公开(公告)号：US20240111221A1

公开(公告)日：2024-04-04

申请号：US18275663

申请日：2022-01-12

Applicant: ASML NETHERLANDS B.V.

Inventor： Hendrik Adriaan VAN LAARHOVEN ,  Bastiaan Maurice VAN DEN BROEK ,  Vito Daniele RUTIGLIANI

IPC: G03F7/00

CPC classification number: G03F7/706841 ,  G03F7/70633 ,  G03F7/706831

Abstract: A method of determining a measurement recipe for measurement of in-die targets located within one or more die areas of an exposure field. The method includes obtaining first measurement data relating to measurement of a plurality of reference targets and second measurement data relating to measurement of a plurality of in-die targets, the targets having respective different overlay biases and measured using a plurality of different acquisition settings for acquiring the measurement data. One or more machine learning models are trained using the first measurement data to obtain a plurality of candidate measurement recipes, wherein the candidate measurement recipes include a plurality of combinations of a trained machine learned model and a corresponding acquisition setting; and a preferred measurement recipe is determined from the candidate measurement recipes using the second measurement data.

公开(公告)号：US20240354552A1

公开(公告)日：2024-10-24

申请号：US18259344

申请日：2021-12-20

Applicant: ASML Netherlands B.V.

Inventor： Alexandru ONOSE ,  Bart Jacobus Martinus TIEMERSMA ,  Nick VERHEUL ,  Remco DIRKS ,  Davide BARBIERI ,  Hendrik Adriaan VAN LAARHOVEN

IPC: G06N3/0455

CPC classification number: G06N3/0455

Abstract: A modular autoencoder model is described. The modular autoencoder model comprises input models configured to process one or more inputs to a first level of dimensionality suitable for combination with other inputs: a common model configured to: reduce a dimensionality of combined processed inputs to generate low dimensional data in a latent space; and expand the low dimensional data in the latent space into one or more expanded versions of the one or more inputs suitable for generating one or more different outputs; output models configured to use the one or more expanded versions of the one or more inputs to generate the one or more different outputs, the one or more different outputs being approximations of the one or more inputs; and a prediction model configured to estimate one or more parameters based on the low dimensional data in the latent space.

公开(公告)号：US20240004309A1

公开(公告)日：2024-01-04

申请号：US18039712

申请日：2021-12-06

Applicant: ASML NETHERLANDS B.V.

Inventor： Hendrik Adriaan VAN LAARHOVEN ,  Alok VERMA ,  Roy ANUNCIADO ,  Hermanus Adrianus DILLEN ,  Stefan Cornelis Theodorus VAN DER SANDEN

IPC: G03F7/00 ,  H01L21/66

CPC classification number: G03F7/70625 ,  G03F7/70633 ,  H01L22/12 ,  H01L22/20

Abstract: A method of monitoring a semiconductor manufacturing process. The method includes obtaining at least one first trained model being operable to derive local performance parameter data from high resolution metrology data, wherein the local performance parameter data describes a local component, or one or more local contributors thereto, of a performance metric and high resolution metrology data relating to at least one substrate having been subject to at least a part of the semiconductor manufacturing process. Local performance parameter data is determined from the high resolution metrology data using the first trained model. The first trained model is operable to determine the local performance parameter data as if it had been subject to an etch step on at least the immediately prior exposed layer, based on the high resolution metrology data including only metrology data performed prior to any such etch step.