Back to results
US 12,181,271 B2Granted
Estimating in-die overlay with tool induced shift correction
AssigneeKLA Corporation
InventorsMin-Yeong Moon, Stilian Pandev, Dimitry Sanko
Life of this patent
Estimating the term…
Abstract
A metrology module includes an estimation model that is configured to provide an estimation of independent overlay with tool induced shift on received wafers based on only one azimuth angle spectra. The estimation model can use at least one machine learning algorithm. The estimation model can be derived by the machine learning algorithm applied to calculated training data based on a first training sample set from initial metrology measurements and an additional tool induced shift training sample.
Claims22
A method comprising:
- determining a first training sample set from initial metrology measurements, wherein the initial metrology measurements include spectra at two azimuthal angles and, optionally, skew;
- preparing an additional tool induced shift training sample by adding a negative value of reference on opposite azimuth angle data from the first training sample set;
- stacking original azimuth angle data from the first training sample set and the opposite angle data in a second training sample set;
- applying at least one machine learning algorithm to the first training sample set and the second training sample set to derive an estimation model;
- obtaining independent overlay with tool induced shift correction embedded at inline wafers collected for spectra at only one azimuthal angle;
- and
- using the estimation model to provide estimations of independent overlay with tool induced shift.
4 more elements
A system comprising:
- a metrology module that includes a processor, wherein the metrology module comprises an estimation model configured to provide an estimation of independent overlay with tool induced shift on received wafers, wherein the estimation model uses at least one machine learning algorithm, and wherein the estimation is based on only one azimuth angle spectra and the estimation model is based on spectra at two azimuthal angles;
- wherein the estimation model is derived by the machine learning algorithm applied to calculated training data based on a first training sample set from initial metrology measurements and an additional tool induced shift training sample, wherein the initial metrology measurements include the spectra at two azimuthal angles and, optionally, skew, and wherein the additional tool induced shift training sample is at opposite azimuth angle data from the first training sample set with a negative value of reference.
Dependencies are inferred from the claim text.