142 includes wafer signature data (e.g., data representing the distribution of wafer defects on the substrate resulting from a single manufacturing problem). In some embodiments, the characteristic data 142 includes chip layer data (e.g., associated with layers or processes in the substrate manufacturing process). In some embodiments, the characteristic data 142 includes chip layout data (e.g., data representing the layout of the substrate in terms of planar geometric shape). In some embodiments, the characteristic data 142 includes edge data (data representing the edges of the wafer; e.g., chipped edges, wafer edge thickness, wafer warp and / or deflection). In some embodiments, the characteristic data 142 includes grayscale data (e.g., data representing the brightness of pixels in the image of the substrate) and signal-to-noise data (e.g., data representing the signal-to-noise ratio of substrate measurements by a spectroscopic measuring instrument).

[0044] In some embodiments, characteristic data 142 (e.g., historical characteristic data 144, current characteristic data 146, etc.) is processed (e.g., by a client device 120 and / or a prediction server 112). In some embodiments, processing of characteristic data 142 includes generating features. In some embodiments, features are patterns in characteristic data 142 (e.g., gradients, widths, heights, 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 a prediction component 114 to obtain prediction data 160.

[0045] In some embodiments, the measuring device 128 may be included as part of the manufacturing apparatus 124. For example, the measuring device 128 may be included inside or connected to the processing chamber and may be configured to generate measurement data (e.g., characteristic data 142, performance data 152, etc.) of the inside of the processing chamber or of the substrate before, during, and / or after a process (e.g., deposition process, etching process, etc.) while the substrate remains inside the processing chamber. In some examples, the measuring device 128 may be referred to as an in-situ measuring device. In other examples, the measuring device 128 may be connected to other stations of the manufacturing apparatus 124. For example, the weighing device may be connected to a transfer chamber, load lock, or factory interface.

[0046] In some embodiments, the sensor 126 may be included as part of the manufacturing apparatus 124. For example, the sensor 126 may be contained within or connected to the processing chamber and may be configured to generate sensor data of the inside of the processing chamber or the substrate before, during, and / or after a process (e.g., a deposition process, an etching process) while the substrate remains in the processing chamber. In some cases, the sensor 126 may be referred to as an in-situ sensor. In other examples, the sensor 126 may be connected to other stations of the manufacturing apparatus 124. For example, the sensor may be connected to a transfer chamber, a load lock, or a factory interface.

[0047] In some embodiments, the measuring device 128 (e.g., ellipsometry device, imaging device, spectrometer, etc.) is used to determine measurement data (e.g., inspection data, image data, spectroscopic data, ellipsometry data, material composition data, optical data, or structural data, etc.) corresponding to the inside of the processing chamber (e.g., the surface) or the substrate manufactured by the manufacturing device 124 (e.g., substrate processing device). In some examples, after the manufacturing device 124 has processed the substrate, the measuring device 128 is used to inspect a portion of the substrate (e.g., a layer) and / or the inside of the processing chamber. In some embodiments, the measuring device 128 performs scanning acoustic microscopy (SAM), ultrasound, X-ray inspection, and / or computed tomography (CT) inspection. In some examples, after the manufacturing device 124 has deposited one or more layers on the substrate, the measuring device 128 is used to determine the quality of the processed substrate (e.g., layer thickness, layer uniformity, and / or interlayer spacing, etc.). In some embodiments, the measuring device 128 includes an imaging device (e.g., a SAM device, an ultrasound device, an X-ray device, and / or a CT device). In some embodiments, the characteristic data 142 includes sensor data from the sensor 126 and / or measurement data from the measuring device 128. In some embodiments, the characteristic data 142 includes sensor data from the sensor 126 and / or measurement data from the measuring device 128, which are located in situ (inside the processing chamber). In some embodiments, the performance data 152 includes user input via the client device 120 and / or measurement data from the measuring device 128. The characteristic data 142 may include measurement data from a first subset of the measuring device 128, and the performance data 152 may include measurement data from a second subset of the measuring device 128.

[0048] In some embodiments, performance data 152 may be associated with the performance of a recipe (e.g., a deposition recipe, an updated recipe, etc.). For example, performance data 152 may be for the recipe and / or for the substrate or processing chamber used in the processing steps of that recipe.

[0049] In some embodiments, characteristic data 142 may be derived from measurement data and / or sensor data. Measurement data may be data describing measurements of the substrate. Sensor data may be data representing the internal state and characteristics of the processing chamber. In some embodiments, characteristic data may include a value for the deposition thickness (e.g., the actual or expected amount of material deposited on the substrate). In some embodiments, characteristic data may include a value for the total residual thickness (e.g., the actual or expected amount of material remaining deposited on the chamber walls). In some embodiments, the value for the deposition thickness is derived from the deposition process recipe (e.g., the deposition thickness is equal to the expected deposition thickness of the deposition process).

[0050] In some embodiments, the actual deposition thickness value or the actual residual thickness value may refer to the amount of material actually deposited on the substrate after the deposition process, or the amount of material remaining deposited on the processing chamber wall. The actual deposition thickness value or the actual total residual thickness value can be measured using a measuring device or sensor.

[0051] In some embodiments, the expected deposition thickness value or expected residual thickness value may refer to the amount of material expected to be deposited on the substrate or remain deposited on the processing chamber wall after the deposition process. In some embodiments, the expected deposition thickness value or the actual total residual thickness value may be derived from the process recipe (e.g., deposition process parameters). In some embodiments, the expected deposition thickness value or the actual residual thickness value may be derived from past actual thickness values ​​(e.g., on the substrate and / or on the processing chamber wall) corresponding to the same deposition process.

[0052] In some embodiments, the datastore 140 is memory (e.g., random access memory), drives (e.g., hard drives, flash drives), a database system, or another type of component or device capable of storing data. In some embodiments, the datastore 140 includes multiple storage components (e.g., multiple drives or multiple databases) spanning multiple computing devices (e.g., multiple server computers). In some embodiments, the datastore 140 stores one or more of the characteristic data 142, performance data 152, and / or prediction data 160.

[0053] The characteristic data 142 may include the expected total residual thickness value, the expected material thickness value, the actual total residual thickness value, the actual material thickness value, the desired total residual thickness value, and the desired material thickness value. The performance data 152 may include the expected total residual thickness value, the expected material thickness value, the actual total residual thickness value, the actual material thickness value, the desired total residual thickness value, and the desired material thickness value.

[0054] In some embodiments, the data store 140 may store expected total residual thickness values ​​and expected material thickness values. The expected total residual thickness value may include one or more data points associated with the expected residual film profile that is expected to be produced by a particular process recipe. In some embodiments, the expected total residual thickness value may include the desired thickness of the film, the desired thickness of one or more layers of the film, and / or the desired thickness of one or more loops of the film. The expected material thickness value may include one or more data points associated with the current film thickness produced by the manufacturing apparatus 124. For example, the expected material thickness value may include the expected thickness of the film, the expected thickness of one or more layers of the film, and / or the expected thickness of one or more loops of the film. For example, the expected material thickness value may include the measured thickness of the film, the measured thickness of one or more layers of the film, and / or the measured thickness of one or more loops of the film. The expected material thickness value may be measured using the measuring device 128. The updated recipe may include one or more adjustments or offsets applied to the processing chamber parameters or process recipe. For example, an updated recipe may include adjustments to the deposition time for film layers and / or loops, the temperature setting of the processing chamber, the pressure setting of the processing chamber, the precursor flow rate setting for the material contained in the film to be deposited on the substrate surface, the power supplied to the processing chamber, and the ratio of two or more settings. An updated recipe may be generated by comparing the expected total residual thickness (e.g., the residual thickness expected to be produced by the process recipe) and determining the adjustments to be applied to the process recipe parameters to achieve the expected material thickness using algorithms, libraries of known defect patterns, etc. The updated recipe may be applied to steps associated with the deposition process, etching process, etc.

[0055] In some embodiments, the data store 140 may be configured to store data associated with known failure patterns. A failure pattern may be one or more values ​​(e.g., vectors, scalars, etc.) associated with one or more problems or failures related to the processing chamber subsystem. In some embodiments, a failure pattern may be associated with a corrective action. For example, a failure pattern may include a parameter adjustment step to correct the problem or failure indicated by the failure pattern. For example, a prediction system can compare a determined failure pattern with a library of known failure patterns to determine the type of failure that occurred in the subsystem, the cause of the failure, recommended corrective actions to correct the failure, and so on.

[0056] In some embodiments, corrective actions may include, for example, updating a recipe (e.g., process recipe, deposition recipe), determining expected material thickness values, processing a substrate based on the updated recipe, training a machine learning model using data inputs including historical residual thickness values ​​and target outputs including historical performance data, and / or receiving outputs associated with prediction data using the trained machine learning model, wherein expected material thickness values ​​are associated with the prediction data. In some embodiments, updating a process recipe may include updating process parameters (e.g., deposition time, flow rate, temperature, etc.). In some embodiments, corrective actions include providing machine learning (e.g., triggering recipe updates based on prediction data, process / process parameter updates, etc.).

[0057] In some embodiments, the predicted data 160 is associated with corrective actions. In some embodiments, the corrective actions are associated with updating a recipe (e.g., process recipe, deposition recipe), determining a predicted material thickness value, processing a substrate based on the updated recipe, training a machine learning model using data inputs including historical residual thickness values ​​and target outputs including historical performance data, using the trained machine learning model to receive outputs associated with the predicted data, repairing one or more parts of the manufacturing equipment 124, replacing one or more parts of the manufacturing equipment 124, computational process control (CPC), statistical process control (SPC) (e.g., SPC for comparison with a 3-sigma graph), advanced process control (APC), model-based process control, preventive operation and maintenance, design optimization, updating manufacturing parameters, modifying wafer recipes, feedback control, and / or modifying machine learning.

[0058] In some embodiments, the data store 140 may be configured to store data that is inaccessible to users of the manufacturing system. For example, process data, spectral data, and context data obtained about a substrate being processed in the manufacturing system are inaccessible to users of the manufacturing system (e.g., operators). In some embodiments, all data stored in the data store 140 may be inaccessible to users of the manufacturing system. In some embodiments, one portion of the data stored in the data store 140 may be inaccessible to users, while other portions of the data stored in the data store 140 may be accessible to users. In some embodiments, one or more portions of the data stored in the data store 140 may be encrypted using an encryption mechanism unknown to the user (e.g., the data is encrypted using a private encryption key). In some embodiments, the data store 140 may include multiple data stores, where data inaccessible to users is stored in one or more first data stores, and data accessible to users is stored in one or more second data stores.

[0059] Performance data 142 includes historical characteristic data 144 and current characteristic data 146. In some embodiments, characteristic data 142 (e.g., sensor data) may include expected total residual thickness values, expected material thickness values, updated RF power for the substrate processing process, updated interval values ​​for the substrate processing process, updated gas flow rate values ​​for the substrate processing process, updated chamber pressure values ​​for the substrate processing process, actual deposition residual thickness data, pressure data, temperature data, temperature range, power data, comparison parameters for comparing inspection data and threshold data, threshold data, cooling rate data, and / or cooling rate range. In some embodiments, at least a portion of the characteristic data 142 is from the sensor 126 and / or measuring device 128.

[0060] Performance data 152 includes historical performance data 154 and current performance data 156. Performance data 152 may indicate whether the substrate is properly designed, properly manufactured, uniform with other substrates, and / or functions properly. Performance data 152 may indicate whether the substrate processing process was performed correctly. For example, performance data 152 may indicate the actual thickness deposited on the wafer or in the processing chamber during the deposition process (e.g., material thickness value, total residual thickness value, historical material thickness value, deposition thickness on the walls of the processing chamber, etc.). Performance data 152 may indicate whether the substrate processing process (e.g., deposition process) was performed effectively. For example, performance data 152 may indicate deposition drift before, during, or after the deposition process, and may indicate the deposition residual thickness value, material thickness value, etc.

[0061] In some embodiments, at least a portion of the performance data 152 is associated with the quality of the products manufactured by the manufacturing apparatus 124. In some embodiments, at least a portion of the performance data 152 is based on measurement data from a measuring device 128 (e.g., past performance data 154 includes measurement data indicating a properly processed substrate, substrate characteristic data, yield, material thickness values, etc.) or measurement data from a sensor 126 (e.g., past performance data 154 includes sensor data indicating a properly processed substrate, substrate characteristic data, yield, material thickness values, etc.). In some embodiments, at least a portion of the performance data 152 is based on inspections inside the substrate or processing chamber (e.g., current performance data 156 based on actual inspections). In some embodiments, the performance data 152 includes user input (e.g., via a client device 120) indicating the quality or deposition drift of the substrate within the processing chamber / substrate processing area or on the substrate. In some embodiments, the performance data 152 includes the display of absolute values ​​(e.g., substrate inspection data is below the threshold data by a calculated value, and drift values ​​are below the threshold drift value by a calculated value) or relative values ​​(e.g., film deposition inspection data is below the threshold data by 5%, and drift values ​​are below the threshold drift value by 5%). In some embodiments, the performance data 152 indicates the satisfaction of threshold error amounts (e.g., at least 5% error in deposition drift after the deposition process, at least 5% error in manufacturing, at least 5% error in flow, at least 5% error in deformation, specification limits).

[0062] In some embodiments, historical data includes one or more historical characteristic data 144 and / or historical performance data 154 (e.g., at least a portion for training the machine learning model 190). Current data includes one or more current characteristic data 146 and / or current performance data 156 (e.g., at least a portion that is input to the machine learning model 190 after it has been trained using the historical data). In some embodiments, current data is used to retrain the trained machine learning model 190.

[0063] In some embodiments, the predictive data 160 is used to trigger the execution of corrective actions on process recipes, recipe / process deposition process parameters, manufacturing equipment, substrate processing systems, or components of substrate processing equipment.

[0064] Performing multiple types of measurements on multiple layers of a product or processing chambers to determine whether to implement corrective actions is costly in terms of time used, measuring devices 128 used, energy consumed, bandwidth used to transmit measurement data, and processor overhead for processing the measurement data. By providing characteristic data 142 to model 190 and receiving predictive data 160 from model 190, system 100 avoids the costly process of using measuring devices 128 on multiple layers of a product and / or sensors on processing chambers, thus having the technical advantage of avoiding wasted time and substrate waste.

[0065] Performing a manufacturing process (e.g., deposition) using manufacturing equipment 124 and / or manufacturing parameters (e.g., deposition process parameters) that result in defective products or damage to the manufacturing equipment is costly in terms of time, energy, products, manufacturing equipment 124, and cost, as it requires identifying corrective actions to prevent the occurrence of defective products. By providing characteristic data 142 to model 190, receiving predictive data 160 from model 190, and triggering corrective actions (e.g., recipe updates) based on the predictive data 160, system 100 has the technical advantage of avoiding the costs of manufacturing, identifying, and discarding defective substrates.

[0066] In some embodiments, the prediction system 110 further includes server machines 170 and 180. Server machine 170 includes a dataset generator 172 that can generate datasets (e.g., a set of data inputs and a set of target outputs) for training, validating, and / or testing a machine learning model 190. The dataset generator 172 has the functions of collecting, compiling, reducing, and / or partitioning the data to make it suitable for machine learning. In some embodiments (e.g., for small datasets), partitioning for post-training validation (e.g., explicit partitioning) is not used. During training, repeated cross-validation (e.g., 5-fold cross-validation, leave-one-out cross-validation) can be used, and during training, a given dataset is substantially repeatedly divided into various training and validation sets. A model (e.g., the best model, the model with the highest accuracy, etc.) is automatically selected from the model vector against a separated combination subset. In some embodiments, the dataset generator 172 explicitly divides 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). Several steps of the dataset generator 172 are described below in detail with respect to Figure 2 according to several embodiments. In some embodiments, the prediction system 110 generates multiple sets of features (e.g., training features) (e.g., via a prediction component 114).In some examples, the features of the first set correspond to characteristic data of the first set type (e.g., from sensors of the first set) (a first combination of values ​​from sensors of the first set, a first pattern in the values ​​from sensors of the first set), and this characteristic data corresponds to each of the above datasets (e.g., training set, validation set, and test set), and the features of the second set correspond to characteristic data of the second set type (e.g., from sensors of a second set different from sensors of the first set) (a second combination of values ​​different from the first combination, a second pattern different from the first pattern), and this characteristic data corresponds to each of the above datasets.

[0067] The 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, the engines (e.g., training engine 182, validation engine 184, selection engine 185, and test engine 186) refer to hardware (e.g., circuits, dedicated logic units, programmable logic units, microcode, processing devices, etc.), software (e.g., processing units, general-purpose computer systems, or instructions executed on dedicated machines), firmware, microcode, or a combination thereof. The training engine 182 can train a machine learning model 190 using one or more sets of features associated with a training set from a dataset generator 172. In some embodiments, the training engine 182 generates multiple trained machine learning models 190, where each trained machine learning model 190 corresponds to a separate set of parameters from the training set (e.g., characteristic data 142) and a corresponding response (e.g., performance data 152). In some embodiments, multiple models are trained with the same parameters on different objectives to model multiple effects. In some examples, a first trained machine learning model is trained using characteristic data 142 from all 126 sensors (e.g., sensors 1-5), a second trained machine learning model is trained using a first subset of characteristic data (e.g., from sensors 1, 2, and 4), and a third trained machine learning model is trained using a second subset of characteristic data that partially overlaps with the first subset of features (e.g., from sensors 1, 3, 4, and 5).

[0068] The validation engine 184 can validate the trained machine learning models 190 using the features of the corresponding sets of validation sets from the dataset generator 172. For example, a first trained machine learning model 190 trained using a first set of features from the training set is validated using a first set of features from the validation set. The validation engine 184 determines the accuracy of each trained machine learning model 190 based on the corresponding sets of features from the validation set. The validation engine 184 evaluates and flags trained machine learning models 190 whose accuracy does not meet a threshold accuracy (e.g., should be discarded). In some embodiments, the selection engine 185 can select one or more trained machine learning models 190 whose accuracy meets a threshold accuracy. In some embodiments, the selection engine 185 can select the trained machine learning model 190 with the highest accuracy among the trained machine learning models 190.

[0069] The test engine 186 can test the trained machine learning models 190 using the corresponding set of features from the test set generated by the dataset generator 172. For example, a first trained machine learning model 190 trained using a first set of features from the training set is tested using a first set of features from the test set. Based on the test set, the test engine 186 determines which of all trained machine learning models 190 has the highest accuracy.

[0070] In some embodiments, the machine learning model 190 (for example, used for classification) refers to a model artifact (e.g., correctly classifying a condition or ordinal level for each training input) generated by the training engine 182 using a training set that includes data inputs and corresponding target outputs. Patterns in the dataset can be found that map data inputs to target outputs (correct classifications or levels), and this mapping is provided to the machine learning model 190 to capture this pattern. In some embodiments, the machine learning model 190 uses one or more of the following: Gaussian Process Regression (GPR), Gaussian Process Classification (GPC), Bayesian Neural Network, Neural Network Gaussian Process, Deep Belief Network, Gaussian Mixture Model, or other probabilistic learning methods. Non-probabilistic methods, including one or more of the following, may also be used: support vector machines (SVMs), radial basis functions (RBFs), clustering, k-nearest neighbor algorithms (k-NNs), linear regression, random forests, and neural networks (e.g., artificial neural networks). In some embodiments, the machine learning model 190 is a multi-variate analysis (MVA) regression model.

[0071] The prediction component 114 provides the current characteristic data 146 (e.g., as input) to the trained machine learning model 190 and runs the trained machine learning model 190 (e.g., on the input to obtain one or more outputs). The prediction component 114 can determine (e.g., extract) prediction data 160 from the trained machine learning model 190 and determine (e.g., extract) uncertainty data indicating the level of confidence that the prediction data 160 corresponds to the current performance data 156. In some embodiments, the prediction component 114 or the corrective action component 122 uses uncertainty data (e.g., an uncertainty function, or an acquisition function derived from such uncertainty function) to determine whether to use the prediction data 160 to perform a corrective action or to further train the model 190.

[0072] For illustrative purposes only, and not limiting, aspects of this disclosure describe training one or more machine learning models 190 using historical data (i.e., previous 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 predictive data 160. In other embodiments, a heuristic model or rule-based model is used to determine predictive data 160 (e.g., without using a trained machine learning model). In other embodiments, a non-probabilistic machine learning model may be used. The predictive component 114 monitors the historical characteristic data 144 and historical performance data 154. In some embodiments, any of the information described with respect to the data input 210 in Figure 2 is monitored or otherwise used by a heuristic model or rule-based model.

[0073] In some embodiments, the functions of client device 120, prediction server 112, server machine 170, and server machine 180 are provided by fewer machines. For example, in some embodiments, server machines 170 and 180 are integrated into a single machine, while in some other embodiments, server machine 170, server machine 180, and prediction server 112 are integrated into a single machine. In some embodiments, client device 120 and prediction server 112 are integrated into a single machine.

[0074] In general, the functions described in one embodiment as being performed by the client device 120, the prediction server 112, the server machine 170, and the server machine 180 can also be performed on the prediction server 112 in other embodiments, where appropriate. Furthermore, functions belonging to a particular component may be performed by various or multiple components working together. For example, in some embodiments, the prediction server 112 determines corrective actions based on prediction data 160. In other examples, the client device 120 determines the prediction data 160 based on data received from a trained machine learning model.

[0075] Furthermore, the functionality of a particular component may be performed by the combined action of various or multiple components. In some embodiments, one or more of the prediction server 112, server machine 170, or server machine 180 are accessed as services provided to other systems or devices via an appropriate application programming interface (API).

[0076] In some embodiments, “User” is presented as a single individual. However, other embodiments of this disclosure include the case where “User” is an entity controlled by multiple users and / or automated sources. In some examples, a collection of individual users linked together as a group of administrators is considered “User.”

[0077] While embodiments of this disclosure describe determining predictive data 160 for residual thickness compensation during substrate manufacturing (e.g., updating recipes based on thickness values) during substrate processing within a manufacturing facility (e.g., a substrate processing facility), in some embodiments, this disclosure is generally applicable to corrective actions within a manufacturing facility. Embodiments can generally be applied to determining component quality based on various types of data.

[0078] Figure 2 shows a dataset generator 272 (e.g., dataset generator 172 in Figure 1) for generating a dataset for a machine learning model (e.g., model 190 in Figure 1) (associated with, for example, residual thickness compensation, methods 400A-400C, etc.) according to a particular embodiment. In some embodiments, the dataset generator 272 is part of the server machine 170 in Figure 1. The dataset generated by the dataset generator 272 in Figure 2 can be used to train a machine learning model (e.g., see Figure 4B) that triggers the execution of a corrective action (e.g., see Figure 4C).

[0079] The dataset generator 272 (e.g., the dataset generator 172 in Figure 1) generates a dataset for a machine learning model (e.g., the model 190 in Figure 1). The dataset generator 272 generates the dataset using historical characteristic data 244 (e.g., historical characteristic data 144 in Figure 1) and historical performance data 254 (e.g., historical performance data 154 in Figure 1). The system 200 in Figure 2 shows the dataset generator 272, data input 210, and target output 220.

[0080] In some embodiments, the dataset generator 272 generates a dataset (e.g., training set, validation set, test set) containing one or more data inputs 210 (e.g., training input, validation input, test input). In some embodiments, the dataset generator 272 does not generate target outputs (e.g., for unsupervised learning). In some embodiments, the dataset generator generates one or more target outputs 220 corresponding to the data inputs 210 (e.g., for supervised learning). The dataset also includes 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 a training engine 182, a validation engine 184, or a test engine 186, where the dataset is used to train, validate, or test a machine learning model 190 (e.g., associated with tuning film deposition parameters based on residual thickness during substrate manufacturing, methods 400A-C, etc.).

[0081] In some embodiments, the dataset generator 272 generates a data input 210 and a target output 220. In some embodiments, the data input 210 includes one or more sets of historical characteristic data 244 (e.g., total residual thickness values, material thickness values, etc.) (e.g., associated with adjustments of film deposition parameters based on residual thickness during substrate manufacturing, methods 400A to 400C, etc.). In some embodiments, the historical characteristic data 244 includes one or more of the following: characteristic data from one or more sensors and / or measuring devices, combinations of characteristic data from one or more sensors and / or measuring devices, and / or patterns from characteristic data from one or more sensors and / or measuring devices.

[0082] 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 (e.g., associated with adjusting film deposition parameters based on residual thickness during substrate manufacturing, methods 400A to 400C, etc.), 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 adjusting film deposition parameters based on residual thickness during substrate manufacturing, methods 400A to 400C, etc.).

[0083] In some embodiments, the dataset generator 272 discretizes (e.g., segments) one or more of the data inputs 210 or target outputs 220 (e.g., for use in a classification algorithm for a regression problem). Discretization of the data inputs 210 or target outputs 220 (e.g., segmentation via a sliding window) converts continuous values ​​of a variable into discrete values. In some embodiments, the discrete values ​​of the data inputs 210 represent discrete historical characteristic data 144 for obtaining the target output 220 (e.g., discrete historical performance data 154).

[0084] The data inputs 210 and target outputs 220 for training, validating, or testing a machine learning model include information about a specific piece of equipment (e.g., a specific substrate manufacturing piece of equipment). In some examples, the historical characteristic data 244 and historical performance data 254 are for the same manufacturing piece of equipment (e.g., associated with adjustments to film deposition parameters based on residual thickness during substrate manufacturing, methods 400A-400C, etc.).

[0085] In some embodiments, the information used to train the machine learning model is from a specific type of manufacturing equipment 124 of manufacturing equipment having specific characteristics (e.g., associated with the adjustment of film deposition parameters based on residual thickness during substrate manufacturing, methods 400A-400C, etc.), enabling the trained machine learning model to determine outcomes for a specific group of manufacturing equipment 124 based on inputs of current parameters (e.g., current characteristic data 146) associated with one or more components that share the characteristics of the specific group. In some embodiments, the information used to train the machine learning model is for components from two or more manufacturing equipment, enabling the trained machine learning model to determine outcomes for components based on inputs from one manufacturing equipment.

[0086] In some embodiments, a dataset is generated, and after training, validating, or testing the machine learning model 190 using the dataset, the machine learning model 190 is further trained, validated, or tested (e.g., current performance data 156 in Figure 1), or adjusted (e.g., weights associated with the input data of the machine learning model 190, such as connection weights in the neural network).

[0087] A machine learning model processes inputs and generates outputs (e.g., tuning film deposition parameters based on residual thickness during substrate manufacturing, associated with methods 400A-400C, etc.). An artificial neural network includes an input layer consisting of values ​​within data points. The next layer is called a 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 takes the input values ​​as inputs, turns them into a multivariate function (e.g., a nonlinear mathematical transformation), and generates output values. 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, each node applies weights to those values, and then generates its own output values. This can happen in 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.

[0088] Therefore, the input may include one or more predictions or estimates (e.g., adjustments to film deposition parameters based on residual thickness during substrate manufacturing, associated with methods 400A-400C, etc.). For example, the output prediction or estimate may include one or more predictions such as deposition drift, film deposition on chamber components, erosion of chamber components, predicted failure of chamber components, and predicted failures of the deposition process. The processing logic unit determines an error (i.e., classification error) based on the difference between the output of the machine learning model (e.g., prediction or estimate) and the target label associated with the input training data. The processing logic unit adjusts the weights of one or more nodes in the machine learning model based on the above error. An error term or delta may be determined for each node in the artificial neural network. Based on the above error, the artificial neural network adjusts one or more of its own parameters (weights for one or more inputs of a given node) of one or more of its own nodes. Parameters may be updated in a backpropagation manner, such that the top layer nodes are updated first, followed by the nodes of the next layer, and so on. An artificial neural network contains multiple layers of "neurons," each layer receiving values ​​as input from the neurons in the previous layer. Parameters for each neuron include weights associated with the values ​​received from each neuron in the previous layer. Therefore, tuning parameters may involve adjusting the weights assigned to each input for one or more neurons in one or more layers of the artificial neural network.

[0089] After one or more training rounds, the processing logic unit can determine if the stopping criteria have been met. The stopping criteria can be a target level of accuracy, a target number of processed images from the training dataset, a target change in parameters relative to one or more previous data points, a combination of these, and / or other criteria. In some embodiments, the stopping criteria are 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 can be, for example, 70%, 80%, or 90%. In some embodiments, the stopping criteria have been met when the accuracy of the machine learning model no longer improves. If the stopping criteria have not been met, further training is performed. If the stopping criteria have been met, training may be completed. Once the machine learning model is trained, a reserved portion of the training dataset is used to test the model.

[0090] Figure 3 is a block diagram showing a system 300 for generating predictive data 360 (e.g., predictive data 160 in Figure 1) according to a particular embodiment. The system 300 is used to determine the predictive data 360 via a trained machine learning model (e.g., model 190 in Figure 1) (associated with, for example, residual thickness compensation, methods 400A to 400C, etc.).

[0091] In block 310, system 300 (e.g., prediction system 110 in Figure 1) performs data partitioning of historical data (e.g., historical characteristic data 344 and historical performance data 354 of model 190 in Figure 1) (e.g., via the dataset generator 172 of server machine 170 in Figure 1) to generate training set 302, validation set 304, and test set 306 (e.g., associated with adjustment of film deposition parameters based on residual thickness during substrate manufacturing, methods 400A-400C, etc.). In some examples, the training set represents 60% of the historical data, the validation set represents 20% of the historical data, and the test set represents 20% of the historical data. System 300 generates multiple sets of features for each of the training set, validation set, and test set. In some examples, if the historical data includes features derived from 20 sensors (e.g., sensor 126 in Figure 1, sensors and / or measuring devices of the manufacturing equipment) and 100 products (e.g., products corresponding to characteristic data from the 20 sensors), then the first set of features is sensors 1-10, the second set of features is sensors 11-20, the training set is products 1-60, the validation set is products 61-80, and the test set is products 81-100. In this example, the first set of features in the training set would be the parameters from sensors 1-10 for products 1-60.

[0092] In block 312, system 300 uses training set 302 to train a model via training engine 182 in Figure 1 (associated with, for example, adjustment of film deposition parameters based on residual thickness during substrate manufacturing, methods 400A-400C, etc.). In some embodiments, system 300 trains multiple models using multiple sets of features from training set 302 (e.g., a first set of features from training set 302, a second set of features from training set 302, etc.). For example, system 300 trains a machine learning model to generate a first trained machine learning model using a first set of features in the training set (e.g., characteristic data from sensors 1-10 for products 1-60), and a second trained machine learning model using a second set of features in the training set (e.g., characteristic data from sensors 11-20 for products 1-60). In some embodiments, a first trained machine learning model and a second trained machine learning model are combined to generate a third trained machine learning model (for example, in some embodiments, the third trained machine learning model itself is a better predictor than the first or second trained machine learning model). In some embodiments, the sets of features used when comparing models overlap (for example, the first set of features is characteristic data from sensors 1-15, and the second set of features is characteristic data from sensors 5-20). In some embodiments, hundreds of models are generated, including models with various feature swaps and combinations of models.

[0093] In block 314, system 300 performs model validation (e.g., via validation engine 184 in Figure 1) using validation set 304. System 300 validates each of the trained models (e.g., associated with adjustments to film deposition parameters based on residual thickness during substrate manufacturing, methods 400A-400C, etc.) using the corresponding sets of features in validation set 304. For example, system 300 validates a first trained machine learning model using a first set of features in the validation set (e.g., parameters from sensors 1-10 for products 61-80) and generates a second trained machine learning model using a second set of features in the validation set (e.g., parameters from sensors 11-20 for products 61-80). In some embodiments, system 300 validates hundreds of models generated in block 312 (e.g., models with various feature swaps, combinations of models, etc.). In block 314, system 300 determines the accuracy of one or more trained models (e.g., through model validation) and determines whether one or more of the trained models have accuracy that meets the threshold accuracy. If it is determined that none of the trained models have accuracy that meets the threshold accuracy, the flow returns to block 312, where system 300 performs model training using different feature sets of the training set. If it is determined that one or more of the trained models have accuracy that meets the threshold accuracy, the flow proceeds to block 316. System 300 discards trained machine learning models whose accuracy falls below the threshold accuracy (e.g., based on the validation set).

[0094] In block 316, system 300 performs model selection (e.g., via selection engine 185 in Figure 1) to determine which of the one or more trained models that satisfy the threshold precision has the highest precision (e.g., selected model 308, based on validation in block 314). If it is determined that two or more trained models that satisfy the threshold precision have the same precision, the flow returns to block 312, where system 300 further trains the model using a more refined training set corresponding to a more refined feature set to determine the trained model with the best precision.

[0095] In block 318, system 300 performs a model test using test set 306 (e.g., via test engine 186 in Figure 1) to test the selected model 308. System 300 tests a first trained machine learning model using a first set of features in the test set (e.g., characteristic data from sensors 1-10 for products 81-100) and determines (e.g., based on the first set of features in test set 306) that the first trained machine learning model meets a threshold precision. If the precision of the selected model 308 does not meet the threshold precision (e.g., the selected model 308 is overfitted to training set 302 and / or validation set 304 and is not applicable to other datasets such as test set 306), the flow proceeds to block 312, where system 300 performs model training (e.g., model retraining) using a different training set corresponding to a different set of features (e.g., characteristic data from different sensors). Depending on the determination based on the test set 306 that the selected model 308 has accuracy that meets the threshold accuracy, the flow proceeds to block 320. In at least block 312, the model learns patterns in past data and makes predictions, and in block 318, the system 300 applies the model to the remaining data (e.g., test set 306) and tests the predictions (e.g., adjustment of film deposition parameters based on residual thickness during substrate manufacturing, associated with methods 400A-400C, etc.).

[0096] In block 320, the system 300 receives current characteristic data 346 (e.g., current characteristic data 146 in Figure 1) using a trained model (e.g., selected model 308) to adjust film deposition parameters based on residual thickness during substrate manufacturing, determines (e.g., extracts) predictive data 360 (e.g., predictive data 160 in Figure 1) from the trained model, and performs corrective actions (e.g., updating the process recipe, causing modifications to the deposition process parameters, processing the substrate based on the updated recipe, etc.). In some embodiments, the current characteristic data 346 corresponds to the same type of features in the historical characteristic data 344. In some embodiments, the current characteristic data 346 corresponds to the same type of features as a subset of features in the historical characteristic data 344 used to train the selected model 308 (e.g., associated with adjusting film deposition parameters based on residual thickness during substrate manufacturing, methods 400A-400C, etc.).

[0097] In some embodiments, current data is received. In some embodiments, the current data includes current performance data 356 (e.g., current performance data 156 in Figure 1) and / or current characteristic data 346 (associated with, for example, adjustment of film deposition parameters based on residual thickness during substrate manufacturing, methods 400A-400C, etc.). In some embodiments, at least a portion of the current data is received from a measuring device (e.g., measuring device 128 in Figure 1) or via user input. In some embodiments, the 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.

[0098] In some embodiments, one or more of blocks 310-320 are performed in various orders and / or together 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 the data partitioning of block 310, model verification of block 314, model selection of block 316, and / or model testing of block 318 are not performed.

[0099] Figures 4A to 4C are flowcharts of methods 400A to 400C associated with residual thickness compensation (e.g., adjustment of residual base of film deposition parameters during substrate manufacturing) according to a particular embodiment. In some embodiments, methods 400A to 400C are performed by a processing logic unit including hardware (e.g., circuits, dedicated logic, programmable logic unit, microcode, processing device, etc.), software (e.g., instructions executed by a processing device, general-purpose computer system, or dedicated machine), firmware, microcode, or a combination thereof. In one embodiment, method 400A may be performed by a computer system, such as the computer system structure 100 in Figure 1. In other embodiments or similar embodiments, one or more steps of method 400A may be performed by one or more other machines not shown in the figures. In some embodiments, methods 400A to 400C are performed at least partially by a prediction system 110. In some embodiments, method 400A is performed by a client device 120 (e.g., a corrective action component 122) and / or the prediction system 110 (e.g., a prediction component). In some embodiments, method 400B is executed by a server machine 180 (e.g., a training engine 182). In some embodiments, method 400C is executed by a prediction server 112 (e.g., a prediction component 114) and / or a client device 120 (e.g., a corrective action component 122). In some embodiments, a non-transient storage medium, when executed by a processing device (e.g., a prediction system 110, a server machine 180, a prediction server 112, a client device 120), stores instructions that cause the processing device to execute one or more of methods 400A to 400C.

[0100] For the sake of simplicity, methods 400A to 400C are illustrated and described as a series of steps. However, the steps relating to this disclosure may be performed in various orders and / or simultaneously, and may be performed together with other steps not presented or described herein. Furthermore, in some embodiments, not all illustrated steps are performed in order to carry out methods 400A to 400C in accordance with the subject matter of the disclosed invention. Furthermore, those skilled in the art will understand and recognize that method 800 may alternatively be represented as a series of interrelated states or events through a state diagram.

[0101] Figure 4A is a flowchart of a method relating to the adjustment of film deposition parameters based on deposition thickness during substrate manufacturing, according to an aspect of this disclosure.

[0102] Referring to Figure 4A, in some embodiments, in block 401, the processing logic unit that executes method 400A identifies the material associated with the substrate processing steps of the recipe. In some embodiments, the identified material can be reused between loops, and a loop may have any number of materials in any order. In some embodiments, deposition drift compensation is based on the identified material and the substrate processing steps associated with that material. In some embodiments, the processing logic unit may receive user input to identify the material associated with the substrate processing steps of the recipe. In other embodiments, the processing logic unit may automatically select the material associated with the substrate processing steps of the recipe. For example, the processing logic unit may identify the material associated with the substrate processing steps of a recipe for which at least one process execution has been completed and the material thickness value has been determined. In yet another embodiment, the processing logic unit may identify the material associated with the substrate processing steps of a recipe based on the currently executing process recipe. For example, the processing logic unit may execute a deposition process on a substrate according to a process recipe. The deposition process may be executed in one or more processing chambers. The process recipe may include one or more deposition parameters for the deposition process. For example, deposition parameters may include deposition time for each layer and / or each loop of the processing recipe, temperature setting of the processing chamber, pressure setting of the processing chamber, flow rate setting of the precursor for the material contained in the film to be deposited on the substrate surface, showerhead height, etc. In some embodiments, deposition parameters may differ for each substrate processing area. The deposition process can deposit multiple layers on the substrate. For example, the deposition process can deposit alternating layers of oxide and nitride layers, or alternating layers of oxide and polysilicon layers.

[0103] In block 402, the processing logic unit determines the expected total residual thickness after the substrate processing step. For example, the expected total residual thickness may include the measured thickness of the residual film, the measured thickness of one or more layers of the residual film, and / or the measured thickness of one or more loops of the residual film. The expected total residual thickness can be measured using the measuring device 128. In some embodiments, a thickness profile is obtained from the data store 140. In some embodiments, the expected total residual thickness may be derived from a process recipe. For example, a process recipe may be designed to deposit a 200 angstrom film. In such a case, the expected total residual thickness may be 200 angstroms. In some embodiments, the expected total residual thickness may be measured using a sensor 126 that measures the deposition on the processing chamber wall. In some embodiments, the expected total residual thickness may be determined based on parameters of at least one deposition step (e.g., deposition time, deposition rate, etc.).

[0104] In some embodiments, the processing logic unit can determine characteristic data (e.g., the expected total residual thickness value) by sensors that collect characteristic data (e.g., by measuring the residual thickness deposited on the processing chamber wall). In some embodiments, the processing logic unit can identify characteristic data based on the expected thickness to be added to the substrate (e.g., thickness parameters of the deposition process, measured thickness from previous runs of the same deposition process). In some embodiments, the processing logic unit can identify characteristic data based on the deposited material and the amount of time it was deposited (e.g., process recipe, deposition process parameters). In some embodiments, the processing logic unit can identify characteristic data based on sensor data and / or measurement data of a substrate subjected to a substrate processing process (e.g., deposition process) (e.g., the total residual thickness value, material thickness value, RF power of the substrate processing process, interval value of the substrate processing process, gas flow rate value of the substrate processing process, or chamber pressure value of the substrate processing process).

[0105] In block 403, the processing logic unit determines the expected material thickness value of the material associated with the substrate processing process based on the expected total residual thickness value.

[0106] In some embodiments, the processing logic unit can determine the expected material thickness value associated with the substrate processing step using one or more formulas or mathematical models. In some embodiments, a relationship may exist between the expected total residual thickness and the expected material thickness (e.g., based on the specified material associated with the substrate processing step in the recipe). In some embodiments, this relationship may be a mathematical relationship, formula, and / or function. In some embodiments, this relationship may be derived using at least the expected material thickness (e.g., a data point representing the material thickness after the deposition step), the expected total residual thickness (e.g., a data point representing the residual thickness of the walls, dirt, etc.), and the deposition time (a data point representing the duration of the deposition step in the process recipe). In some embodiments, the input to the formula or function is the expected total residual thickness, and the output of the formula is the expected material thickness. In some embodiments, the processing logic unit can appropriately scale the deposition step time to compensate for drift.

[0107] In some embodiments, a first relationship associated with a material may correspond to a first substrate processing area (e.g., a slot), and a second relationship associated with the same material may correspond to a second substrate processing area (e.g., a relationship based on the same material may be specific to a particular slot).

[0108] In some embodiments, the processing logic unit can generate mathematical formulas (e.g., polynomials, linear formulas, logarithmic formulas, etc.) associated with the identified material. In some embodiments, the formulas can be reused between loops. In some embodiments, there may be material-based formulas specific to each substrate processing area (e.g., slots). For example, a polynomial of degree 3 could be used, such as y=ax 3 +bx2 It can be expressed as +cx+d, where (x,y) are coordinates and a, b, c, and d are constants. As an example, a polynomial of degree 3 was used, but polynomials (of any degree), linear, logarithmic, exponential, etc., can be used. In some embodiments, the formula can be generated using a set of values ​​for the expected total residual thickness as the x variable (e.g., chamber wall residual thickness after loop 1, chamber wall residual thickness after loop 2, chamber wall residual thickness after loop 3, etc.) and a value for the expected material thickness as the y coordinate (e.g., expected deposit thickness at various chamber wall residual thicknesses). The values ​​of (x,y) can be obtained from the expected profile. The constants for the formula are determined using the set of (x,y) coordinates. In some embodiments, the total residual thickness (e.g., chamber wall residual thickness) is the sum of the seasoning thickness and the deposit thickness, where the deposit thickness is equal to the total thickness of all previous loops. The seasoning thickness may include a layer (e.g., a silicon oxide layer) on top of the chamber wall before the substrate is introduced into the chamber for processing. The deposited seasoning layer reduces the possibility of contaminants interfering with subsequent processing steps.

[0109] In some embodiments, the processing logic unit can determine the value of (y) for a particular loop using a formula and the total residual thickness. In particular, the processing logic unit can receive an input (e.g., user-based input, automatic input, etc.) indicating a loop in a layer or deposition process. The processing logic unit can then input the actual material thickness of the loop or layer (obtained from a thickness profile) into a formula to calculate the value of (y) for the loop or layer.

[0110] In some embodiments, the expected material thickness value may include a desired thickness of the film, a desired thickness of one or more layers of the film, and / or a desired thickness of one or more loops of the film. In some embodiments, the expected material thickness value is obtained from a data store 140. In some embodiments, the expected material thickness value may be the difference between a desired material thickness value and an actual material thickness value. In some embodiments, determining the expected material thickness value may include providing a trained machine learning model with an expected total residual thickness value as input. In some embodiments, determining the expected material thickness value may include receiving an output from the trained machine learning model associated with prediction data, where the expected material thickness value is associated with prediction data. In some embodiments, the trained machine learning model may be trained using a data input including historical total residual thickness values ​​and a target output of historical material thickness values.

[0111] In block 404, the processing logic unit updates the recipe based on the material and the expected material thickness of the material to generate an updated recipe (including updated deposition process parameters such as the time value (of deposition), the updated time value, the RF power of the substrate processing process, the interval value of the substrate processing process, the gas flow rate value of the substrate processing process, the chamber pressure value of the substrate processing process, and the chamber temperature). In some embodiments, updating the recipe may include determining an updated time value associated with the substrate processing process. In some embodiments, determining the updated time value associated with the substrate processing process may be based on the time value associated with the substrate processing process, the expected total residual thickness value, and the expected material thickness value. In some embodiments, updating the recipe may include determining at least one of the updated RF power of the substrate processing process, the updated interval value of the substrate processing process, the updated gas flow rate value of the substrate processing process, or the updated chamber pressure value of the substrate processing process.

[0112] In some embodiments, the updated recipe may include one or more corrective actions (e.g., updating deposition process parameters, updating the process recipe) applied to parameters of the process recipe (e.g., associated with processing chambers between one or more steps of the process recipe). In particular, the updated recipe may include adjustments to the deposition time for one or more layers and / or loops, the temperature setting of the processing chamber, the pressure setting of the processing chamber, the flow rate setting of the precursor for the material contained in the film to be deposited on the substrate surface, the power supplied to the processing chamber, the ratio of two or more settings, etc. For example, the updated recipe may include adjustments to the deposition time for loops in the process recipe. In some embodiments, the updated recipe may include a set of parameter adjustments for each layer and / or each loop of the process recipe. For example, the updated recipe may include adjustments to the deposition time for the first loop, second loop, third loop, etc., up to the final loop. Each adjustment may be applied to each deposition step to adjust the thickness of one or more loops or layers so that the expected film thickness indicated by the expected total residual thickness is the same as the film stack thickness. For example, the expected total residual thickness may include the measured thickness of the film, the measured thickness of one or more layers of the film, and / or the measured thickness of one or more loops of the film. The thickness profile may be measured using the measuring device 128 and / or one or more sensors 126. In some embodiments, the thickness profile is retrieved from the data store 140.

[0113] For example, if the expected film thickness after loop 39 (e.g., expected total residual thickness) is a first value (e.g., 30,000 nm), the expected film thickness after loop 40 is a second value (e.g., 30,500 nm), and the actual film thickness during and after the deposition is a third value (e.g., 30,050 nm), then the updated recipe can instruct a modification to the deposition time for loop 40 (e.g., shortening the deposition time for loop 40 by a specific period) so that the actual film thickness after loop 40 is equal to the expected film thickness (e.g., 30,500 nm).

[0114] In some embodiments, the processing logic unit can generate an updated recipe using one or more formulas or mathematical models associated with materials associated with the substrate processing steps of the recipe. For example, the processing logic unit can generate a curve-fitting model using data values ​​from the expected total residual thickness and / or expected material thickness, and then use the curve-fitting model to determine the offset time values ​​for specific steps during the current deposition process.

[0115] In some embodiments, for example, a mathematical formula (for example, a polynomial of degree 3, y=ax) is used. 3 +bx 2 The formula (x, y) is expressed as (x, y) / (y, d) is a constant, and can be used to update a recipe (e.g., a recipe for a substrate processing area). For example, in some embodiments, the processing logic unit can use the formula and the total residual thickness to determine the value of (y) for a particular loop. In particular, the processing logic unit can receive inputs indicating a loop in a layer or deposition process (e.g., user-based input, automatic input, etc.). The processing logic unit can then input the actual material thickness of the loop or layer (obtained from the thickness profile) into the formula to calculate the value of (y) for the loop or layer. In some embodiments, the processing logic unit generates an updated recipe based on the calculated value of (y). In some embodiments, the updated recipe may be generated based on the following formula: For example, updated recipe = (y[first loop] / y[current loop number])*t step However, t step This is the expected time for the selected loop. While we have described determining a modified profile (e.g., an updated recipe) using a curve fitting method, models including but not limited to regression analysis and least squares methods can be used to generate a modified profile.

[0116] In some embodiments, the processing logic unit can generate updated recipes using a machine learning model (e.g., machine learning model 190) or an estimation engine.

[0117] In block 405, the processing logic unit processes the substrate based on the updated recipe. For example, the processing logic unit may deposit a first set of film layers on the substrate (e.g., execute the first set of the substrate processing loop), determine the expected total residual thickness of the deposited film, generate an updated recipe to correct any defects detected during the deposition of the first set of film layers, apply the updated recipe to the process recipe, and deposit a second set of film layers on the substrate (e.g., execute the second set of the substrate processing loop). Thus, the deposition process recipe can be adjusted in real time or near real time (e.g., substantially real time). This process can be repeated for each deposition step of the process recipe.

[0118] In some embodiments, the updated recipe in block 405 may still cause drift in the processing chamber and during layer deposition on the substrate. In some embodiments, performance data associated with the updated recipe is identified after block 405. In some embodiments, specific parts of method 400A may be updated based on performance data (e.g., updating the expected total residual thickness associated with the substrate processing steps of the recipe, updating the expected material thickness value, updating deposition process parameters, etc.). In some embodiments, the updated method 400A may be repeated to more accurately execute the substrate processing steps of the recipe. In some embodiments, the processing logic unit can determine whether the drift (e.g., the material thickness value) meets a first threshold (e.g., is above a certain value) and can repeat method 400A until the drift meets a second threshold (e.g., is below a certain value). Figure 4B shows a method for training a machine learning model (e.g., model 190 in Figure 1) to determine predictive data (e.g., predictive data 160 in Figure 1) associated with residual thickness compensation, according to an aspect of the present disclosure.

[0119] Referring to Figure 4B, in block 410 of method 400B, the processing logic unit identifies past characteristic data of the substrate (e.g., past total residual thickness values, past materials associated with past substrate processing steps of past recipes, past material thickness values, past characteristic data 144, etc.). Past characteristic data may include data from past recipes, past deposition process parameters, past substrates, and / or past processing chamber characteristic data.

[0120] In some embodiments, in block 412, the processing logic unit identifies past performance data (e.g., past material thickness values, the difference between the actual material thickness value and the expected material thickness value, the difference between the actual total residual thickness value and the expected total residual thickness value, past performance data 154 in Figure 1, etc.) of past deposition process parameters, process recipes, substrates, and / or processing chambers. The past performance data may include past material thickness values ​​(e.g., the difference between the actual material thickness value and the expected material thickness value, the difference between the actual total residual thickness value and the expected total residual thickness value, etc.) and / or data from past processing chambers (e.g., one or more values ​​such as the accuracy of the deposition process and / or satisfaction of the expected total residual thickness value (e.g., after the deposition process)). Performance data, including historical performance data, may include sensor data and / or measurement data (e.g., total residual thickness value, material thickness value, RF power value, interval value, gas flow rate value, or chamber pressure value), or user input indicating the performance of a substrate when it satisfies certain parameters or achieves a certain level of performance (e.g., the ability to pass a probe test measuring voltage). Performance data, including historical performance data, may include sensor data and / or measurement data, or user input indicating the performance of a processing chamber when it satisfies certain parameters or achieves a certain level of performance (e.g., the ability to pass a deposition drift test). At least a portion of the historical characteristic data and historical performance data may be associated with components of a new substrate processing apparatus (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.

[0121] In block 414, the processing logic unit trains a machine learning model using a data input containing historical characteristic data 144 and / or a target output containing historical performance data 154, and generates a trained machine learning model.

[0122] In some embodiments, historical characteristic data is from past substrates or processing chambers, and / or historical performance data corresponds to past substrates or processing chambers. In some embodiments, historical characteristic data corresponds to a deposition process or process recipe, or to a substrate or processing chamber used in a deposition process or process recipe. In some embodiments, historical characteristic data includes past measurements of past substrates or processing chambers, and / or historical performance data corresponds to past substrates or processing chambers. Historical performance data may be associated with substrate quality, such as substrate measurement data, substrate throughput, and substrate defects. Historical performance data may be associated with the quality of a process recipe (e.g., deposition process), such as the agreement between the actual total residual thickness value and the expected total residual thickness value. Historical performance data may be associated with the quality of process recipe or deposition process parameters, such as the ability to accurately deposit each layer and / or film to match the expected total residual thickness of the deposition process. Historical performance data may be associated with the quality of components of the substrate processing apparatus, such as test data, substrate measurement data, and substrate failure time.

[0123] In block 414, the processing logic unit uses data inputs including historical characteristic data 144 (e.g., historical total residual thickness values) and / or target outputs including historical performance data 154 (e.g., historical material thickness values) to train a machine learning model and generate a trained machine learning model.

[0124] In some embodiments, historical characteristic data is from past substrates or processing chambers, and / or historical performance data corresponds to past substrates or processing chambers. In some embodiments, historical characteristic data includes past measurements of past substrates or processing chambers, and / or historical performance data corresponds to past substrates or processing chambers. Historical performance data may be associated with substrate quality, such as substrate measurement data (e.g., total residual thickness value, material thickness value, etc.), substrate throughput, and substrate defects. Historical performance data may be associated with the quality of the process recipe or deposition process, such as the ability to accurately deposit the expected total residual thickness and / or expected material thickness. Historical performance data may be associated with the quality of components of the substrate processing apparatus, such as test data, substrate measurement data, and substrate failure time.

[0125] In block 414, a trained machine learning model may be generated, which is trained using a target output including historical characteristic data 144 and / or historical performance data 154, and configured to update recipes, generate updated recipes, and / or trigger corrective actions based on the characteristic data (e.g., processing the substrate based on the updated recipe). In some embodiments, the trained machine learning model may be configured to predict performance data 152 (e.g., performance data including updated process recipes, updated deposition process parameters, performance data of substrates processed with the updated process recipe, performance data of substrates processed with updated deposition process parameters, etc.) based on characteristic data 142 (e.g., expected total residual thickness value in block 402 in Figure 4A, expected material thickness value in block 403 in Figure 4A). Depending on whether the predicted performance data meets a threshold (e.g., deposition drift exceeds a certain value), the processing logic unit may trigger corrective actions (e.g., updating deposition process parameters, updating the process recipe, processing the substrate based on the updated recipe, etc.). If the predicted performance data does not meet the threshold, the processing logic unit may choose not to perform any corrective actions (for example, by keeping the process recipe the same or keeping the deposition process parameters the same).

[0126] In some embodiments, the deposition process parameters may include time values, updated time values, recipes, updated recipes, RF power for the substrate processing process, interval values ​​for the substrate processing process, gas flow rate values ​​for the substrate processing process, chamber pressure values ​​for the substrate processing process, updated RF power for the substrate processing process, updated interval values ​​for the substrate processing process, updated gas flow rate values ​​for the substrate processing process, and updated chamber pressure values ​​for the substrate processing process.

[0127] Figure 4C shows a method 400C in which a trained machine learning model (e.g., Model 190 in Figure 1) is associated with adjusting deposition parameters based on residual thickness during substrate manufacturing, thereby triggering the execution of corrective actions.

[0128] Referring to Figure 4C, in block 420 of method 400C, the processing logic unit identifies characteristic data. In some embodiments, the characteristic data in block 420 includes the expected total residual thickness value, the expected material thickness value, and so on. In some embodiments, block 420 is similar to blocks 401 and 402 in Figure 4A.

[0129] In block 422, the processing logic unit provides characteristic data as data input to a trained machine learning model (trained, for example, via block 414 in Figure 4B). In some embodiments, the trained machine learning model may be associated with a variable relationship between the expected total residual thickness and the expected material thickness.

[0130] In block 424, the processing logic unit receives output from a trained machine learning model, associated with the predicted data, where the updated recipe is based on the predicted data.

[0131] In block 426, the processing logic unit triggers the execution of corrective actions based on the predicted data.

[0132] In some embodiments, block 403 in Figure 4A includes training a machine learning model to determine the expected material thickness value of the material associated with the substrate processing step based on the expected total residual thickness value. In some embodiments, block 403 in Figure 4A uses the trained machine learning model to This includes determining the expected material thickness value of the material associated with the substrate processing step based on the expected total residual thickness value.

[0133] In some embodiments, block 404 in Figure 4A includes training a machine learning model to update the recipe based on the material and the expected material thickness value of the material to generate an updated recipe.

[0134] In some embodiments, the characteristic data 142 is a value of the expected total residual thickness (e.g., an expected deposition thickness associated with the deposition process), and the trained machine learning model of block 422 was trained using a data input that includes historical expected total residual thickness values ​​and / or historical actual total residual thickness values, and a target output that includes historical performance data 154 (e.g., actual total residual thickness values, actual material thickness values, etc.).

[0135] In some embodiments, the characteristic data 142 is characteristic data of the deposition thickness (e.g., the expected total residual thickness value, the expected material thickness value, etc.), and the trained machine learning model in block 422 is trained using a data input that includes historical deposition thickness characteristic data and a target output that includes historical performance data 154 that includes historical deposition thickness characteristic data of historical substrates or historical deposition processes. The prediction data 160 in block 424 can be associated with predicted performance data (e.g., substrate performance data, or deposition recipe or process performance data) based on the characteristic data. Depending on whether the predicted performance data meets a threshold (e.g., deposition drift exceeds a certain level), the processing logic unit can trigger corrective actions (e.g., updating the processing recipe, updating deposition parameters, etc.). Depending on whether the substrate does not meet a threshold, the processing logic unit can prevent corrective actions from being taken (e.g., keeping the process recipe the same, keeping the deposition process parameters the same, etc.).

[0136] Figure 5 is a block diagram showing a computer system 500 according to a particular embodiment. In some embodiments, the computer system 500 is one or more such as a client device 120, a prediction system 110, a server machine 170, a server machine 180, and / or a prediction server 112.

[0137] In some embodiments, the computer system 500 is connected to other computer systems (for example, via a network such as a local area network (LAN), intranet, extranet, or the Internet). In some embodiments, the computer system 500 operates with the capacity of a server or client computer in a client-server environment, or as a peer computer in a peer-to-peer or distributed network environment. In some embodiments, the computer system 500 is provided by a personal computer (PC), tablet PC, set-top box (STB), personal digital assistant (PDA), mobile phone, web appliance, server, network router, switch or bridge, or any device capable of executing (sequentially or separately) a set of instructions that specify the actions to be performed by that device. Furthermore, the term “computer” includes any collection of computers that individually or in conjunction execute one or more sets of instructions to perform any one or more of the methods described herein.

[0138] 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.

[0139] 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 specialized processor (e.g., an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), a Digital Signal Processor (DSP), or a network processor).

[0140] In some embodiments, the computer system 500 further includes a network interface device 522 (for example, connected to a network 574). In some embodiments, the computer system 500 also includes a video display unit 510 (for example, a liquid crystal display (LCD)), an alphanumeric input device 512 (for example, a keyboard), a cursor control device 514 (for example, a mouse), and a signal generating device 520.

[0141] In some embodiments, the data storage device 518 includes a non-transient computer-readable storage medium 524 that stores instructions 526 for encoding one or more of the methods or functions described herein, the instructions 526 including instructions for encoding the components of Figure 1 (e.g., corrective action component 122, predictive component 114, etc.) and for performing the methods described herein (e.g., one or more of methods 400A to 400C).

[0142] In some embodiments, instruction 526 also resides entirely or partially in the volatile memory 504 and / or processing device 502 during execution by the computer system 500, and therefore, in some embodiments, the volatile memory 504 and processing device 502 also constitute a machine-readable storage medium.

[0143] Although the computer-readable storage medium 524 is shown as a single medium in the illustrated example, the term “computer-readable storage medium” includes a single or multiple mediums (e.g., a centralized or distributed database, and / or associated caches and servers) that store one or more sets of executable instructions. The term “computer-readable storage medium” also includes any tangible medium capable of storing or encoding a set of instructions for computer execution that causes a computer to perform one or more of the methods described herein. The term “computer-readable storage medium” includes, but is not limited to, solid-state memory, optical media, and magnetic media.

[0144] In some embodiments, the methods, components, and features described herein may be implemented by separate hardware components or incorporated into the functionality of other hardware components such as application-specific integrated circuits (ASICs), FPGAs, DSPs, or similar devices. In addition, the methods, components, and features may be implemented by firmware modules or functional circuits within a hardware device. Furthermore, the methods, components, and features may be implemented in any combination of hardware devices and computer program components, or in a computer program.

[0145] Unless otherwise specified, terms such as “identifying,” “determining,” “updating,” “causing,” “providing,” “receiving,” “performing,” “obtaining,” “accessing,” “adding,” and “training” refer to actions and processes performed or realized by a computer system that manipulates data represented as physical (electronic) quantities in the computer system’s registers and memory, and converts it into other data similarly represented as physical quantities in the computer system’s memory or registers, or in other such information storage devices, transmission devices, or display devices. Furthermore, in this specification, terms such as “first,” “second,” “third,” and “fourth” are presented as labels to distinguish between various elements and do not have an orderly meaning according to their numerical designation.

[0146] The embodiments described herein also relate to apparatus for carrying out the methods described herein. The apparatus may be specifically configured for carrying out the methods described herein, or may include a general-purpose computer system selectively programmed by a computer program stored in the computer system. Such a computer program is stored in a computer-readable tangible storage medium.

[0147] The methods and exemplary embodiments described herein are not inherently related to any particular computer or other device. Various general-purpose systems can be used in accordance with the teachings described herein, or it may be more convenient to construct more specialized devices for performing each of the methods and / or individual functions, routines, subroutines, or steps of said methods. Examples of various systems are described in the preceding specification.

[0148] The descriptions in the preceding specification are intended to be illustrative and not limiting. While this disclosure has been described with reference to specific exemplary practices and embodiments, it will be clear that this disclosure is not limited to the examples and embodiments described. The scope of this disclosure should be defined with reference to the following claims, together with the entire scope of equivalents to which such claims are granted.

Claims

1. Identifying materials associated with the substrate processing steps in the recipe, To determine the expected total residual thickness after the substrate processing step, Based on the expected total residual thickness value, the expected material thickness value of the material associated with the substrate processing step is determined. To compensate for deposition drift, the deposition process parameters are updated based on the material and the expected material thickness of the material, thereby generating an updated recipe. The substrate is processed according to the updated recipe, Methods that include...

2. The method according to claim 1, wherein the expected material thickness value is the difference between the desired material thickness value and the actual material thickness value.

3. The method according to claim 1, wherein the updating of the recipe includes determining an updated time value associated with the substrate processing step.

4. The method according to claim 3, wherein the determination of the updated time value associated with the substrate processing step is based on the time value associated with the substrate processing step, the expected total residual thickness value, and the expected material thickness value.

5. The method according to claim 1, wherein the recipe update includes determining at least one of the updated radio frequency (RF) power of the substrate processing step, the updated interval value of the substrate processing step, the updated gas flow rate value of the substrate processing step, or the updated chamber pressure value of the substrate processing step.

6. The determination of the expected material thickness value is as follows: The aforementioned expected total residual thickness value is provided as input to a trained machine learning model, The method according to claim 1, wherein an output associated with prediction data is received from the trained machine learning model, the predicted material thickness value being associated with the prediction data.

7. The method according to claim 6, wherein the trained machine learning model is trained using data inputs including past total residual thickness values ​​and target outputs of past material thickness values.

8. A non-transient computer-readable storage medium for storing instructions, wherein, when an instruction is executed, it is stored on a processing device. Identifying materials associated with the substrate processing steps in the recipe, To determine the expected total residual thickness after the substrate processing step, Based on the expected total residual thickness value, the expected material thickness value of the material associated with the substrate processing step is determined. To compensate for deposition drift, the deposition process parameters are updated based on the material and the expected material thickness of the material, thereby generating an updated recipe. The substrate is processed according to the updated recipe, A non-transient, computer-readable storage medium that enables the execution of processes including the following.

9. The non-transient computer-readable storage medium according to claim 8, wherein the expected material thickness value is the difference between the desired material thickness value and the actual material thickness value.

10. The non-transient computer-readable storage medium according to claim 8, wherein updating the recipe includes determining an updated time value associated with the substrate processing step.

11. The non-transient computer-readable storage medium according to claim 10, wherein determining the updated time value associated with the substrate processing step is based on the time value associated with the substrate processing step, the expected total residual thickness value, and the expected material thickness value.

12. The non-transient computer-readable storage medium according to claim 8, wherein the recipe update includes determining at least one of the updated radio frequency (RF) power of the substrate processing step, the updated interval value of the substrate processing step, the updated gas flow rate value of the substrate processing step, or the updated chamber pressure value of the substrate processing step.

13. The determination of the expected material thickness value is as follows: The aforementioned expected total residual thickness value is provided as input to a trained machine learning model, A non-transient computer-readable storage medium according to claim 8, which receives an output from the trained machine learning model associated with prediction data, wherein the predicted material thickness value is associated with the prediction data.

14. The non-transient computer-readable storage medium according to claim 13, wherein the trained machine learning model is trained using data inputs including past total residual thickness values ​​and target outputs of past material thickness values.

15. It is a system, Memory and A processing device connected to the aforementioned memory, The processing device comprises, Identifying materials associated with the substrate processing steps in the recipe, To determine the expected total residual thickness after the substrate processing step, Based on the expected total residual thickness value, the expected material thickness value of the material associated with the substrate processing step is determined. To compensate for deposition drift, the deposition process parameters are updated based on the material and the expected material thickness of the material, thereby generating an updated recipe. The substrate is processed according to the updated recipe, A system that performs this task.

16. The system according to claim 15, wherein the expected material thickness value is the difference between the desired material thickness value and the actual material thickness value.

17. The system according to claim 15, wherein the processing device determines an updated time value associated with the substrate processing step in order to update the recipe.

18. The system according to claim 17, wherein the processing device determines the updated time value associated with the substrate processing step based on the time value associated with the substrate processing step, the expected total residual thickness value, and the expected material thickness value.

19. In order to determine the expected material thickness value, The processing device is The aforementioned expected total residual thickness value is provided as input to a trained machine learning model, Receiving an output from the trained machine learning model associated with prediction data, wherein the predicted material thickness value is associated with the prediction data. The system according to claim 15, which performs the following.

20. The system according to claim 19, wherein the trained machine learning model is trained using data inputs including past total residual thickness values ​​and target outputs of past material thickness values.

Images