公开(公告)号：US11791224B2

公开(公告)日：2023-10-17

申请号：US17317232

申请日：2021-05-11

Applicant: Applied Materials, Inc.

Inventor： Kun Xu ,  Kiran Lall Shrestha ,  Doyle E. Bennett ,  David Maxwell Gage ,  Benjamin Cherian ,  Jun Qian ,  Harry Q. Lee

IPC: B24B37/013 ,  B24B49/10 ,  G06N3/08 ,  H01L21/321 ,  H01L21/66 ,  H01L21/304 ,  G06F17/15

CPC classification number: H01L22/14 ,  B24B37/013 ,  B24B49/105 ,  G06F17/15 ,  G06N3/08 ,  H01L21/304 ,  H01L21/3212 ,  H01L22/12 ,  H01L22/26

Abstract: 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.

公开(公告)号：US20210407065A1

公开(公告)日：2021-12-30

申请号：US17359307

申请日：2021-06-25

Applicant: Applied Materials, Inc.

Inventor： Sivakumar Dhandapani ,  Arash Alahgholipouromrani ,  Dominic J. Benvegnu ,  Jun Qian ,  Kiran Lall Shrestha

IPC: G06T7/00 ,  G06T7/60

Abstract: 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.

公开(公告)号：US20210402551A1

公开(公告)日：2021-12-30

申请号：US17344779

申请日：2021-06-10

Applicant: Applied Materials, Inc.

Inventor： Kun Xu ,  Benjamin Cherian ,  Jun Qian ,  Kiran Lall Shrestha

IPC: B24B37/013 ,  G06N3/08

Abstract: 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.

公开(公告)号：US20210354265A1

公开(公告)日：2021-11-18

申请号：US17317232

申请日：2021-05-11

Applicant: Applied Materials, Inc.

Inventor： Kun Xu ,  Kiran Lall Shrestha ,  Doyle E. Bennett ,  David Maxwell Gage ,  Benjamin Cherian ,  Jun Qian ,  Harry Q. Lee

IPC: B24B49/10 ,  G06N3/08 ,  H01L21/321 ,  B24B37/013

Abstract: 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.

公开(公告)号：US10651098B2

公开(公告)日：2020-05-12

申请号：US15173584

申请日：2016-06-03

Applicant: Applied Materials, Inc.

Inventor： Tomohiko Kitajima ,  Jeffrey Drue David ,  Jun Qian ,  Taketo Sekine ,  Garlen C. Leung ,  Sidney P. Huey

IPC: B24B49/10 ,  H01L21/66 ,  H01L21/67 ,  B24B37/013 ,  H01L21/321 ,  H01L21/3105

Abstract: A method of controlling polishing includes storing a base measurement, the base measurement being a measurement of a substrate after deposition of at least one layer overlying a semiconductor wafer and before deposition of an outer layer over the at least one layer, after deposition of the outer layer over the at least one layer and during polishing of the outer layer on substrate, receiving a sequence of raw measurements of the substrate from an in-situ monitoring system, normalizing each raw measurement in the sequence of raw measurement to generate a sequence of normalized measurements using the raw measurement and the base measurement, and determining at least one of a polishing endpoint or an adjustment for a polishing rate based on at least the sequence of normalized measurements.

公开(公告)号：US20190299356A1

公开(公告)日：2019-10-03

申请号：US16368649

申请日：2019-03-28

Applicant: Applied Materials, Inc.

Inventor： Kun Xu ,  Denis Ivanov ,  Harry Q. Lee ,  Jun Qian

IPC: B24B37/005 ,  B24B49/10 ,  H01L21/67 ,  G05B19/048 ,  G06N20/00 ,  G06N3/063

Abstract: Data received from an in-situ monitoring system includes, for each scan of a sensor, a plurality of measured signal values for a plurality of different locations on a layer. A thickness of a polishing pad is determined based on the data from the in-situ monitoring system. For each scan, a portion of the measured signal values are adjusted based on the thickness of the polishing pad. For each scan of the plurality of scans and each location of the plurality of different locations, a value is generated representing a thickness of the layer at the location. This includes processing the adjusted signal values using one or more processors configured by machine learning. A polishing endpoint is detected or a polishing parameter is modified based on the values representing the thicknesses at the plurality of different locations.

公开(公告)号：US20170100814A1

公开(公告)日：2017-04-13

申请号：US15385202

申请日：2016-12-20

Applicant: Applied Materials, Inc.

Inventor： Jun Qian ,  Harry Q. Lee

IPC: B24B37/013 ,  B24B37/10 ,  B24B37/20 ,  B24B37/04

CPC classification number: B24B37/013 ,  B24B37/042 ,  B24B37/10 ,  B24B37/205 ,  B24B49/045 ,  B24B49/12

Abstract: A computer-implemented method of generating reference spectra includes polishing a first substrate in a polishing apparatus having a rotatable platen, measuring a sequence of spectra from the substrate during polishing with an in-situ monitoring system, associating each spectrum in the sequence of spectra with a index value equal to a number of platen rotations at which the each spectrum was measured, and storing the sequence of spectra as reference spectra.

公开(公告)号：US12057354B2

公开(公告)日：2024-08-06

申请号：US18200244

申请日：2023-05-22

Applicant: Applied Materials, Inc.

Inventor： Kun Xu ,  Kiran Lall Shrestha ,  Doyle E. Bennett ,  David Maxwell Gage ,  Benjamin Cherian ,  Jun Qian ,  Harry Q. Lee

IPC: H01L21/66 ,  B24B37/013 ,  B24B49/10 ,  G06F17/15 ,  G06N3/08 ,  H01L21/304 ,  H01L21/321

CPC classification number: H01L22/14 ,  B24B37/013 ,  B24B49/105 ,  G06F17/15 ,  G06N3/08 ,  H01L21/304 ,  H01L21/3212 ,  H01L22/12 ,  H01L22/26

Abstract: 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.

公开(公告)号：US12020159B2

公开(公告)日：2024-06-25

申请号：US18310520

申请日：2023-05-01

Applicant: Applied Materials, Inc.

Inventor： Benjamin Cherian ,  Nicholas A. Wiswell ,  Jun Qian ,  Thomas H. Osterheld

IPC: G06N3/08 ,  G05B13/02 ,  G05B19/4063 ,  G05B19/4155 ,  G06N3/045 ,  H01L21/66

CPC classification number: G06N3/08 ,  G05B13/027 ,  G05B19/4063 ,  G05B19/4155 ,  G06N3/045 ,  H01L22/12 ,  G05B2219/32335 ,  G05B2219/40066 ,  G05B2219/41054 ,  G05B2219/45031 ,  G05B2219/45199

Abstract: A method of generating training spectra for training of a neural network includes measuring a first plurality of training spectra from one or more sample substrates, measuring a characterizing value for each training spectra of the plurality of training spectra to generate a plurality of characterizing values with each training spectrum having an associated characterizing value, measuring a plurality of dummy spectra during processing of one or more dummy substrates, and generating a second plurality of training spectra by combining the first plurality of training spectra and the plurality of dummy spectra, there being a greater number of spectra in the second plurality of training spectra than in the first plurality of training spectra. Each training spectrum of the second plurality of training spectra having an associated characterizing value.

公开(公告)号：US20240062364A1

公开(公告)日：2024-02-22

申请号：US18500811

申请日：2023-11-02

Applicant: Applied Materials, Inc.

Inventor： Sivakumar Dhandapani ,  Arash Alahgholipouromrani ,  Dominic J. Benvegnu ,  Jun Qian ,  Kiran Lall Shrestha

IPC: G06T7/00 ,  B24B37/013 ,  G06T7/60

CPC classification number: G06T7/001 ,  B24B37/013 ,  G06T7/60 ,  G06T2207/10024 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30148

Abstract: 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.