Identification of hot spots or defects by machine learning

Patent metadata

Field	Value
Publication number	US-12360461-B2
Application number	US-202217744091-A
Country	US
Kind code	B2
Filing date	May 13, 2022
Priority date	May 12, 2016
Publication date	Jul 15, 2025
Grant date	Jul 15, 2025

Abstract

Methods of identifying a hot spot from a design layout or of predicting whether a pattern in a design layout is defective, using a machine learning model. An example method disclosed herein includes obtaining sets of one or more characteristics of performance of hot spots, respectively, under a plurality of process conditions, respectively, in a device manufacturing process; determining, for each of the process conditions, for each of the hot spots, based on the one or more characteristics under that process condition, whether that hot spot is defective; obtaining a characteristic of each of the process conditions; obtaining a characteristic of each of the hot spots; and training a machine learning model using a training set including the characteristic of one of the process conditions, the characteristic of one of the hot spots, and whether that hot spot is defective under that process condition.

First claim

What is claimed is:

1. A method comprising:
obtaining a characteristic representing how a test pattern performs in terms of being made in a device manufacturing process;
determining based on the characteristic whether the test pattern is a hot spot;
training, by a hardware computer system, a machine learning model using a training set comprising a sample whose feature vector comprises the characteristic and whose label is whether the test pattern is a hot spot; and configuring the device manufacturing process based on the trained machine learning model and/or providing a signal representing, or based on, the trained machine learned model to an apparatus for use by a tool or system in configuring the device manufacturing process.

2. The method of claim 1 , wherein the characteristic comprises a process window of the test pattern in the device manufacturing process.

3. The method of claim 1 , wherein the feature vector comprises a characteristic of geometric shape of the test pattern, a density distribution of a pixelated image of the test pattern, a result of functional decomposition of the test pattern, fragmentation of the test pattern, diffraction order distribution of the test pattern, a Bossung curve of the test pattern, or a geometric characteristic of the test pattern.

4. The method of claim 1 , wherein obtaining the characteristic comprises performing a simulation, performing metrology, or performing comparison of the characteristic to empirical data.

5. The method of claim 1 , wherein determining whether the test pattern is a hot spot comprises comparing the characteristic to an overlapping process window of a group of patterns that comprises the test pattern.

6. The method of claim 1 , further comprising using the trained machine learning model to configure the device manufacturing process.

7. A computer program product comprising a non-transitory computer readable medium having instructions therein, the instructions, when executed by a computer system, configured to cause the computer system to at least:
obtain a characteristic representing how or in what manner a test pattern performs in terms of being made in a device manufacturing process;
determine based on the characteristic whether the test pattern is a hot spot; train a machine learning model using a training set comprising a sample whose feature vector comprises the characteristic and whose label is whether the test pattern is a hot spot; and
configure the device manufacturing process based on the trained machine learning model and/or provide a signal representing, or based on, the trained machine learned model to an apparatus for use by a tool or system in configuring the device manufacturing process.

8. A method comprising:
obtaining a machine learning model trained using a training set comprising a sample whose feature vector comprises a performance characteristic representing how or in what manner a test pattern performs in terms of being made in a device manufacturing process and whose label is whether the test pattern is a hot spot determined based on the performance characteristic;
applying one or more characteristics of a sample pattern to the machine learning model;
generating, by the machine learning model based on the one or more characteristics of the sample pattern, an output indicating whether the sample pattern is, or has, a hot spot; and
configuring the device manufacturing process based on the output and/or providing a signal representing, or based on, the output to an apparatus for use by a tool or system in configuring the device manufacturing process.

9. The method of claim 8 , wherein the one or more characteristics of the sample pattern comprises a characteristic of geometric shape of the sample pattern, a density distribution of a pixelated image of the sample pattern, a result of functional decomposition of the sample pattern, fragmentation of the sample pattern, diffraction order distribution of the sample pattern, a Bossung curve of the sample pattern, or a geometric characteristic of the sample pattern.

10. The method of claim 8 , wherein the output comprises a characteristic of the hot spot, the characteristic of the hot spot comprising a characteristic of geometric shape of the hot spot, a density distribution of a pixelated image of the hot spot, a result of functional decomposition of the hot spot, fragmentation of the hot spot, diffraction order distribution of the hot spot, a Bossung curve for the hot spot, or a geometric characteristic of the hot spot.

11. The method of claim 8 , further comprising configuring, based on the output, the device manufacturing process.

12. The method of claim 8 , wherein the performance characteristic comprises a process window of the test pattern in the device manufacturing process.

13. The method of claim 8 , wherein whether the test pattern is a hot spot is determined by comparison of the performance characteristic to an overlapping process window of a group of patterns that comprises the test pattern.

14. A computer program product comprising a non-transitory computer readable medium having instructions therein, the instructions, when executed by a computer system, configured to cause the computer system to at least:
obtain a machine learning model trained using a training set comprising a sample whose feature vector comprises a performance characteristic representing how or in what manner a test pattern performs in terms of being made in a device manufacturing process and whose label is whether the test pattern is a hot spot determined based on the performance characteristic;
apply one or more characteristics of a sample pattern to the machine learning model;
generate, by the machine learning model based on the one or more characteristics of the sample pattern, an output indicating whether the sample pattern is, or has, a hot spot; and
configure the device manufacturing process based on the output and/or provide a signal representing, or based on, the output to an apparatus for use by a tool or system in configuring the device manufacturing process.

15. A method comprising:
obtaining a machine learning model trained using a training set comprising a plurality of samples, wherein each of the samples has a feature vector comprising a respective characteristic of one of a plurality of process conditions and a label comprising whether a hot spot is defective under that process condition;
applying one or more characteristics associated with a sample pattern to the machine learning model;
generating, by the machine learning model based on the one or more characteristics associated with the sample pattern, an output indicating whether the sample pattern is, or has, a hot spot that is defective; and
configuring the device manufacturing process based on the output and/or providing a signal representing, or based on, the output to an apparatus for use by a tool or system in configuring the device manufacturing process.

16. The method of claim 15 , wherein the one or more characteristics associated with the sample pattern comprises focus, dose, a reticle map, moving standard deviation (MSD), or a chemical-mechanical planarization (CMP) heat map.

17. The method of claim 15 , further comprising configuring, based on the output, a device manufacturing process.

18. The method of claim 15 , wherein the training set further includes a characteristic of the hot spot, the characteristic of the hot spot comprising a characteristic of geometric shape of a hot spot, a density distribution of a pixelated image of a hot spot, a result o

Assignees

• Asml Netherlands Bv

Inventors

• Su Jing
• Zou Yi
• Lin Chenxi
• Hunsche Stefan
• Jochemsen Marinus
• Lu Yen-Wen
• Cheong Lin Lee

Classifications

• G06N20/00

  Machine learning · CPC title

• G06V10/772

  Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries · CPC title

• G06F18/28

  Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries · CPC title

• G06V2201/06

  Recognition of objects for industrial automation · CPC title

• G06F30/398

  Design verification or optimisation, e.g. using design rule check [DRC], layout versus schematics [LVS] or finite element methods [FEM] (optical proximity correction [OPC] design processes G03F1/36) · CPC title