Patents by Inventor Kiran Lall Shrestha
Kiran Lall Shrestha has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240062364Abstract: A neural network is trained for use in a substrate thickness measurement system by obtaining ground truth thickness measurements of a top layer of a calibration substrate at a plurality of locations, each location at a defined position for a die being fabricated on the substrate. A plurality of color images of the calibration substrate are obtained, each color image corresponding to a region for a die being fabricated on the substrate. A neural network is trained to convert color images of die regions from an in-line substrate imager to thickness measurements for the top layer in the die region. The training is performed using training data that includes the plurality of color images and ground truth thickness measurements with each respective color image paired with a ground truth thickness measurement for the die region associated with the respective color image.Type: ApplicationFiled: November 2, 2023Publication date: February 22, 2024Inventors: Sivakumar Dhandapani, Arash Alahgholipouromrani, Dominic J. Benvegnu, Jun Qian, Kiran Lall Shrestha
-
Publication number: 20240054634Abstract: A neural network is trained for use in a substrate residue classification system by obtaining ground truth residue level measurements of a top layer of a calibration substrate at a plurality of locations, each location at a defined position for a die being fabricated on the substrate. A plurality of color images of the calibration substrate are obtained, each color image corresponding to a region for a die being fabricated on the substrate. A neural network is trained to convert color images of die regions from an in-line substrate imager to residue level measurements for the top layer in the die region.Type: ApplicationFiled: October 27, 2023Publication date: February 15, 2024Inventors: Sivakumar Dhandapani, Arash Alahgholipouromrani, Dominic J. Benvegnu, Jun Qian, Kiran Lall Shrestha
-
Publication number: 20240014080Abstract: A method of polishing a substrate includes polishing a conductive layer on the substrate at a polishing station, monitoring the layer with an in-situ eddy current monitoring system to generate a plurality of measured signals values for a plurality of different locations on the layer, generating thickness measurements the locations, and detecting a polishing endpoint or modifying a polishing parameter based on the thickness measurements. The conductive layer is formed of a first material having a first conductivity. Generating includes calculating initial thickness values based on the plurality of measured signals values and processing the initial thickness values through a neural network that was trained using training data acquired by measuring calibration substrates having a conductive layer formed of a second material having a second conductivity that is lower than the first conductivity to generated adjusted thickness values.Type: ApplicationFiled: September 21, 2023Publication date: January 11, 2024Inventors: Kun Xu, Kiran Lall Shrestha, Doyle E. Bennett, David Maxwell Gage, Benjamin Cherian, Jun Qian, Harry Q. Lee
-
Patent number: 11847776Abstract: A neural network is trained for use in a substrate thickness measurement system by obtaining ground truth thickness measurements of a top layer of a calibration substrate at a plurality of locations, each location at a defined position for a die being fabricated on the substrate. A plurality of color images of the calibration substrate are obtained, each color image corresponding to a region for a die being fabricated on the substrate. A neural network is trained to convert color images of die regions from an in-line substrate imager to thickness measurements for the top layer in the die region. The training is performed using training data that includes the plurality of color images and ground truth thickness measurements with each respective color image paired with a ground truth thickness measurement for the die region associated with the respective color image.Type: GrantFiled: June 25, 2021Date of Patent: December 19, 2023Assignee: Applied Materials, Inc.Inventors: Sivakumar Dhandapani, Arash Alahgholipouromrani, Dominic J. Benvegnu, Jun Qian, Kiran Lall Shrestha
-
Patent number: 11836913Abstract: A neural network is trained for use in a substrate thickness measurement system by obtaining ground truth thickness measurements of a top layer of a calibration substrate at a plurality of locations, each location at a defined position for a die being fabricated on the substrate. A plurality of color images of the calibration substrate are obtained, each color image corresponding to a region for a die being fabricated on the substrate. A neural network is trained to convert color images of die regions from an in-line substrate imager to thickness measurements for the top layer in the die region. The training is performed using training data that includes the plurality of color images and ground truth thickness measurements with each respective color image paired with a ground truth thickness measurement for the die region associated with the respective color image.Type: GrantFiled: June 25, 2021Date of Patent: December 5, 2023Assignee: Applied Materials, Inc.Inventors: Sivakumar Dhandapani, Arash Alahgholipouromrani, Dominic J. Benvegnu, Jun Qian, Kiran Lall Shrestha
-
Publication number: 20230381912Abstract: A method of training a neural network includes obtaining two ground truth thickness profiles a test substrate, obtaining two thickness profiles for the test substrate as measured by an in-situ monitoring system while the test substrate is on polishing pads of different thicknesses, generating an estimated thickness profile for another thickness value that is between the two thickness values by interpolating between the two profiles, and training a neural network using the estimated thickness profile.Type: ApplicationFiled: August 4, 2023Publication date: November 30, 2023Inventors: Kun Xu, Benjamin Cherian, Jun Qian, Kiran Lall Shrestha
-
Patent number: 11791224Abstract: A method of polishing a substrate includes polishing a conductive layer on the substrate at a polishing station, monitoring the layer with an in-situ eddy current monitoring system to generate a plurality of measured signals values for a plurality of different locations on the layer, generating thickness measurements the locations, and detecting a polishing endpoint or modifying a polishing parameter based on the thickness measurements. The conductive layer is formed of a first material having a first conductivity. Generating includes calculating initial thickness values based on the plurality of measured signals values and processing the initial thickness values through a neural network that was trained using training data acquired by measuring calibration substrates having a conductive layer formed of a second material having a second conductivity that is lower than the first conductivity to generated adjusted thickness values.Type: GrantFiled: May 11, 2021Date of Patent: October 17, 2023Assignee: Applied Materials, Inc.Inventors: Kun Xu, Kiran Lall Shrestha, Doyle E. Bennett, David Maxwell Gage, Benjamin Cherian, Jun Qian, Harry Q. Lee
-
Patent number: 11780047Abstract: A method of training a neural network includes obtaining two ground truth thickness profiles a test substrate, obtaining two thickness profiles for the test substrate as measured by an in-situ monitoring system while the test substrate is on polishing pads of different thicknesses, generating an estimated thickness profile for another thickness value that is between the two thickness values by interpolating between the two profiles, and training a neural network using the estimated thickness profile.Type: GrantFiled: June 10, 2021Date of Patent: October 10, 2023Assignee: Applied Materials, Inc.Inventors: Kun Xu, Benjamin Cherian, Jun Qian, Kiran Lall Shrestha
-
Publication number: 20230290691Abstract: A method of polishing a substrate includes polishing a conductive layer on the substrate at a polishing station, monitoring the layer with an in-situ eddy current monitoring system to generate a plurality of measured signals values for a plurality of different locations on the layer, generating thickness measurements the locations, and detecting a polishing endpoint or modifying a polishing parameter based on the thickness measurements. The conductive layer is formed of a first material having a first conductivity. Generating includes calculating initial thickness values based on the plurality of measured signals values and processing the initial thickness values through a neural network that was trained using training data acquired by measuring calibration substrates having a conductive layer formed of a second material having a second conductivity that is lower than the first conductivity to generated adjusted thickness values.Type: ApplicationFiled: May 22, 2023Publication date: September 14, 2023Inventors: Kun Xu, Kiran Lall Shrestha, Doyle E. Bennett, David Maxwell Gage, Benjamin Cherian, Jun Qian, Harry Q. Lee
-
Patent number: 11658078Abstract: A method of polishing a substrate includes polishing a conductive layer on the substrate at a polishing station, monitoring the layer with an in-situ eddy current monitoring system to generate a plurality of measured signals values for a plurality of different locations on the layer, generating thickness measurements the locations, and detecting a polishing endpoint or modifying a polishing parameter based on the thickness measurements. The conductive layer is formed of a first material having a first conductivity. Generating includes calculating initial thickness values based on the plurality of measured signals values and processing the initial thickness values through a neural network that was trained using training data acquired by measuring calibration substrates having a conductive layer formed of a second material having a second conductivity that is lower than the first conductivity to generated adjusted thickness values.Type: GrantFiled: May 11, 2021Date of Patent: May 23, 2023Assignee: Applied Materials, Inc.Inventors: Kun Xu, Kiran Lall Shrestha, Doyle E. Bennett, David Maxwell Gage, Benjamin Cherian, Jun Qian, Harry Q. Lee
-
Publication number: 20210407065Abstract: A neural network is trained for use in a substrate thickness measurement system by obtaining ground truth thickness measurements of a top layer of a calibration substrate at a plurality of locations, each location at a defined position for a die being fabricated on the substrate. A plurality of color images of the calibration substrate are obtained, each color image corresponding to a region for a die being fabricated on the substrate. A neural network is trained to convert color images of die regions from an in-line substrate imager to thickness measurements for the top layer in the die region. The training is performed using training data that includes the plurality of color images and ground truth thickness measurements with each respective color image paired with a ground truth thickness measurement for the die region associated with the respective color image.Type: ApplicationFiled: June 25, 2021Publication date: December 30, 2021Inventors: Sivakumar Dhandapani, Arash Alahgholipouromrani, Dominic J. Benvegnu, Jun Qian, Kiran Lall Shrestha
-
Publication number: 20210402551Abstract: A method of training a neural network includes obtaining two ground truth thickness profiles a test substrate, obtaining two thickness profiles for the test substrate as measured by an in-situ monitoring system while the test substrate is on polishing pads of different thicknesses, generating an estimated thickness profile for another thickness value that is between the two thickness values by interpolating between the two profiles, and training a neural network using the estimated thickness profile.Type: ApplicationFiled: June 10, 2021Publication date: December 30, 2021Inventors: Kun Xu, Benjamin Cherian, Jun Qian, Kiran Lall Shrestha
-
Publication number: 20210407066Abstract: A neural network is trained for use in a substrate thickness measurement system by obtaining ground truth thickness measurements of a top layer of a calibration substrate at a plurality of locations, each location at a defined position for a die being fabricated on the substrate. A plurality of color images of the calibration substrate are obtained, each color image corresponding to a region for a die being fabricated on the substrate. A neural network is trained to convert color images of die regions from an in-line substrate imager to thickness measurements for the top layer in the die region. The training is performed using training data that includes the plurality of color images and ground truth thickness measurements with each respective color image paired with a ground truth thickness measurement for the die region associated with the respective color image.Type: ApplicationFiled: June 25, 2021Publication date: December 30, 2021Inventors: Sivakumar Dhandapani, Arash Alahgholipouromrani, Dominic J. Benvegnu, Jun Qian, Kiran Lall Shrestha
-
Publication number: 20210379723Abstract: A method of compensating for a contribution of conductivity of the semiconductor wafer to a measured trace by an in-situ electromagnetic induction monitoring system includes storing or generating a modified reference trace. The modified reference trace represents measurements of a bare doped reference semiconductor wafer by an in-situ electromagnetic induction monitoring system as modified by a neutral network. The substrate is monitored with an in-situ electromagnetic induction monitoring system to generate a measured trace that depends on a thickness of the conductive layer, and at least a portion of the measured trace is applied to a neural network to generate a modified measured trace. An adjusted trace is generated, including subtracting the modified reference trace from the modified measured trace.Type: ApplicationFiled: September 26, 2018Publication date: December 9, 2021Inventors: Kun Xu, David Maxwell Gage, Harry Q. Lee, Denis Anatolyevich Ivanov, Hassan G. Iravani, Doyle E. Bennett, Kiran Lall Shrestha
-
Publication number: 20210358819Abstract: A method of polishing a substrate includes polishing a conductive layer on the substrate at a polishing station, monitoring the layer with an in-situ eddy current monitoring system to generate a plurality of measured signals values for a plurality of different locations on the layer, generating thickness measurements the locations, and detecting a polishing endpoint or modifying a polishing parameter based on the thickness measurements. The conductive layer is formed of a first material having a first conductivity. Generating includes calculating initial thickness values based on the plurality of measured signals values and processing the initial thickness values through a neural network that was trained using training data acquired by measuring calibration substrates having a conductive layer formed of a second material having a second conductivity that is lower than the first conductivity to generated adjusted thickness values.Type: ApplicationFiled: May 11, 2021Publication date: November 18, 2021Inventors: Kun Xu, Kiran Lall Shrestha, Doyle E. Bennett, David Maxwell Gage, Benjamin Cherian, Jun Qian, Harry Q. Lee
-
Publication number: 20210354265Abstract: A method of polishing a substrate includes polishing a conductive layer on the substrate at a polishing station, monitoring the layer with an in-situ eddy current monitoring system to generate a plurality of measured signals values for a plurality of different locations on the layer, generating thickness measurements the locations, and detecting a polishing endpoint or modifying a polishing parameter based on the thickness measurements. The conductive layer is formed of a first material having a first conductivity. Generating includes calculating initial thickness values based on the plurality of measured signals values and processing the initial thickness values through a neural network that was trained using training data acquired by measuring calibration substrates having a conductive layer formed of a second material having a second conductivity that is lower than the first conductivity to generated adjusted thickness values.Type: ApplicationFiled: May 11, 2021Publication date: November 18, 2021Inventors: Kun Xu, Kiran Lall Shrestha, Doyle E. Bennett, David Maxwell Gage, Benjamin Cherian, Jun Qian, Harry Q. Lee
-
Patent number: 9679823Abstract: A method of controlling polishing of a substrate is described. A controller stores a library having a plurality of reference spectra. The controller polishes a substrate and measures a sequence of spectra of light from the substrate during polishing. For each measured spectrum of the sequence of spectra, the controller finds a best matching reference spectrum from the plurality of reference spectra and generates a sequence of best matching reference spectra. The controller uses a cell counting technique for finding the best matching reference spectrum. The controller determines at least one of a polishing endpoint or an adjustment for a polishing rate based on the sequence of best matching reference spectra.Type: GrantFiled: March 15, 2013Date of Patent: June 13, 2017Assignee: Applied Materials, Inc.Inventor: Kiran Lall Shrestha
-
Patent number: 9482610Abstract: A method of controlling processing of a substrate includes measuring a spectrum reflected from the substrate, for each partition of a plurality of partitions of the measured spectrum, computing a partition value based on the measured spectrum within the partition to generate a plurality of partition values, for each reference spectrum signature of a plurality of reference spectrum signatures, determining a membership function for each partition, for each partition, computing a membership value based on the membership function for the partition and the partition value for the partition to generate a plurality of groups of membership values with each group of the plurality of groups associated with a reference spectrum signature, selecting a best matching reference spectrum signature from the plurality of reference spectra signatures based on the plurality of groups of membership values, and determining a characterizing value associated with the best matching reference spectrum signature.Type: GrantFiled: November 12, 2012Date of Patent: November 1, 2016Assignee: Applied Materials, Inc.Inventors: Kiran Lall Shrestha, Boguslaw A. Swedek, Jeffrey Drue David, Harry Q. Lee
-
Publication number: 20140273296Abstract: A method of controlling polishing of a substrate is described. A controller stores a library having a plurality of reference spectra. The controller polishes a substrate and measures a sequence of spectra of light from the substrate during polishing. For each measured spectrum of the sequence of spectra, the controller finds a best matching reference spectrum from the plurality of reference spectra and generates a sequence of best matching reference spectra. The controller uses a cell counting technique for finding the best matching reference spectrum. The controller determines at least one of a polishing endpoint or an adjustment for a polishing rate based on the sequence of best matching reference spectra.Type: ApplicationFiled: March 15, 2013Publication date: September 18, 2014Applicant: Applied Materials, Inc.Inventor: Kiran Lall Shrestha
-
Publication number: 20140134758Abstract: A method of controlling processing of a substrate includes measuring a spectrum reflected from the substrate, for each partition of a plurality of partitions of the measured spectrum, computing a partition value based on the measured spectrum within the partition to generate a plurality of partition values, for each reference spectrum signature of a plurality of reference spectrum signatures, determining a membership function for each partition, for each partition, computing a membership value based on the membership function for the partition and the partition value for the partition to generate a plurality of groups of membership values with each group of the plurality of groups associated with a reference spectrum signature, selecting a best matching reference spectrum signature from the plurality of reference spectra signatures based on the plurality of groups of membership values, and determining a characterizing value associated with the best matching reference spectrum signature.Type: ApplicationFiled: November 12, 2012Publication date: May 15, 2014Inventors: Kiran Lall Shrestha, Boguslaw A. Swedek, Jeffrey Drue David, Harry Q. Lee