Method to label substrates based on process parameters

Patent metadata

Field	Value
Publication number	US-12045555-B2
Application number	US-201916960376-A
Country	US
Kind code	B2
Filing date	Jan 22, 2019
Priority date	Jan 31, 2018
Publication date	Jul 23, 2024
Grant date	Jul 23, 2024

Abstract

Substrates to be processed are partitioned based on pre-processing data that is associated with substrates before a process step. The data is partitioned using a partition rule and the substrates are partitioned into subsets in accordance with subsets of the data obtained by the partitioning. Corrections are applied, specific to each subset. The partition rule is obtained using decision tree analysis on a training set of substrates. The decision tree analysis uses pre-processing data associated with the training substrates before they were processed, and post-processing data associated with the training substrates after being subject to the process step. The partition rule that defines the decision tree is selected from a plurality of partition rules based on a characteristic of subsets of the post-processing data. The associated corrections are obtained implicitly at the same time.

First claim

The invention claimed is:

1. A method for partitioning data associated with substrates undergoing a process step of a manufacturing process, the method comprising:
obtaining first data associated with substrates before being subject to the process step of the manufacturing process;
obtaining second data associated with substrates after being subject to the process step of the manufacturing process;
applying a plurality of partition rules to the first data to obtain a plurality of configurations of subsets of the first data, wherein subsets of the second data are associated with the subsets of the first data; and
selecting a partition rule from the plurality of partition rules based on a characteristic of the subsets of the second data.

2. The method of claim 1 , wherein a decision tree training algorithm is utilized to perform the applying the plurality of partition rules and the selecting the partition rule.

3. The method of claim 2 , wherein the training algorithm is a recursive binary decision tree algorithm utilized to perform the applying the plurality of partition rules and the selecting the partition rule.

4. The method of claim 3 , wherein the decision tree algorithm is trained using one or more decision tree training algorithms.

5. The method of claim 2 , further comprising evaluating the training algorithm using cross-validation and selecting parameters of the training algorithm in accordance with the evaluation.

6. The method of claim 1 , further comprising pre-processing the first data to apply a transformation or projection, prior to applying the partition rules.

7. The method of claim 1 , further comprising:
obtaining third data associated with substrates before being subject to a subsequent process step; and
applying a plurality of partition rules to the third data to obtain a plurality of configurations of subsets of the third data, wherein at least one partition rule out of the plurality of partition rules is based on the selected partition rule.

8. The method of claim 7 , wherein the third data is defined as a difference between data associated with substrates before being subject to a subsequent process step and data associated with substrates before being subject to the process step.

9. The method of claim 7 , wherein the third data is one or more selected from: alignment, leveling, and/or context data.

10. A method of partitioning substrates based on data associated with substrates before being subject to a process step, the method comprising:
partitioning the data using a partition rule as selected by the method according to claim 1 ; and
partitioning the substrates into subsets, wherein each subset is associated with a subset of the data obtained by the partitioning.

11. The method of claim 10 , further comprising determining a process control characteristic associated with a subset of the substrates.

12. The method of claim 10 , wherein the partition rule defines a decision tree comprising a succession of decision steps.

13. The method of claim 1 , wherein the first data comprises one or parameters and values associated with the one or more parameters, relating to one or more selected from:
a property of an alignment mark;
a height map of a substrate;
a property of a surface of a substrate;
a setting of a tool utilized for processing substrates before the process step;
identification of a tool utilized for processing substrates before the process step; and/or
a characteristic of a tool utilized for processing substrates before the process step.

14. The method of claim 13 , wherein the partition rule includes at least one decision operation configured to divide the first data based on a value of a parameter comprised within the first data.

15. The method of claim 1 , wherein the second data comprises one or parameters and values associated with the one or more parameters, relating to one or more selected from:
a property of an alignment mark;
a height map of a substrate;
a property of a surface of a substrate;
performance data associated with a feature provided to substrates, the performance data relating to one or more selected from: overlay between layers, overlay between patterns applied by multiple patterning steps in a single layer, focus quality, CD of the feature, edge placement error of the feature, an electrical characteristic of the feature, and/or yield of substrates relating to a relative amount of functioning devices comprising the feature.

16. A computer product comprising a non-transitory computer-readable medium having computer-readable instructions therein, the instructions, upon execution by a computer system, configured to cause the computer system to at least:
obtain first data associated with substrates undergoing a process step of a manufacturing process before being subject to the process step;
obtain second data associated with substrates after being subject to the process step of the manufacturing process;
apply a plurality of partition rules to the first data to obtain a plurality of configurations of subsets of the first data, wherein subsets of the second data are associated with the subsets of the first data; and
select from the plurality of partition rules a partition rule based on a characteristic of the subsets of the second data.

17. The computer product of claim 16 , wherein a decision tree training algorithm is utilized to perform the applying of the plurality of partition rules and the selecting of the partition rule.

18. The computer product of claim 17 , wherein the training algorithm is a recursive binary decision tree algorithm utilized to perform the applying of the plurality of partition rules and the selecting of the partition rule.

19. The computer product of claim 16 , wherein the instructions are further configured to cause the computer system to evaluate the training algorithm using cross-validation and select parameters of the training algorithm in accordance with the evaluation.

20. The computer product of claim 16 , wherein the instructions are further configured to cause the computer system to:
obtain third data associated with substrates before being subject to a subsequent process step; and
apply a plurality of partition rules to the third data to obtain a plurality of configurations of subsets of the third data, wherein at least one partition rule out of the plurality of partition rules is based on the selected partition rule.

21. The computer product of claim 16 , wherein the instructions are further configured to partition the substrates into subsets, wherein each subset is associated with a subset of the data obtained by the partitioning.

Assignees

• Asml Netherlands Bv

Inventors

• Bastani Vahid
• Ypma Alexander
• Sonntag Dag
• Mos Everhardus Cornelis
• Cekli Hakki Ergün
• Lin Chenxi

Classifications

• G03F7/706837

  Data analysis, e.g. filtering, weighting, flyer removal, fingerprints or root cause analysis · CPC title

• G06F2119/18

  Manufacturability analysis or optimisation for manufacturability · CPC title

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• G06N20/20

  Ensemble learning · CPC title