Process Characterization and Correction Using Optical Wall Process Sensor (OWPS)

Abstract

A method includes receiving, by a processing device, first sensor data indicating a state of a wall corresponding to a first processing chamber. The first sensor data includes optical spectral data. The method further includes determining, by the processing device, a first value based on the first sensor data. The first value corresponds to a first amount of a product disposed along a surface of the wall at a first time. The method further includes determining, by the processing device, a first update to a first process operation associated with the first processing chamber based on the first value. The method further includes performing, by the processing device, one or more of (i) preparing a notification indicating the first update for presentation on a graphical user interface (GUI), or (ii) causing the first process operation to be performed in accordance with the first update.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to process control and process learning using optical sensors. Background Art

[0002] Variations in the conditions on the process chamber surfaces affect various process parameters. For example, etch byproducts

[0003] Conventional systems lack a reliable method to monitor surface conditions within the process chamber, including the liner (or

[0004] Furthermore, due to the lack of information such as optical information about the state of the process chamber walls, Summary of the invention

[0005] The following is a simplified summary of the present disclosure to provide an overview of some aspects of the present disclosure.

[0006] Some embodiments described herein encompass a method comprising: performing, by a processing device,

[0007] Additional or related embodiments described herein encompass a system comprising: processing

[0008] Additional or related embodiments described herein include a non-transitory machine operable to store instructions.

[0009] According to these and other aspects of the present disclosure, numerous other features are provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The present disclosure is illustrated by way of example and not by way of limitation in the figures of the accompanying drawings, in which

[0011] Figure 1 is a schematic top view of an example processing system according to some embodiments.

[0012] Figure 2 is a simplified side view of a system for monitoring a processing chamber in accordance with some embodiments.

[0013] Figure 3 According to some embodiments, Figure 2 An enlarged portion of a side view of the system, shown embedded in

[0014] Figure 4 is a block diagram illustrating an exemplary system architecture, and embodiments of the present disclosure may be implemented in

[0015] Figure 5A According to some embodiments, a method for determining a process operation based on a chamber wall value update is provided.

[0016] Figure 5B According to some embodiments, a method for using optical sensor data to initiate corrective action is provided.

[0017] Figure 5C According to some embodiments, a method for maintaining uniformity of a processing chamber is provided.

[0018] Figure 5D According to some embodiments, a method for detecting and correcting anomalies in a process chamber and / or

[0019] Figure 5E According to some embodiments, a method for utilizing optical sensor data generated over time is provided.

[0020] Fig. 6A -D is related to determining a process operation based on a chamber wall value update according to some embodiments

[0021] Figure 7 According to some embodiments, one or more optical elements of a deposited thin film on a transparent film are used.

[0022] Figure 8 Illustration of model training for updated prediction and simulation of chamber operation according to some embodiments

[0023] Fig. 9 A block diagram of an example computing device is depicted in accordance with some embodiments. DETAILED DESCRIPTION

[0024] Embodiments described herein relate to a method for controlling a process using an optical wall process sensor (OWPS)

[0025] In some systems, it is desirable to characterize a film deposited on a surface within a processing chamber (e.g., a

[0026] In conventional systems, a sample can be used to monitor thin films deposited on surfaces within a processing chamber.

[0027] Embodiments of the present disclosure can address at least one of these deficiencies of conventional solutions.

[0028] In some embodiments, determining the state of a processing chamber may involve adapting the analysis to take into account the processing

[0029] In various embodiments, the condition of a portion of a liner of a processing chamber generally indicates the condition of the processing chamber.

[0030] In another example, the thickness of the deposited film layer on the inner surface of the processing chamber can be different from the thickness of the film layer being treated.

[0031] Some embodiments of the disclosed systems and methods include a light source (e.g., a broadband light source), a spectrometer

[0032] In various embodiments, during processing within the chamber, the light coupling device can couple light from the light source to the

[0033] In some embodiments, the optical coupling device reflects light (e.g., a combination of light reflected from various surfaces)

[0034] Embodiments of the system and method may also include a processing device (or control device) coupled to the spectrometer.

[0035] The processing equipment can then fit the reflectance measurement signal to a thin film optical model to determine

[0036] In one embodiment, for example, the processing device (or controller) compares the thickness of the process film layer with the base film layer.

[0037] In some embodiments, the processing device (or controller) determines the transparent film and / or the chamber wall /

[0038] Embodiments of the present disclosure provide a method for updating process parameters based on optical chamber wall values.

[0039] In addition, embodiments of the present disclosure provide a method for generating a novel oscilloscope based on the OWPS sensor.

[0040] The method of the present disclosure includes: receiving, by a processing device, a first

[0041] Another aspect of the present disclosure includes a non-transmittable machine-readable storage medium.

[0042] Another aspect of the present disclosure includes a method comprising: by a processing device,

[0043] Figure 1 FIG. 1 is a top view of an exemplary processing system 100 according to one aspect. The processing system 100 includes

[0044] The processing system 100 may further include a host 102 including a transfer chamber 114 and a

[0045] In various embodiments, the processing chamber 103 may be adapted to perform any number of operations on the substrate 110.

[0046] In the embodiment, and by way of illustration of any robot, the transfer chamber robot 101 comprises

[0047] In various embodiments, one or more of the processing chambers 103 may include a transparent window 120.

[0048] Controller 109 (e.g., tool and equipment controller) can control various aspects of processing system 100.

[0049] In various embodiments, the controller 109 includes (or is coupled to) a processing device 130 and is associated with an optical

[0050] In some embodiments, the processing device 130 may analyze the one or more optical film properties.

[0051] The controller 109 and / or the processing device 130 may be and / or may include, for example, a personal computer, a server, or a processor.

[0052] Figure 2 A simplified side view of a system 200 for monitoring a processing chamber is illustrated in accordance with one aspect.

[0053] System 200 may include, for example, a processing chamber 103 including a liner 124, such as Figure 1 As shown. Processing

[0054] In an embodiment, the system 200 further includes a light source 201 (e.g., a broadband light source or other electromagnetic

[0055] In some embodiments, light source 201 is a flashlight. Light source 201 can produce predictable lighting,

[0056] In various embodiments, the optical coupling device 204 may be adapted to couple light along the optical path in two directions.

[0057] In one embodiment, the spectrometer 225 also has a detection range similar to the wavelength range of the light source.

[0058] In various embodiments, the controller 109 includes or is coupled to a processing device 130 and includes a memory

[0059] In some embodiments, the one or more optical film properties include the deposited film thickness

[0060] Figure 3 According to one embodiment, Figure 2 An enlarged portion of a side view of the system, shown embedded in the

[0061] In various embodiments, the transparent window 120 may be shaped like a plug (eg, a plug).

[0062] The flange 305 can abut against the outer surface of the wall 222. In one embodiment, the seal 313 is positioned

[0063] In various embodiments, the transparent film 307 may be deposited onto the substrate, for example, via atomic layer deposition (ALD).

[0064] In various embodiments, the deposition process (eg, ALD) of the transparent film 307 is carefully controlled.

[0065] In some embodiments, during processing, the process film layer 309 (eg, the process film layer) is deposited

[0066] The return optical signal at each interface (e.g., the surface that can reflect light) can be

[0067] Figure 4 is a block diagram illustrating an exemplary system architecture, and embodiments of the present disclosure may be implemented in

[0068] Manufacturing system 402, metering system 410, client device 450, data storage 440, server

[0069] Client device 450 may be or include any personal computer (PC), laptop computer,

[0070] like Figure 4 As shown, the manufacturing system 402 includes a processing tool 404, a process program 406, and a process controller.

[0071] Processing procedures 406, or sometimes referred to as process recipes, process operations, or process steps, may include

[0072] The process controller 408 may include a device designed to manage and / or coordinate the actions of the process tool 404.

[0073] like Figure 4 As shown, the metrology system 410 includes a metrology tool 414 and a data preparation tool 416.

[0074] Data preparation tools 416 may include tools for extracting features and / or generating data that is consistent with the data measured by metrology tools 414.

[0075] In some embodiments, data preparation tool 416 may perform measurement data (e.g.,

[0076] In some embodiments, the state of the processing chamber can be measured throughout the process operation. For example,

[0077] In some embodiments, the extracted features, generated synthetic / engineering data and statistical analysis

[0078] Data storage 440 may be a memory (such as a random access memory), a drive (such as a

[0079] Server 420 may include one or more computing devices, such as rack-mounted servers, routers,

[0080] Chamber matching tool 422, sensor matching tool 424, recipe development tool 426 and process control

[0081] In some embodiments, chamber matching tool 422, sensor matching tool 424, recipe development tool

[0082] In one example, the chamber matching tool 422 can determine the first process based on the chamber value data.

[0083] In another example, the sensor matching tool 424 can determine the pairing of the chamber value data with the chamber value data.

[0084] In another example, the recipe development tool 426 can determine the process recipe based on the chamber value data.

[0085] As another example, the process control tool 428 may determine, based on the chamber value data, whether to perform a process

[0086] Updates to the process recipe may change the way the processing tool 404 implements the process recipe 406.

[0087] As previously described, in some embodiments, the chamber matching tool 422, the sensor matching tool 424,

[0088] Modeling system 470 may include one or more computing devices, such as rack-mounted servers, routers,

[0089] In some embodiments, model 490 is stored on server machine 492 and / or server 420 .

[0090] In some embodiments, the modeling system 470 further includes a server machine 472 and a server machine

[0091] The server machine 472 may include a data set generator 474 that is capable of generating a data set (e.g., a

[0092] The server machine 480 includes a training engine 482, a validation engine 484, and a test engine 486.

[0093] The validation engine 484 can determine the trained model based on the corresponding set of features of each training set.

[0094] Model 490 may refer to a model created by training engine 482 using a training set including

[0095] The chamber value component 494 can provide current data (e.g., indicating the material on the inner surface of the processing chamber).

[0096] For purposes of illustration and not limitation, aspects of the present disclosure describe the use of historical data.

[0097] In some embodiments, client device 450, server 420, data storage 440, and modeling

[0098] Generally speaking, in one embodiment, the client device 450, the data storage 440,

[0099] In some embodiments, a "user" may be represented as a single individual.

[0100] Figure 5A -E is a flow chart of method 500A-E associated with using an optical sensor for a processing chamber

[0101] For ease of explanation, method 500A-E is depicted and described as a series of operations.

[0102] refer to Figure 5A At block 502 of method 500A, a processing device may receive a signal indicating that the first

[0103] At block 504, the processing device may determine a first value based on the first sensor data.

[0104] At block 506, the processing device may determine, based on the first value, a value associated with the first processing chamber.

[0105] In some embodiments, optical sensor data can be used to track the state of the chamber.

[0106] In some embodiments, optical data (and / or optical-based data) for a set of processing chambers is received and stored.

[0107] In some embodiments, multivariate methods can be used, for example, for anomaly detection, outlier labeling,

[0108] At block 508, the processing device may prepare a notification indicating the first update for presentation on the GUI.

[0109] Optionally, at block 510, the processing device may determine, based on the first value, a pair of

[0110] In some embodiments, a baselining procedure may be performed to identify and / or correct the optical sensor

[0111] Optionally, at block 512, the processing device may determine a second

[0112] Optionally, at block 514, the processing equipment may determine a process associated with the first process operation.

[0113] Figure 5B According to some embodiments, an implementation for using optical sensor data to initiate corrective action

[0114] At block 522, processing logic processes the first data to obtain second data. The second data includes

[0115] In some embodiments, the process chamber may be in a reference state (e.g., consistent with typical process conditions).

[0116] At block 524, processing logic generates a property of a processing operation for the processing chamber based on the second data.

[0117] At block 526, processing logic causes corrective action based on the indication of the performance of the processing chamber.

[0118] Figure 5C According to some embodiments, a method 500C for maintaining uniformity of a processing chamber is shown.

[0119] At block 532, processing logic receives second data from an optical sensor of the processing chamber.

[0120] At block 534, processing logic generates a process chamber based on the first data and the second data.

[0121] At block 536, processing logic determines one or more of the performance between the first operation and the second operation.

[0122] Figure 5D According to some embodiments, a method for detecting and correcting anomalies in a process chamber and / or

[0123] At block 544, processing logic generates a first indication of the performance of the first chamber based on the first data.

[0124] At block 546, processing logic determines the performance between the first processing chamber and the second processing chamber.

[0125] At block 548, processing logic causes the first processing chamber and the second processing chamber to perform a

[0126] Figure 5E According to some embodiments, a method for utilizing optical sensor data collected over time is

[0127] At block 554, processing logic compares the first sensor data to the second sensor data.

[0128] In some embodiments, the

[0129] In some embodiments, data from several processing operations (e.g., executed over a period of time) may be analyzed.

[0130] Fig. 6A -D is associated with determining a process operation based on a chamber wall value update according to some embodiments

[0131] refer to Fig. 6A , a process 600A for updating a chamber cleaning recipe is shown. The process 600A may be performed by

[0132] At block 608, the processing device may cause the initiation of the processing operation. In some embodiments,

[0133] After the processing operation, at block 610, the processing equipment may determine whether the film on the wall of the processing chamber

[0134] At block 612, the processing device may determine whether a threshold process layer characteristic has been met.

[0135] refer to Figure 6B , a process 600B for calibrating a sensor of a processing chamber is shown. The process 600B may be

[0136] refer to Figure 6C , a process 600C for updating a chamber process recipe is shown. The process 600C may be performed by

[0137] At block 638, the processing device may update the first dimensionless value and the second dimensionless value.

[0138] refer to Fig.6D , a process 600D for updating a chamber process recipe endpoint is shown. The process 600D may be

[0139] At block 624, the processing equipment may determine the characteristics of the film deposited on the walls of the processing chamber.

[0140] Figure 7 According to various aspects of the present disclosure, a transparent film on a processing chamber wall (e.g.

[0141] refer to Figure 7 , method 700 may begin at block 710, where processing logic processes the reflection measurement

[0142] In various embodiments, a threshold change (e.g., from a baseline measurement, a standard measurement, a golden run measurement)

[0143] The method 700 may continue at block 725, where the processing logic triggers a correction process within the processing chamber.

[0144] The method 700 may similarly continue, where processing logic determines at block 730 that the process film layer 309

[0145] In some embodiments, method 700 may continue to block 740, where a processing device is disposed in a processing chamber.

[0146] In various embodiments, method 700 may continue with the cleaning process triggered by operation 745.

[0147] Conceived as additional to or similar to Figure 7 The method 700 is a method of processing a process in a processing chamber.

[0148] According to some embodiments, the processing chamber may be configured to process a substrate (or a group of substrates) after each substrate (or a group of substrates) is processed.

[0149] Figure 8 FIG. 1 illustrates a model for updating prediction and simulation of chamber operation according to aspects of the present disclosure.

[0150] Model training workflow 805 is used to train one or more machine learning models (e.g., deep learning

[0151] The various model outputs are described in this paper. The specific quantities and arrangements of the models are described and shown.

[0152] In some embodiments, one or more models are trained to perform one or more of the previously described

[0153] The chamber operation update predictor 864 may be based on the inner surface of the processing chamber wall (e.g., the processing chamber

[0154] The chamber quality index generator 870 may generate quality index data 872. In some embodiments,

[0155] The performance matching model 874 can accept the input data 862 and generate performance matching data 876 as

[0156] The correction action predictor 878 can receive input data 862 and generate correction action data 880 as

[0157] One type of machine learning model that can be used to perform some or all of the above tasks is the Artificial Intelligence Model.

[0158] In one embodiment, the one or more machine learning models are recurrent neural networks (RNNs).

[0159] The training of a neural network can be achieved in a supervised learning manner, which involves feeding the network with

[0160] For model training workflow 805, use a dataset containing hundreds, thousands, tens of thousands, hundreds of thousands, or

[0161] To implement training, processing logic inputs the training data set 836 into one or more untrained machine

[0162] Training can be performed by processing the chamber data 810 and the process result data 812 one at a time or

[0163] A machine learning model processes input to produce output. An artificial neural network consists of an input layer.

[0164] Thus, the output may include one or more predictions or inferences. For example, the output predictions or inferences may include:

[0165] Once the model parameters have been optimized, model validation can be performed to determine whether the model has improved.

[0166] Once one or more trained machine learning models 838 are generated, they can be stored

[0167] For the model application workflow 817, according to one embodiment, input data 862 may be input

[0168] In some embodiments, input data 862 may be provided to a chamber quality index generator 870 for

[0169] In some embodiments, input data 862 may be provided to performance matching model 874. Performance Matching

[0170] In some embodiments, input data 862 may be provided to a corrective action predictor 878.

[0171] Fig. 9 An example computing device operating in accordance with one or more aspects of the present disclosure is described.

[0172] The example computing device 900 can be connected to other networks in a LAN, an internal network, an external network, and / or the Internet.

[0173] The example computing device 900 may include processing devices 902 that may communicate with each other via a bus 930.

[0174] Processing device 902 represents one or more general-purpose processing devices, such as a microprocessor, a central processing unit, or a processor.

[0175] The example computing device 900 may further include a network interface device 908 that can communicate with a network 920

[0176] The data storage device 918 may include a computer-readable storage medium (or more specifically, a non-

[0177] The executable instructions 922 may also be completely executed during execution of the instructions by the example computing device 900.

[0178] Despite Fig. 9 The computer readable storage medium 928 is shown as a single medium, but the term

[0179] Some portions of the above detailed description are presented in terms of algorithms and operations on data bits within a computer memory.

[0180] It should be borne in mind, however, that all of these and similar terms are to be associated with the appropriate physical quantities.

[0181] Examples of the present disclosure also relate to an apparatus for performing the methods described herein.

[0182] The foregoing description sets forth numerous specific details such as examples of specific systems, components, methods, etc.

[0183] The "one / a" embodiment mentioned throughout this specification means that

[0184] Although the operations of the methods herein are shown and described in a particular order, they may be altered.

[0185] It should be understood that the above description is intended to be illustrative, and not restrictive.

Claims

1. A method comprising: By the processing device, receiving first sensor data indicating a state of a wall corresponding to a first processing chamber The processing device determines a first value based on the first sensor data, the first value being determining, by the processing device, a The processing device performs one or more of the following: (i) preparing a notification indicating the first update; 2. The method of claim 1, wherein the first sensor data is from an optical wall The processing device determines, based on the first value, to increase the value of the sensor corresponding to the OWPS.

3. The method of claim 1, wherein the first value is set along the surface By the processing device, based on the first sensor data a second value, wherein the second value is The processing device determines, using the first value and the second value, 4. The method of claim 3, wherein the first update is associated with the first process operation.

5. The method of claim 3, wherein the process rate or the endpoint condition is 6. The method of claim 1, wherein the first value indicates the 7. The method of claim 1, further comprising: receiving, by the processing device, a second state of a second wall corresponding to a second processing chamber; determining, by the processing device, a second value based on the second sensor data, wherein the second Wherein the first update is further determined using the second value.

8. The method of claim 7, further comprising: by the processing device, causing execution of a comparison based on a comparison between the first value and the second value 9. The method of claim 1, further comprising: By the processing device, using the first sensor data to perform data normalization to determine the 10. The method of claim 1, further comprising: The processing device uses the first sensor data as a basis for processing a machine learning (ML) model. The processing device receives one or more outputs of the ML model, wherein the one or more 11. A system comprising: A processing chamber comprising a first wall having an inner surface positioned within the processing chamber An optical sensor is coupled to the processing chamber, wherein the optical sensor is configured to obtain Memory; as well as A processing device is coupled to the memory, and the processing device is configured to: receiving first sensor data indicating a state of a wall corresponding to a first processing chamber, A first value is determined based on the first sensor data, the first value being related to a Determining a first process operation associated with the first processing chamber based on the first value Perform one or more of the following: (i) prepare a notification indicating the first update to be displayed to the graphical user; 12. The system of claim 11, wherein the first sensor data is from an optical Determine a sensor gain value or a sensor offset corresponding to the OWPS based on the first value 13. The system of claim 11, wherein the first value is related to a A second value is determined based on the first sensor data, wherein the second value is related to a Determine a process speed associated with the first process operation using the first value and the second value.

14. The system of claim 11, wherein the first value indicates a 15. The system of claim 11, wherein the processing device is further configured to: receiving second sensor data indicating a second state of a second wall corresponding to a second processing chamber, A second value is determined based on the second sensor data, wherein the second value is related to the Wherein the first update is further determined using the second value.

16. A non-transitory machine-readable storage medium storing instructions, wherein the instructions receiving first sensor data indicating a state of a wall corresponding to a first processing chamber, the first A first value is determined based on the first sensor data, the first value being related to a surface along the wall Determining a first process operation associated with the first processing chamber based on the first value Perform one or more of the following: (i) prepare a notification indicating the first update to be displayed in a graphical user interface; 17. The non-transitory machine-readable storage medium of claim 16, wherein the Determine a sensor gain value or a sensor offset corresponding to the OWPS based on the first value 18. The non-transitory machine-readable storage medium of claim 17, wherein the A second value is determined based on the first sensor data, wherein the second value is related to a Determine a process speed associated with the first process operation using the first value and the second value.

19. The non-transitory machine-readable storage medium of claim 16, wherein the receiving second sensor data indicating a second state of a second wall corresponding to a second processing chamber, A second value is determined based on the second sensor data, wherein the second value is related to the Wherein the first update is further determined using the second value.

20. The non-transitory machine-readable storage medium of claim 16, wherein the using the first sensor data as input to an ML model; and receiving one or more outputs of the ML model, the one or more outputs indicating the first

Images