US 11,791,224 B2
Technique for training neural network for use in in-situ monitoring during polishing and polishing system
Kun Xu, Sunol, CA (US); Kiran Lall Shrestha, San Jose, CA (US); Doyle E. Bennett, Santa Clara, CA (US); David Maxwell Gage, Sunnyvale, CA (US); Benjamin Cherian, San Jose, CA (US); Jun Qian, Sunnyvale, CA (US); and Harry Q. Lee, Los Altos, CA (US)
Assigned to Applied Materials, Inc., Santa Clara, CA (US)
Filed by Applied Materials, Inc., Santa Clara, CA (US)
Filed on May 11, 2021, as Appl. No. 17/317,232.
Claims priority of provisional application 63/025,108, filed on May 14, 2020.
Prior Publication US 2021/0354265 A1, Nov. 18, 2021
Int. Cl. B24B 37/013 (2012.01); B24B 49/10 (2006.01); G06N 3/08 (2023.01); H01L 21/321 (2006.01); H01L 21/66 (2006.01); H01L 21/304 (2006.01); G06F 17/15 (2006.01)
CPC H01L 22/14 (2013.01) [B24B 37/013 (2013.01); B24B 49/105 (2013.01); G06F 17/15 (2013.01); G06N 3/08 (2013.01); H01L 21/304 (2013.01); H01L 21/3212 (2013.01); H01L 22/12 (2013.01); H01L 22/26 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A computer program product, tangibly embodied in a non-transitory computer readable medium, comprising instructions to cause one or more computers to:
receive from a monitoring system a first set of sensor measurements generated by scanning a sensor of an in-situ monitoring system across a calibration substrate having a conductive layer formed of a first material having a first conductivity;
receive ground truth measurements of a thickness of the conductive layer of the calibrations substrate to provide a first thickness profile;
create a data set including a modified second thickness profile by scaling the first thickness profile based on the first conductivity and a target second conductivity that is greater than the first conductivity, wherein the modified second thickness profile is equivalent to a thickness profile that would be generated if the conductive layer were formed of a second material of the second conductivity, and
train a neural network to convert sensor measurements from the in-situ monitoring system to thickness measurements for a layer formed of the second material, the training performed using training data including the data set including the modified training second thickness profile and calibration thickness values based on the first set of sensor measurements from the conductive layer formed of the first material, such that neural network is trained using training data that is equivalent to thinner layers of higher conductivity.