US 11,860,973 B2
Method and system for foreline deposition diagnostics and control
Ala Moradian, Sunnyvale, CA (US); Martin A. Hilkene, Gilroy, CA (US); Zuoming Zhu, Sunnyvale, CA (US); Errol Antonio C. Sanchez, Santa Clara, CA (US); Bindusagar Marath Sankarathodi, San Jose, CA (US); Patricia M. Liu, Saratoga, CA (US); and Surendra Singh Srivastava, Santa Clara, CA (US)
Assigned to Applied Materials, Inc., Santa Clara, CA (US)
Filed by Applied Materials, Inc., Santa Clara, CA (US)
Filed on Oct. 27, 2020, as Appl. No. 17/081,459.
Prior Publication US 2022/0129698 A1, Apr. 28, 2022
Int. Cl. G06K 9/62 (2022.01); G06F 18/214 (2023.01); H01L 21/02 (2006.01); G06N 20/00 (2019.01); G06F 18/24 (2023.01)
CPC G06F 18/214 (2023.01) [G06F 18/24 (2023.01); G06N 20/00 (2019.01); H01L 21/0206 (2013.01); H01L 21/02019 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system for foreline diagnostics and control, comprising:
a foreline coupled to an exhaust of a processing chamber;
a sensor positioned to measure deposition build-up in the foreline; and
a build-up monitor coupled to the first sensor, the build-up monitor comprising a trained machine learning (ML) model and configured to generate an output indicating deposition build-up and trigger a corrective action when the indicated deposition build-up is at or above a build-up threshold, wherein the trained ML model is trained via a process comprising:
receiving sensor training data from a database comprising sensor data from prior operation of a semiconductor processing chamber;
classifying the sensor training data to differentiate between a clean surface of the foreline and a deposition thickness of a material deposited on the foreline; and
generating model parameters for the trained machine learning model based on the classifying.