公开(公告)号：US20210165399A1

公开(公告)日：2021-06-03

申请号：US17174159

申请日：2021-02-11

Applicant: ASML NETHERLANDS B.V.

Inventor： Sarathi ROY ,  Edo Maria HULSEBOS ,  Roy WERKMAN ,  Junru RUAN

IPC: G05B19/418 ,  G06N3/04 ,  G03F7/20 ,  G05B13/02

Abstract: A method for configuring a semiconductor manufacturing process, the method including: obtaining a first value of a first parameter based on measurements associated with a first operation of a process step in the semiconductor manufacturing process and a first sampling scheme; using a recurrent neural network to determine a predicted value of the first parameter based on the first value; and using the predicted value of the first parameter in configuring a subsequent operation of the process step in the semiconductor manufacturing process.

公开(公告)号：US20240345569A1

公开(公告)日：2024-10-17

申请号：US18674537

申请日：2024-05-24

Applicant: ASML NETHERLANDS B.V.

Inventor： Sarathi ROY ,  Edo Maria HULSEBOS ,  Roy WERKMAN ,  Junru RUAN

IPC: G05B19/418 ,  G03F7/00 ,  G05B13/02 ,  G06N3/044

CPC classification number: G05B19/41875 ,  G03F7/70508 ,  G03F7/70525 ,  G05B13/027 ,  G05B19/41885 ,  G06N3/044 ,  G05B2219/33025 ,  G05B2219/45028 ,  G05B2219/45031

Abstract: A method for configuring a semiconductor manufacturing process, the method including: obtaining a first value of a first parameter based on measurements associated with a first operation of a process step in the semiconductor manufacturing process and a first sampling scheme; using a recurrent neural network to determine a predicted value of the first parameter based on the first value; and using the predicted value of the first parameter in configuring a subsequent operation of the process step in the semiconductor manufacturing process.

公开(公告)号：US20210333785A1

公开(公告)日：2021-10-28

申请号：US17367901

申请日：2021-07-06

Applicant: ASML NETHERLANDS B.V.

Inventor： Sarathi ROY ,  Edo Maria HULSEBOS ,  Roy WERKMAN ,  Junru RUAN

IPC: G05B19/418 ,  G03F7/20 ,  G05B13/02 ,  G06N3/04

Abstract: A method for configuring a semiconductor manufacturing process, the method including: obtaining a first value of a first parameter based on measurements associated with a first operation of a process step in the semiconductor manufacturing process and a first sampling scheme; using a recurrent neural network to determine a predicted value of the first parameter based on the first value; and using the predicted value of the first parameter in configuring a subsequent operation of the process step in the semiconductor manufacturing process.

公开(公告)号：US20240402617A1

公开(公告)日：2024-12-05

申请号：US18799534

申请日：2024-08-09

Applicant: ASML Netherlands B.V.

Inventor： Spencer ALEXANDER ,  Junru RUAN ,  Haiyan LI ,  Nathan Richard KEECH ,  Huai-Ying CHIN

IPC: G03F7/00

Abstract: In some embodiments, one or more non-transitory, machine-readable medium has instructions thereon, the instructions when executed by a processor being configured to perform operations comprising obtaining scanning electron microscopy (SEM) metrology data for first areas on a training wafer, obtaining optical metrology data for second areas on the training wafer, and training a model, by using the SEM metrology data and the optical metrology data for the training wafer, to generate parameters for features on a production wafer based on optical metrology data for areas of the production wafer.

公开(公告)号：US20240212125A1

公开(公告)日：2024-06-27

申请号：US18596323

申请日：2024-03-05

Applicant: ASML Netherlands B.V.

Inventor： Junru RUAN ,  Haiyan LI

IPC: G06T7/00 ,  G06T7/60

CPC classification number: G06T7/0004 ,  G06T7/60 ,  G06T2207/10061 ,  G06T2207/30144 ,  G06T2207/30148

Abstract: A method of obtaining focus and dose data that requires no special marks and that uses images of in-die features is described. A focus/dose matrix wafer is created. Dimensions such as critical dimension (CD), CD uniformity (CDU), edge placement error (EPE), etc., at in-die locations are measured using a charged particle inspection system having a large field of view. Machine learning or regression methods are used to determine a relationship between focus and dose and the measured data. The same dimensions can then be measured on a production wafer and the relationship can be utilized to determine the focus and dose for the production wafer.