# US 2024/0201637 A1 · System and method for estimating measurement uncertainty for characterization systems > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2024/0201637 A1 - Document ID: US20240201637A1 - Status: Published application - Kind: A1 - Application number: 18/081,191 - Filed: 2022-12-14 - Published: 2024-06-20 - Earliest claimed: 2022-12-14 - Assignees: KLA Corporation - Applicants: KLA Corporation - Inventors: Stilian Pandev; Min-Yeong Moon - Web page: https://patentgrep.com/patent/US20240201637A1 ## CPC - G05B 13/0265: {the criterion being a learning criterion} - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) ## Abstract A characterization system is disclosed. The system may include one or more controllers including one or more processors configured to execute a set of program instructions stored in memory. The controller may be configured to train a machine learning-based characterization library based on a set of training data. The controller may be configured to generate one or more characterization measurements using the trained machine learning-based characterization library based on the real-time characterization data associated with the one or more samples from the characterization sub-system. The controller may be configured to determine one or more additional characterization measurements based on a non-machine learning-based technique. The controller may be configured to compare the one or more characterization measurements and the one or more additional characterization measurements to monitor a measurement uncertainty of the machine learning-based characterization library. ## Claims ### Claim 1 A characterization system, the characterization system comprising: one or more controllers including one or more processors configured to execute a set of program instructions stored in memory, the set of program instructions configured to cause the one or more processors to: train a machine learning-based characterization library based on a set of training data, the set of training data including at least known characterization data associated with one or more samples, theoretical characterization data, and real-time characterization data associated with the one or more samples from a characterization sub-system; generate one or more characterization measurements using the trained machine learning-based characterization library based on the real-time characterization data associated with the one or more samples from the characterization sub-system; determine one or more additional characterization measurements based on a non-machine learning-based technique, the non-machine learning-based technique configured to determine the one or more additional characterization measurements based on the real-time characterization data from the characterization sub-system or additional real-time characterization data from an additional characterization sub-system; and compare the one or more characterization measurements based on the generated machine learning-based characterization library and the one or more additional characterization measurements based on the non-machine learning-based technique to monitor a measurement uncertainty of the machine learning-based characterization library. ### Claim 2 (depends on 1) The system of claim 1, wherein the set of program instructions are further configured to cause the one or more processors to: adjust the generated machine learning-based characterization library based on the comparison of the one or more characterization measurements and the one or more additional characterization measurements. ### Claim 3 (depends on 1) The system of claim 1, wherein the machine learning-based characterization library includes a machine learning-based overlay measurement library. ### Claim 4 (depends on 1) The system of claim 1, wherein the machine learning-based characterization library includes a machine learning-based angular tilt measurement library. ### Claim 5 (depends on 1) The system of claim 1, wherein the one or more characterization measurements includes one or more overlay metrology measurements. ### Claim 6 (depends on 1) The system of claim 1, wherein the one or more characterization measurements includes one or more angular tilt metrology measurements. ### Claim 7 (depends on 1) The system of claim 1, wherein the determine one or more additional characterization measurements based on a non-machine learning-based technique further comprises: calculating an asymmetry signal; determining a zero overlay site per sample based on the calculated asymmetry signal; determining an overlay function relating the calculated asymmetry signal to an additional overlay measurement; determining the additional overlay measurement by applying the determined overlay function to the sample; and calculating an overlay error value based on the one or more characterization measurements and the additional overlay measurements. ### Claim 8 (depends on 7) The system of claim 7, wherein the calculating an asymmetry signal comprises: calculating the asymmetry signal based on Mueller components. ### Claim 9 (depends on 7) The system of claim 7, wherein the calculating an asymmetry signal comprises: calculating the asymmetry signal based on opposite azimuth angles. ### Claim 10 (depends on 7) The system of claim 7, wherein the compare the one or more characterization measurements based on the generated machine learning-based characterization library and the one or more additional characterization measurements based on the non-machine learning-based technique to monitor a measurement uncertainty of the machine learning-based characterization library further comprises: defining one or more key performance indicators at one of a sample level or a site level. ### Claim 11 (depends on 7) The system of claim 7, wherein the compare the one or more characterization measurements based on the generated machine learning-based characterization library and the one or more additional characterization measurements based on the non-machine learning-based technique to monitor a measurement uncertainty of the machine learning-based characterization library further comprises: determining a measurement performance degradation for the machine learning-based characterization library using one of a mean of the calculated overlay error across the sample or a sigma of the calculated overlay error across the sample. ### Claim 12 (depends on 1) The system of claim 1, wherein the determine one or more additional characterization measurements based on a non-machine learning-based technique further comprises: calculating an asymmetry signal; determining a tilt function relating the calculated asymmetry signal to an additional tilt measurement; and determining the additional tilt measurement by applying the determined tilt function to the sample. ### Claim 13 (depends on 1) The system of claim 1, wherein the determine one or more additional characterization measurements based on a non-machine learning-based technique further comprises: calculating a brightness per angle; determining a tilt function relating the calculated brightness per angle to an additional tilt measurement; and determining the additional tilt measurement by applying the determined tilt function to the sample. ### Claim 14 A characterization system, the characterization system comprising: a characterization sub-system configured to obtain real-time characterization data of one or more samples; and one or more controllers including one or more processors configured to execute a set of program instructions stored in memory, the set of program instructions configured to cause the one or more processors to: train a machine learning-based characterization library based on a set of training data, the set of training data including at least known characterization data associated with the one or more samples, theoretical characterization data, and the real-time characterization data associated with the one or more samples from the characterization sub-system; generate one or more characterization measurements using the trained machine learning-based characterization library based on the real-time characterization data associated with the one or more samples from the characterization sub-system; determine one or more additional characterization measurements based on a non-machine learning-based technique, the non-machine learning-based technique configured to determine the one or more additional characterization measurements based on the real-time characterization data from the characterization sub-system or additional real-time characterization data from an additional characterization sub-system; and compare the one or more characterization measurements based on the generated machine learning-based characterization library and the one or more additional characterization measurements based on the non-machine learning-based technique to monitor a measurement uncertainty of the machine learning-based characterization library. ### Claim 15 (depends on 14) The system of claim 14, wherein the set of program instructions are further configured to cause the one or more processors to: adjust the generated machine learning-based characterization library based on the comparison of the one or more characterization measurements and the one or more additional characterization measurements. ### Claim 16 (depends on 14) The system of claim 14, wherein the characterization sub-system includes an overlay metrology sub-system. ### Claim 17 (depends on 16) The system of claim 16, wherein the machine learning-based characterization library includes a machine learning-based overlay measurement library. ### Claim 18 (depends on 14) The system of claim 14, wherein the characterization sub-system includes an x-ray metrology sub-system. ### Claim 19 (depends on 18) The system of claim 18, wherein the machine learning-based characterization library includes a machine learning-based angular tilt measurement library. ### Claim 20 (depends on 16) The system of claim 16, wherein the determine one or more additional characterization measurements based on a non-machine learning-based technique further comprises: calculating an asymmetry signal; determining a zero overlay site per sample based on the calculated asymmetry signal; determining an overlay function relating the calculated asymmetry signal to an additional overlay measurement; determining the additional overlay measurement by applying the determined overlay function to the sample; and calculating an overlay error value based on the one or more characterization measurements and the additional overlay measurement. ### Claim 21 (depends on 20) The system of claim 20, wherein the calculating an asymmetry signal comprises: calculating the asymmetry signal based on Mueller components. ### Claim 22 (depends on 20) The system of claim 20, wherein the calculating an asymmetry signal comprises: calculating the asymmetry signal based on opposite azimuth angles. ### Claim 23 (depends on 20) The system of claim 20, wherein the compare the one or more characterization measurements based on the generated machine learning-based characterization library and the one or more additional characterization measurements based on the non-machine learning-based technique to monitor a measurement uncertainty of the machine learning-based characterization library further comprises: defining one or more key performance indicators at one of a sample level or a site level. ### Claim 24 (depends on 20) The system of claim 20, wherein the compare the one or more characterization measurements based on the generated machine learning-based characterization library and the one or more additional characterization measurements based on the non-machine learning-based technique to monitor a measurement uncertainty of the machine learning-based characterization library further comprises: determining a measurement performance degradation for the machine learning-based characterization library using one of a mean of the calculated overlay error across the sample or a sigma of the calculated overlay error across the sample. ### Claim 25 (depends on 18) The system of claim 18, wherein the determine one or more additional characterization measurements based on a non-machine learning-based technique further comprises: calculating an asymmetry signal; and determining a tilt function relating the calculated asymmetry signal to an additional tilt measurement; and determining the additional tilt measurement by applying the determined tilt function to the sample. ### Claim 26 (depends on 18) The system of claim 18, wherein the determine one or more additional characterization measurements based on a non-machine learning-based technique further comprises: calculating a brightness per angle; and determining a tilt function relating the calculated brightness per angle to an additional tilt measurement; and determining the additional tilt measurement by applying the determined tilt function to the sample. ### Claim 27 A method, the method comprising: training a machine learning-based characterization library based on a set of training data, the set of training data including at least known characterization data associated with one or more samples, theoretical characterization data, and real-time characterization data associated with the one or more samples from a characterization sub-system; generating one or more characterization measurements using the trained machine learning-based characterization library based on the real-time characterization data associated with the one or more samples from the characterization sub-system; determining one or more additional characterization measurements based on a non-machine learning-based technique, the non-machine learning-based technique configured to determine the one or more additional characterization measurements based on the real-time characterization data from the characterization sub-system or additional real-time characterization data from an additional characterization sub-system; and comparing the one or more characterization measurements based on the generated machine learning-based characterization library and the one or more additional characterization measurements based on the non-machine learning-based technique to monitor a measurement uncertainty of the machine learning-based characterization library. ### Claim 28 (depends on 27) The method of claim 27, further comprising: adjusting the generated machine learning-based characterization library based on the comparison of the one or more characterization measurements and the one or more additional characterization measurements. ### Claim 29 (depends on 27) The method of claim 27, wherein the determining one or more additional characterization measurements based on a non-machine learning-based technique further comprises: calculating an asymmetry signal; determining a zero overlay site per sample based on the calculated asymmetry signal; determining an overlay function relating the calculated asymmetry signal to an additional overlay measurement; determining the additional overlay measurement by applying the determined overlay function to the sample; and calculating an overlay error value based on the obtained one or more characterization measurements and the additional overlay measurement. ### Claim 30 (depends on 27) The method of claim 27, wherein the determining one or more additional characterization measurements based on a non-machine learning-based technique further comprises: calculating an asymmetry signal; determining a tilt function relating the asymmetry signal to an additional tilt measurement; and determining the additional tilt measurement by applying the determined tilt function to the sample. ### Claim 31 (depends on 27) The method of claim 27, wherein the determining one or more additional characterization measurements based on a non-machine learning-based technique further comprises: calculating a brightness per angle; determining a tilt function relating the calculated brightness per angle to an additional tilt measurement; and determining the additional tilt measurement by applying the determined tilt function to the sample.