Grouping spectral data from polishing substrates

Patent metadata

Field	Value
Publication number	US-10012494-B2
Application number	US-201314063740-A
Country	US
Kind code	B2
Filing date	Oct 25, 2013
Priority date	Oct 25, 2013
Publication date	Jul 3, 2018
Grant date	Jul 3, 2018

Abstract

Among other things, a computer-based method is described. The method comprises receiving, by one or more computers, a plurality of measured spectra reflected from a substrate at a plurality of different positions on the substrate. The substrate comprises at least two regions having different structural features. The method also comprises performing, by the one or more computers, a clustering algorithm on the plurality of measured spectra to separate the plurality of measured spectra into a number of groups based on the spectral characteristics of the plurality of measured spectra; selecting one of the number of groups to provide a selected group having a subset of spectra from the plurality of measured spectra; and determining, in the one or more computers, at least one characterizing value for the substrate based on the subset of spectra of the selected group.

First claim

What is claimed is:

1. A computer-based method comprising:
receiving, by one or more computers, a plurality of measured spectra reflected from a substrate at a plurality of different positions on the substrate, the substrate comprising at least two regions having different structural features;
performing, by the one or more computers, a clustering algorithm on the plurality of measured spectra to separate the plurality of measured spectra into a number of groups based on spectral characteristics of the plurality of measured spectra, the number of groups being greater than a number of regions having different structural features expected on the substrate;
selecting one of the number of groups to provide a selected group having a subset of spectra from the plurality of measured spectra;
determining, in the one or more computers, at least one characterizing value for the substrate based on the subset of spectra of the selected group; and
controlling polishing of the substrate based on the characterizing value, wherein controlling polishing of the substrate includes determining a polishing endpoint based on the characterizing value and stopping polishing at the polishing endpoint.

2. The method of claim 1 , wherein the characterizing value is a thickness of an outermost layer of the substrate.

3. The method of claim 1 , wherein the clustering algorithm comprises a k-means clustering algorithm.

4. The method of claim 1 , wherein the plurality of measured spectra are measured with an in-line monitoring system before polishing of the substrate.

5. The method of claim 1 , wherein the plurality of measured spectra are measured with an in-situ monitoring system during polishing of the substrate.

6. A computer program product residing on a computer readable medium, the computer program product comprising instructions for causing a processor to:
receive a plurality of measured spectra reflected from a substrate at a plurality of different positions on the substrate, the substrate comprising at least two regions having different structural features;
perform a clustering algorithm on the plurality of measured spectra to separate the plurality of measured spectra into a number of groups based on spectral characteristics of the plurality of measured spectra, the number of groups being greater than a number of regions having different structural features expected on the substrate;
select one of the number of groups to provide a selected group having a subset of spectra from the plurality of measured spectra;
determine at least one characterizing value for the substrate based on the subset of spectra of the selected group; and
control polishing of the substrate based on the characterizing value, wherein the instructions to control polishing of the substrate comprise instructions to determine a polishing endpoint based on the characterizing value and cause a polishing system to stop polishing at the polishing endpoint.

7. The computer program product of claim 6 , wherein the instructions to perform the clustering algorithm comprise instructions to initialize a centroid for each group.

8. The computer program product of claim 7 , wherein the instructions to initialize the centroid for each group comprise instructions to select a spectrum from the plurality of measured spectra to provide a selected spectrum and set the centroid to have the spectral characteristics of the selected spectrum.

9. The computer program product of claim 8 , wherein the instructions to initialize the centroid for each group comprise instructions to select a pair of spectra from the plurality of measured spectra having a greatest distance metric, set a first centroid to have the spectral characteristics of a first spectrum of the pair of spectra and set a second centroid to have the spectral characteristics of a second spectrum of the pair of spectra.

10. The computer program product of claim 9 , wherein the instructions to select the pair of spectra from the plurality of measured spectra having the greatest distance metric comprise instructions to determine a Euclidian distance between every pair of spectra from the plurality of measured spectra and select a pair of spectra that has the largest Euclidean distance.

11. The computer program product of claim 7 , wherein the instructions to perform the clustering algorithm comprise instructions to assign each spectrum of the received plurality of measured spectra to its nearest, initialized centroid and form multiple groups based on the assignment.

12. The computer program product of claim 11 , wherein the instructions to perform the clustering algorithm comprise instructions to generate a new centroid for each group by averaging the spectra in each group.

13. The computer program product of claim 12 , wherein the instructions to perform the clustering algorithm comprise instructions to reassign each spectrum of the received plurality of measured spectra to its nearest new centroid and form multiple new groups based on the assignment.

14. The computer program product of claim 13 , wherein the instructions to perform the clustering algorithm comprise instructions to iteratively update the new centroids and form new groups until the new centroids converge.

15. The computer program product of claim 7 , wherein the characterizing value is a thickness of an outermost layer of the substrate.

16. A polishing system, comprising:
a support to hold a polishing pad;
a carrier head to hold a substrate comprising at least two regions having different structural features in contact with the polishing pad;
an in-situ optical monitoring system to measure a plurality of measured spectra reflected from the substrate at a plurality of different positions on the substrate; and
a controller configured to
receive the plurality of measured spectra from the in-situ optical monitoring system;
perform a clustering algorithm on the plurality of measured spectra to separate the plurality of measured spectra into a number of groups based on spectral characteristics of the plurality of measured spectra, the number of groups being greater than a number of regions having different structural features expected on the substrate;
select one of the number of groups to provide a selected group having a subset of spectra from the plurality of measured spectra;
determine at least one characterizing value for the substrate based on the subset of spectra of the selected group; and
control polishing of the substrate based on the characterizing value, wherein the controller is configured to determine a polishing endpoint based on the characterizing value and stop polishing at the polishing endpoint.

17. The polishing system of claim 16 , wherein the characterizing value is a thickness of an outermost layer of the substrate.

Assignees

• Applied Materials Inc

Inventors

• David Jeffrey Drue
• Swedek Boguslaw A

Classifications

• H10P74/238

  comprising acting in response to an ongoing measurement without interruption of processing, e.g. endpoint detection or in-situ thickness measurement · CPC title

• H10P74/203

  Structural properties, e.g. testing or measuring thicknesses, line widths, warpage, bond strengths or physical defects · CPC title

• H10P74/23

  characterised by multiple measurements, corrections, marking or sorting processes · CPC title

• G01B11/0625

  with measurement of absorption or reflection · CPC title

• G01B11/06 Primary

  for measuring thickness {; e.g. of sheet material (thickness measurement by thermal means G01B21/085)} · CPC title