System implementing machine learning in complex multivariate wafer processing equipment
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
H01J-037/32
H01L-021/3065
H01L-021/67
출원번호
15967541
(2018-04-30)
등록번호
10615009
(2020-04-07)
발명자
/ 주소
Guha, Joydeep
Daugherty, John
Vahedi, Vahid
Gottscho, Richard Alan
출원인 / 주소
Lam Research Corporation
대리인 / 주소
Penilla IP, APC
인용정보
피인용 횟수 :
0인용 특허 :
0
초록▼
A system for controlling processing state of a plasma process is provided. One example system includes a plasma reactor having a plurality of tuning knobs for making settings to operational conditions of the plasma reactor. A plurality of sensors of the plasma reactor is included, where each of the
A system for controlling processing state of a plasma process is provided. One example system includes a plasma reactor having a plurality of tuning knobs for making settings to operational conditions of the plasma reactor. A plurality of sensors of the plasma reactor is included, where each of the plurality of sensors is configured to produce a data stream of information during operation of the plasma reactor for carrying out the plasma process. A controller of the plasma reactor is configured to execute a multivariate processing that is configured to use as input desired processing state values that define intended measurable conditions within a processing environment of the plasma reactor and identify current plasma processing values. The multivariate processing uses a machine learning engine that receives as inputs the desired processing state values and data streams from the plurality of sensors during processing of the plasma process. The machine learning engine is configured to identify current processing state values used to produce a compensation vector, such that the compensation vector defines differences between the desired process state values and the current processing state values. The controller is further configured to execute a compensation processing operation that transforms the compensation vector expressed in terms of measured conditions within the processing environment to changes of specific one or more of the tuning knobs of the plasma reactor.
대표청구항▼
1. A system for controlling processing state of a plasma process, comprising: a plasma reactor having a plurality of tuning knobs for making settings to operational conditions of the plasma reactor;a plurality of sensors of the plasma reactor, each of the plurality of sensors is configured to produc
1. A system for controlling processing state of a plasma process, comprising: a plasma reactor having a plurality of tuning knobs for making settings to operational conditions of the plasma reactor;a plurality of sensors of the plasma reactor, each of the plurality of sensors is configured to produce a data stream of information during operation of the plasma reactor for carrying out the plasma process; anda controller of the plasma reactor is configured to execute a multivariate processing that is configured to use as input desired processing state values that define intended measurable conditions within a processing environment of the plasma reactor and identify current plasma processing values, the multivariate processing using a machine learning engine that receives as inputs the desired processing state values and data streams from the plurality of sensors during processing of the plasma process, and the machine learning engine is configured to identify current processing state values used to produce a compensation vector, such that the compensation vector defines differences between the desired processing state values and the current processing state values;wherein the controller is further configured to execute a compensation processing operation that transforms the compensation vector expressed in terms of measured conditions within the processing environment to changes of specific one or more of the tuning knobs of the plasma reactor. 2. The system of claim 1, wherein the controller is further configured to generate changes for the tuning knobs of the plasma reactor to cause a change in the measurable conditions of the processing environment of the reactor. 3. The system of claim 1, wherein the machine learning engine is configured to periodically receive measured substrate performance data regarding one or both of etch rate measurements or monitor wafer measurements, the measured substrate performance data is used to make adjustments to the desired processing state values, which in turn cause adjustments to the compensation vector and the changes to said one or more of the tuning knobs. 4. The system of claim 3, wherein the machine learning engine is configured to perform verification of the current processing state values with real data obtained from one or both of etch rate measurements or monitor wafer measurements. 5. The system of claim 1, wherein the machine learning engine further receives sensitivity data regarding sensor signals to compensation of tuning knobs. 6. The system of claim 1, wherein the machine learning engine further receives reactor wall surface dynamics for use by a phenomenological model that defines plasma dynamics within the processing environment in terms of said data streams produced by said plurality of sensors of the plasma reactor. 7. The system of claim 1, wherein the system is configured to be executed in one or more operational phases, wherein one operational phase includes, during plasma reactor seasoning phase that uses non-production substrates, the plasma reactor seasoning phase being monitored by the controller by executing the multivariate processing to identify when the current processing state values are within a bound that enables adjustment of the tuning knobs to place the plasma reactor in a state that is ready for processing production substrates and enables discontinuing of the plasma reactor seasoning phase. 8. The system of claim 1, wherein the system is configured to be executed in one or more operational phases, wherein one operational phase includes, during a production phase that uses production substrates, the controller executes the multivariate processing to identify when the current processing state values are within a bound that enables adjustment of the tuning knobs to compensate for drift in the plasma process. 9. The system of claim 8, wherein the compensation for drift occurs multiple times during said production phase, and the adjustments in the tuning knobs are calculated to move the processing environment closer to the desired processing state values as measured by the plurality of sensors. 10. A system for controlling processing state of a plasma process, comprising: a plasma reactor having a plurality of tuning knobs for making settings to operational conditions of the plasma reactor;a plurality of sensors of the plasma reactor, each of the plurality of sensors is configured to produce a data stream of information during operation of the plasma reactor for carrying out the plasma process; anda controller of the plasma reactor is configured to execute a multivariate processing that is configured to use as input desired processing state values that define intended measurable conditions within a processing environment of the plasma reactor and identify current plasma processing values, the multivariate processing uses a machine learning engine that takes as inputs, the desired processing state values, data streams from the plurality of sensors during processing of the plasma process, and sensitivity data regarding sensor signals to compensation of tuning knobs, and the machine learning engine is configured to identify current processing state values used to produce a compensation vector,wherein the compensation vector identifies differences between the desired process state values and the current processing state values. 11. The system of claim 10, wherein the controller is further configured to execute a compensation processing operation that transforms the compensation vector expressed in terms of measured conditions within the processing environment to changes of specific one or more of the tuning knobs of the plasma reactor. 12. The system of claim 11, wherein the controller is further configured to instruct changes to one or more of the tuning knobs of the plasma reactor to cause a change in the measurable conditions of the processing environment of the reactor. 13. The system of claim 10, wherein the machine learning engine is configured to periodically receive measured substrate performance data regarding one or both of etch rate measurements or monitor wafer measurements. 14. They system of claim 13, wherein a metrology tool is used to measure substrate performance data from one or more substrates processed by the plasma reactor. 15. The system of claim 10, wherein the system is configured to be executed in one or more operational phases, wherein one operational phase includes, during plasma reactor seasoning phase that uses non-production substrates, the plasma reactor seasoning phase being monitored by the controller by executing the multivariate processing to identify when the current processing state values are within a bound that enables adjustment of the tuning knobs to place the plasma reactor in a state that is ready for processing production substrates and enables discontinuing of the plasma reactor seasoning phase. 16. The system of claim 10, wherein the system is configured to be executed in one or more operational phases, wherein one operational phase includes, during a production phase that uses production substrates, the controller executes the multivariate processing to identify when the current processing state values are within a bound that enables adjustment of the tuning knobs to compensate for drift in the plasma process.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.