Method and system for identifying a clean endpoint time for a chamber

Patent metadata

Field	Value
Publication number	US-10309013-B2
Application number	US-201414208688-A
Country	US
Kind code	B2
Filing date	Mar 13, 2014
Priority date	Mar 15, 2013
Publication date	Jun 4, 2019
Grant date	Jun 4, 2019

Abstract

Systems and methods are provided for determining a clean endpoint time for a current run of a chamber. The clean endpoint time for the current run may be determined by determining that a chamber parameter, such as a chamber pressure, has stabilized. Historical clean endpoint time data is updated by adding the clean endpoint time for the current run of the chamber. A recommended clean endpoint time is then determined for the chamber based on the updated historical clean endpoint time data.

First claim

What is claimed is:

1. A method comprising:
determining, by a processing device, a clean endpoint time for a current run of a chamber by determining that a chamber pressure of the current run has stabilized;
retrieving, by the processing device, historical clean endpoint time data that is based on tracking of a time evolution profile of the chamber pressure during chamber cleaning over a historical period;
updating, by the processing device, the historical clean endpoint time data by adding the clean endpoint time for the current run of the chamber to the historical clean endpoint time data;
computing, by the processing device, a recommended clean endpoint time for the chamber to minimize an effect of run-to-run fluctuation of the chamber pressure over the historical period, wherein the recommended clean endpoint time for the chamber is computed based on the updated historical clean endpoint time data using a subset of the updated historical clean endpoint time data, the subset corresponding to a time window that comprises the clean endpoint time for the current run; and
causing the current run of the chamber to end at the recommended clean endpoint time for the chamber.

2. The method of claim 1 , wherein determining that the chamber pressure of the current run of the chamber has stabilized comprises:
computing an average value of the chamber pressure for each of a plurality of time windows, wherein each of the plurality of time windows corresponds to a time period during the current run; and
computing a plurality of delta values, wherein each delta value corresponds to two windows of the plurality of windows that are adjacent to each other in time.

3. The method of claim 2 , wherein determining that the chamber pressure of the current run of the chamber has stabilized further comprises:
comparing each of the plurality of delta values to a threshold delta value to identify a time window indicative of a stabilized chamber pressure, wherein the identified time window corresponds to the recommended clean endpoint time.

4. The method of claim 1 , wherein determining the recommended clean endpoint time for the chamber based on the updated historical clean endpoint time data comprises:
determining a noise distribution in the updated historical clean endpoint time data;
and filtering out the noise in the updated historical clean endpoint time data based on the identified noise distribution.

5. The method of claim 1 , further comprising:
transmitting the recommended clean endpoint time to a device of a network.

6. A system comprising:
a memory to store historical clean endpoint time data that is based on tracking a time evolution profile of the chamber pressure during chamber cleaning over a historical period; and a processing device, coupled to the memory, to:
determine a clean endpoint time for a current run of a chamber by determining that a chamber pressure of the current run has stabilized;
retrieve the stored historical clean endpoint time data;
update the historical clean endpoint time data by adding the clean endpoint time for the current run of the chamber to the historical clean endpoint time data;
compute a recommended clean endpoint time for the chamber to minimize an effect of run-to-run fluctuation of the chamber pressure over the historical period, wherein the recommended clean endpoint time for the chamber is computed based on the updated historical clean endpoint time data using a subset of the updated historical clean endpoint time data, the subset corresponding to a time window that comprises the clean endpoint time for the current run; and
cause the current run of the chamber to end at the recommended clean endpoint time for the chamber.

7. The system of claim 6 , wherein determining that the chamber pressure of the current run of the chamber has stabilized comprises:
computing an average value of the chamber pressure for each of a plurality of time windows, wherein each of the plurality of time windows corresponds to a time period during the current run; and
computing a plurality of delta values, wherein each delta value corresponds to two windows of the plurality of windows that are adjacent to each other in time.

8. The system of claim 7 , wherein determining that the chamber pressure of the current run of the chamber has stabilized further comprises:
comparing each of the plurality of delta values to a threshold delta value to identify a time window indicative of a stabilized chamber pressure, wherein the identified time window corresponds to the recommended clean endpoint time.

9. The system of claim 6 , wherein determining the recommended clean endpoint time for the chamber based on the updated historical clean endpoint time data comprises:
determining a noise distribution in the updated historical clean endpoint time data; and filtering out the noise in the updated historical clean endpoint time data based on the identified noise distribution.

10. The system of claim 6 , wherein the processing device is further to: transmit the recommended clean endpoint time to a device of a network.

11. A non-transitory computer-readable storage medium storing instructions which, when executed, cause a processing device to perform the operations of:
determining, by a processing device, a clean endpoint time for a current run of a chamber by determining that a chamber pressure of the current run has stabilized;
retrieving, by the processing device, historical clean endpoint time data that is based on tracking of a time evolution profile of the chamber pressure during chamber cleaning over a historical period;
updating, by the processing device, the historical clean endpoint time data by adding the clean endpoint time for the current run of the chamber to the historical clean endpoint time data;
computing, by the processing device, a recommended clean endpoint time for the chamber to minimize an effect of run-to-run fluctuation of the chamber pressure over the historical period, wherein the recommended clean endpoint time for the chamber is computed based on the updated historical clean endpoint time data using a subset of the updated historical clean endpoint time data, the subset corresponding to a time window that comprises the clean endpoint time for the current run; and
causing the current run of the chamber to end at the recommended clean endpoint time for the chamber.

12. The non-transitory computer-readable storage medium of claim 11 , wherein determining that the chamber pressure of the current run of the chamber has stabilized comprises:
computing an average value of the chamber pressure for each of a plurality of time windows, wherein each of the plurality of time windows corresponds to a time period during the current run; and
computing a plurality of delta values, wherein each delta value corresponds to two windows of the plurality of windows that are adjacent to each other in time.

13. The non-transitory computer-readable storage medium of claim 12 , wherein determining that the chamber pressure of the current run of the chamber has stabilized further comprises:
comparing each of the plurality of delta values to a threshold delta value to identify a time window indicative of a stabilized chamber pressure, wherein the identified time window corresponds to the recommended clean endpoint time.

14. The non-transitory computer-readable storage medium of claim 11 , wherein determining the recommended clean endpoint time for the chamber based on the updated historical clean endpoint time data comprises:
determining a noise distribution in the updated historical clean endpoint time data; an

Assignees

• Applied Materials Inc

Inventors

• Iliopoulos Ilias
• Na Shuo
• Albor Jose

Classifications

• C23C16/4405 Primary

  Cleaning of reactor or parts inside the reactor by using reactive gases · CPC title

• B08B13/00

  Accessories or details of general applicability for machines or apparatus for cleaning · CPC title