Controlling a fabrication tool using support vector machine

• US 7,567,352 B2
• Filed: 05/13/2008
• Issued: 07/28/2009
• Est. Priority Date: 04/12/2007
• Status: Expired due to Fees

• Current Assignee: Tokyo Electron Limited
• Original Assignee: Tokyo Electron Limited
• Inventors: Li, Shifang, Jin, Wen, Madriaga, Manuel, Bao, Junwei
• Primary Examiner(s): NGUYEN, SANG H
• Application Number:
  US12/120,148
• Publication Number:
  US 20080252908A1
• Time in Patent Office: 441 Days
• Field of Search: 356600-636, 356/394, 356/237.4, 356/237.5, 250/339.08, 250/339.11, 702/23, 702/155, 702/179, 702/189, 438/14, 438/16
• US Class Current: 356/625
• CPC Class Codes: G03F 7/70491 Information management, e.g. software; Active and passive control, e.g. details of controlling exposure processes or exposure tool monitoring processes
• CPC Class Codes: G03F 7/70616 Monitoring the printed patterns

Abstract

A fabrication tool can be controlled using a support vector machine. A profile model of the structure is obtained. The profile model is defined by profile parameters that characterize the geometric shape of the structure. A set of values for the profile parameters is obtained. A set of simulated diffraction signals is generated using the set of values for the profile parameters, each simulated diffraction signal characterizing the behavior of light diffracted from the structure. The support vector machine is trained using the set of simulated diffraction signals as inputs to the support vector machine and the set of values for the profile parameters as expected outputs of the support vector machine. After the support vector machine has been trained, a fabrication process is performed using the fabrication tool to fabricate the structure on the wafer. A measured diffraction signal off the structure is obtained. The measured diffraction signal is inputted into the trained support vector machine. Values of profile parameters of the structure are obtained as an output from the trained support vector machine. One or more process parameters or equipment settings of the fabrication tool are adjusted based on the obtained values of the profile parameters.

Claims

1. A method of controlling a fabrication tool using a support vector machine, the method comprising:

a) performing a fabrication process using a first fabrication tool to fabricate the structure on a wafer;

b) obtaining a measured diffraction signal, wherein the measured diffraction signal was measured off the structure using an optical metrology tool;

c) inputting the measured diffraction signal into the support vector machine, wherein the support vector machine was trained using a set of simulated diffraction signals as inputs to the support vector machine and a set of values for profile parameters as expected outputs of the support vector machine, wherein the set of simulated diffraction signals was generated using the set of values for the profile parameters, and wherein the profile parameters define a profile model that characterizes the geometric shape of the structure;

d) after c), obtaining values of profile parameters of the structure as an output from the trained support vector machine; and

e) after d), adjusting one or more process parameters or equipment settings of the first fabrication tool based on the values of the profile parameters obtained in d).

2. The method of claim 1, wherein the set of simulated diffraction signals is generated using a standard set of signal parameters comprising a reflectance parameter, which characterizes the change in intensity of light when reflected on the structure, and a polarization parameter, which characterizes the change in polarization states of light when reflected on the structure, wherein the polarization parameter comprises:

a first polarization parameter that characterizes a difference between the square of the absolute value of complex reflection coefficients average over depolarization effects, and normalized to the reflectance parameter;

a second polarization parameter that characterizes an imaginary component of an interference of the complex reflection coefficients average over depolarization effects, and normalized to the reflectance parameter; and

a third polarization parameter that characterizes a real component of an interference of the complex reflection coefficients average over depolarization effects, and normalized to the reflectance parameter.

3. The method of claim 1, further comprising:

normalizing values of profile parameters, wherein the set of simulated diffraction signals are generated using the normalized values of profile parameters; and

de-normalizing the values of profile parameter obtained in d).

4. The method of claim 1, further comprising:

determining correlations for profile parameters; and

selecting the profile parameters used to define the profile model based on the determined correlations.

5. The method of claim 1, before c):

obtaining a test set of simulated diffraction signals and a test set of values for profile parameters;

testing the support vector machine using the test set of simulated diffraction signals as inputs to the support vector machine and the test set of values for profile parameters as expected outputs of the support vector machine; and

if one or more accuracy criteria are not met, retraining the support vector machine using one or more of the simulated diffraction signals in the test set and one or more values for profile parameters in the test set.

6. The method of claim 1, further comprising:

adjusting one or more process parameters or equipment settings of a second fabrication tool based on the values of the profile parameters determined in d).

7. The method of claim 6, wherein the first fabrication tool processes the wafer prior to the second fabrication tool.

8. The method of claim 6, wherein the first fabrication tool processes the wafer subsequent to the second fabrication tool.

9. A computer-readable storage medium containing computer executable instructions for causing a computer to control a fabrication tool using a support vector machine, comprising instructions for:

a) obtaining a measured diffraction signal that was measured off a structure on a wafer using an optical metrology tool, wherein the structure was fabricated on the wafer by performing a fabrication process using a first fabrication tool;

b) inputting the measured diffraction signal into the support vector machine, wherein the support vector machine was trained using a set of simulated diffraction signals as inputs to the support vector machine and a set of values for profile parameters as expected outputs of the support vector machine, wherein the set of simulated diffraction signals was generated using the set of values for the profile parameters, and wherein the profile parameters define a profile model that characterizes the geometric shape of the structure;

c) after b), obtaining values of profile parameters of the structure as an output from the trained support vector machine; and

d) after c), adjusting one or more process parameters or equipment settings of the first fabrication tool based on the values of the profile parameters obtained in c).

10. The computer-readable storage medium of claim 9, wherein the set of simulated diffraction signals is generated using a standard set of signal parameters comprising a reflectance parameter, which characterizes the change in intensity of light when reflected on the structure, and a polarization parameter, which characterizes the change in polarization states of light when reflected on the structure, wherein the polarization parameter comprises:

a first polarization parameter that characterizes a difference between the square of the absolute value of complex reflection coefficients average over depolarization effects, and normalized to the reflectance parameter;

a second polarization parameter that characterizes an imaginary component of an interference of the complex reflection coefficients average over depolarization effects, and normalized to the reflectance parameter; and

a third polarization parameter that characterizes a real component of an interference of the complex reflection coefficients average over depolarization effects, and normalized to the reflectance parameter.

11. The computer-readable storage medium of claim 9, further comprising instructions for:

normalizing values of profile parameters, wherein the set of simulated diffraction signals are generated using the normalized values of profile parameters; and

de-normalizing the values of profile parameter obtained in c).

12. The computer-readable storage medium of claim 9, further comprising instructions for:

determining correlations for profile parameters; and

selecting the profile parameters used to define the profile model based on the determined correlations.

13. The computer-readable storage medium of claim 9, before b):

obtaining a test set of simulated diffraction signals and a test set of values for profile parameters;

testing the support vector machine using the test set of simulated diffraction signals as inputs to the support vector machine and the test set of values for profile parameters as expected outputs of the support vector machine; and

if one or more accuracy criteria are not met, retraining the support vector machine using one or more of the simulated diffraction signals in the test set and one or more values for profile parameters in the test set.

14. The computer-readable storage medium of claim 9, further comprising instructions for:

adjusting one or more process parameters or equipment settings of a second fabrication tool based on the values of the profile parameters determined in c).

15. The computer-readable storage medium of claim 14, wherein the first fabrication tool processes the wafer prior to the second fabrication tool.

16. The computer-readable storage medium of claim 14, wherein the first fabrication tool processes the wafer subsequent to the second fabrication tool.

17. A system to system to control fabrication of a structure on a semiconductor wafer, comprising:

a first fabrication tool configured to perform a fabrication process to fabricate the structure on the wafer;

an optical metrology device configured to measure a diffraction signal off the structure on the wafer; and

a processor configured to input the measured diffraction signal into a support vector machine, obtain values of profile parameters of the structure as an output from the trained support vector machine, and adjust one or more process parameters or equipment settings of the first fabrication tool based on the obtained values of the profile parameters, wherein the support vector machine was trained using a set of simulated diffraction signals as inputs to the support vector machine and a set of values for the profile parameters as expected outputs of the support vector machine, wherein the set of simulated diffraction signals was generated using the set of values for the profile parameters, and wherein the profile parameters characterize the geometric shape of the structure.

18. The system of claim 17, wherein the set of simulated diffraction signals is generated using a standard set of signal parameters comprising a reflectance parameter, which characterizes the change in intensity of light when reflected on the structure, and a polarization parameter, which characterizes the change in polarization states of light when reflected on the structure, wherein the polarization parameter comprises:

a first polarization parameter that characterizes a difference between the square of the absolute value of complex reflection coefficients average over depolarization effects, and normalized to the reflectance parameter;

a second polarization parameter that characterizes an imaginary component of an interference of the complex reflection coefficients average over depolarization effects, and normalized to the reflectance parameter; and

a third polarization parameter that characterizes a real component of an interference of the complex reflection coefficients average over depolarization effects, and normalized to the reflectance parameter.

19. The system of claim 17, wherein the set of simulated diffraction signals are generated using normalized values of profile parameters, and wherein the processor is configured to de-normalize the values of profile parameters obtained as outputs from the support vector machine.

20. The system of claim 17, wherein the support vector machine is tested using a test set of simulated diffraction signals and a test set of values for profile parameters, and wherein, if one or more accuracy criteria are not met when the support vector machine is tested, the support vector machine is retrained using one or more of the simulated diffraction signals in the test set and one or more values for profile parameters in the test set.

21. The system of claim 17, further comprising:

a second fabrication tool configured to perform a fabrication process on the wafer, wherein the processor is configured to adjust one or more process parameters or equipment settings of the second fabrication tool based on the obtained values of the profile parameters.

22. The system of claim 21, wherein the first fabrication tool processes the wafer prior to the second fabrication tool.

23. The system of claim 21, wherein the first fabrication tool processes the wafer subsequent to the second fabrication tool.