Search

JP-7855713-B2 - Synthetic time series data related to processing equipment

JP7855713B2JP 7855713 B2JP7855713 B2JP 7855713B2JP-7855713-B2

Inventors

  • マーハー ジョシュア トマス

Assignees

  • アプライド マテリアルズ インコーポレイテッド

Dates

Publication Date
20260508
Application Date
20230303
Priority Date
20220307

Claims (20)

  1. A method performed by a computer, To provide random or pseudo-random inputs to a first trained machine learning model trained to generate synthetic sensor time-series data for a processing chamber, A method comprising providing a first trained machine learning model with first data indicating one or more attributes of target synthetic sensor time series data, and receiving an output from the first trained machine learning model, wherein the output includes synthetic sensor time series data associated with the processing chamber, and the output is generated taking into account the first data indicating one or more attributes.
  2. Further including training the first machine learning model, training the model The first machine learning model generates synthetic sensor time-series data. The aforementioned synthesized sensor time-series data is provided to a second machine learning model. The measured sensor time series data is provided to the second machine learning model, wherein the second machine learning model is configured to distinguish between the synthesized sensor time series data and the measured sensor time series data. The method according to claim 1, comprising: providing the first machine learning model with feedback data indicating how accurately the second machine learning model distinguished the synthetic sensor time series data from the measured sensor time series data; and updating the first machine learning model so that the second machine learning model generates synthetic sensor time series data that distinguishes from the measured sensor time series data with less accuracy.
  3. The method according to claim 1, wherein the first trained machine learning model includes a generator of a generative adversarial network.
  4. The method according to claim 1, wherein the first trained machine learning model includes a recurrent neural network model.
  5. The aforementioned composite sensor time-series data, Power, voltage, or current supplied to the components of the processing chamber, The method according to claim 1, comprising data corresponding to one or more of pressure or temperature.
  6. Further including training a second machine learning model, training the said second machine learning model The output composite sensor time series data is provided to the second machine learning model as training input, and the first data indicating one or more attributes related to the output composite sensor time series data is provided to the second machine learning model as target output. The method according to claim 1, comprising providing the second machine learning model configured to predict the attributes of the processing chamber based on measured sensor time-series data of the processing chamber.
  7. The method according to claim 6, wherein the second machine learning model is configured to detect one or more anomalies related to the measured sensor time-series data of the processing chamber.
  8. The attributes of the target composite sensor time series data are, Time since the installation of the processing chamber, The method according to claim 1, comprising one or more of the time since the previous maintenance event in the processing chamber, or defects present in the processing chamber.
  9. A system including memory and a processing device coupled to the memory, wherein the processing device is The objective is to provide a first trained machine learning model with random or pseudo-random inputs, wherein the first trained machine learning model is trained to generate synthetic sensor time-series data for a processing chamber. A system configured to perform the following: provide a first trained machine learning model with first data indicating one or more attributes of target synthetic sensor time series data; and receive an output from the first trained machine learning model, wherein the output includes synthetic sensor time series data associated with the processing chamber, and the output is generated taking into account the first data indicating one or more attributes.
  10. The aforementioned processing device further, It is configured to train the first machine learning model, and training the model is The first machine learning model generates synthetic sensor time-series data. The aforementioned synthesized sensor time-series data is provided to a second machine learning model. The measured sensor time series data is provided to the second machine learning model, wherein the second machine learning model is configured to distinguish between the synthesized sensor time series data and the measured sensor time series data. The system according to claim 9, comprising: providing the first machine learning model with feedback data indicating how accurately the second machine learning model distinguished the synthetic sensor time series data from the measured sensor time series data; and updating the first machine learning model so that the second machine learning model generates synthetic sensor time series data that distinguishes from the measured sensor time series data with less accuracy.
  11. The system according to claim 9, wherein the first trained machine learning model includes a generator of a generative adversarial network.
  12. The system according to claim 9, wherein the first trained machine learning model includes a recurrent neural network model.
  13. The aforementioned composite sensor time-series data, High-frequency plasma generation components, Power, voltage, or current supplied to one or more of the heating device or substrate support, The system according to claim 9, comprising data corresponding to one or more of pressure or temperature.
  14. The aforementioned processing device further, It is configured to train a second machine learning model, and training the said second machine learning model is The system according to claim 9, comprising providing the output composite sensor time series data as training input to the second machine learning model, and providing the second machine learning model as target output a first data indicating one or more attributes related to the output composite sensor time series data, wherein the second machine learning model is configured to predict the attributes of the processing chamber based on the measured sensor time series data of the processing chamber.
  15. The system according to claim 14, wherein the second machine learning model is configured to detect one or more anomalies related to the measured sensor time-series data of the processing chamber.
  16. The attributes of the target composite sensor time series data are, Time since the installation of the processing chamber, The system according to claim 9, comprising one or more of the following: the time since the previous maintenance event in the processing chamber, or defects present in the processing chamber.
  17. A non-temporary machine- readable storage medium storing instructions, wherein when the instructions are executed, To provide random or pseudo-random inputs to a first trained machine learning model trained to generate synthetic sensor time-series data for a processing chamber, A non-temporary machine-readable storage medium that causes a processing device to perform an operation including providing a first trained machine learning model with first data indicating one or more attributes of target synthetic sensor time series data, and receiving an output from the first trained machine learning model, wherein the output includes synthetic sensor time series data associated with the processing chamber and is generated taking into account the first data indicating one or more attributes.
  18. The aforementioned operation, Further including training the first machine learning model, training the model The first machine learning model generates synthetic sensor time-series data. The aforementioned synthesized sensor time-series data is provided to a second machine learning model. The measured sensor time series data is provided to the second machine learning model, wherein the second machine learning model is configured to distinguish between the synthesized sensor time series data and the measured sensor time series data. A non-temporal machine-readable storage medium according to claim 17, comprising: providing the first machine learning model with feedback data indicating how accurately the second machine learning model distinguished synthetic sensor time series data from measured sensor time series data; and updating the first machine learning model so that the second machine learning model generates synthetic sensor time series data that distinguishes from measured sensor time series data with less accuracy.
  19. The attributes of the target composite sensor time series data are, The time elapsed since the installation of the processing chamber, The non-temporary machine-readable storage medium according to claim 17, comprising one or more of the time elapsed since a previous maintenance event in the processing chamber, or defects present in the processing chamber.
  20. The aforementioned operation, Further including training a second machine learning model, training the said second machine learning model A non-temporary machine-readable storage medium according to claim 17, comprising providing the output composite sensor time series data as training input to the second machine learning model, and providing the second machine learning model as target output a first data indicating one or more attributes related to the output composite sensor time series data, wherein the second machine learning model is configured to predict the attributes of the processing chamber based on the measured sensor time series data of the processing chamber.

Description

This disclosure relates to methods related to machine learning models. More specifically, this disclosure relates to methods for generating and utilizing synthetic data using machine learning models related to processing equipment. Products may be produced by executing one or more manufacturing processes using manufacturing equipment. For example, semiconductor manufacturing equipment may be used to produce substrates through semiconductor manufacturing processes. Products are produced so that specific characteristics are suitable for the target application. Machine learning models are used for various process control and predictive functions related to manufacturing equipment. Machine learning models are trained using data related to manufacturing equipment. The following is a simplified summary of the Disclosure to provide a basic understanding of some aspects of the Disclosure. This summary is not intended to provide a comprehensive overview of the Disclosure. It is not intended to identify key or critically important elements of the Disclosure, nor is it intended to limit the scope of any particular embodiment or claim of the Disclosure. The sole purpose of this summary is to provide a simplified overview of some of the ideas of the Disclosure as a prelude to the more detailed description that follows. The method includes providing random or pseudo-random inputs to a first trained machine learning model trained to generate synthetic sensor time-series data for a processing chamber. The method further includes providing the first trained machine learning model with first data indicating one or more attributes of the target synthetic sensor time-series data. The method further includes receiving an output from the first trained machine learning model. This output includes synthetic sensor time-series data associated with the processing chamber. This output is generated considering the first data indicating one or more attributes. In another aspect of this disclosure, a system is disclosed comprising a memory and a processing device coupled to the memory. The processing device is configured to perform an operation. This operation includes providing a first trained machine learning model with random or pseudo-random inputs. The first trained machine learning model is trained to generate synthetic sensor time-series data for a processing chamber. The operation further includes providing the first trained machine learning model with first data indicating one or more attributes of the target synthetic sensor time-series data. The operation further includes receiving an output from the first trained machine learning model. This output includes synthetic sensor time-series data associated with the processing chamber. This output is generated considering the first data indicating one or more attributes. In another embodiment, a non-temporary machine-readable storage medium is disclosed. This non-temporary machine-readable storage medium stores instructions, which, when executed, cause a processing device to perform an operation. This operation includes providing random or pseudo-random inputs to a first trained machine learning model trained to generate synthetic sensor time-series data for a processing chamber. This operation further includes providing the first trained machine learning model with first data indicating one or more attributes of the target synthetic sensor time-series data. This operation further includes receiving an output from the first trained machine learning model. This output includes synthetic sensor time-series data associated with the processing chamber. This output is generated considering the first data indicating one or more attributes. In the attached drawings, this disclosure is shown as an example and is not intended to limit it. This block shows an exemplary system architecture in several embodiments.This is a block diagram of an exemplary dataset generator that generates datasets for a model, according to several embodiments.This is a block diagram of an exemplary dataset generator that generates datasets for a model, according to several embodiments.A block diagram showing a system for generating output data according to several embodiments.This is a flowchart of a method related to generating one or more machine learning models for generating predictive data, according to several embodiments.This is a flowchart of a method related to generating one or more machine learning models for generating predictive data, according to several embodiments.This is a flowchart of a method related to generating one or more machine learning models for generating predictive data, according to several embodiments.This is a block diagram of an exemplary machine learning architecture for generating synthetic data, according to several embodiments.This is a block diagram of an exemplary machine learning architecture for generating synthetic data, according to several embodiments.This is a block di