Applied Materials, Inc.

Lsi Logic Corporation

Jun Qian

Harry Q Lee

Jeffrey Drue David

Benjamin Cherian

Dominic J Benvegnu

Thomas H Osterheld

Sivakumar Dhandapani

Boguslaw A Swedek

Kiran Lall Shrestha

Kun Xu

Doyle E Bennett

Charles C Garretson

Nicholas Alexander Wiswell

Lakshmanan Karuppiah

Ingemar Carlsson

Sidney P Huey

Abraham Ravid

David Maxwell Gage

Arash Alahgholipouromrani

Tomohiko Kitajima

Garlen C Leung

Taketo Sekine

Gregory E Menk

Thomas Li

Denis Ivanov

Ningzhuo Cui

Steven M Zuniga

Jeonghoon Oh

Stan D Tsai

Shou-Sung Chang

Jason Garcheung Fung

Jimin Zhang

Haosheng Wu

Hassan G Iravani

David J Lischka

Eric Lau

King Yi Heung

Christopher Cocca

Arun Balakrishnan

Kaushik De

Shuchivrat Datar

Eric T Wu

Christopher Lai

Patrick A Higashi

David Chui

A chemical mechanical polishing apparatus includes a platen to support a polishing pad, a carrier head to hold a surface of a substrate against the polishing pad, a motor to generate relative motion between the platen and the carrier head so as to polish an overlying layer on the substrate, an in-situ acoustic monitoring system comprising an acoustic sensor that receives acoustic signals from the surface of the substrate, and a controller configured to determine a angular orientation of the substrate based on received acoustic signals from the in-situ acoustic monitoring system.

Determining substrate orientation with acoustic signals

A method of processing substrates includes: subjecting each respective first substrate of a first plurality of substrates to a process that modifies a thickness of an outer layer of the respective first substrate; generating a plurality of groups of process parameter values, wherein the plurality of process parameters comprise a plurality of control parameters and a plurality of state parameters; generating a plurality of measured removal profiles; generating a matrix that relates the plurality of process parameters to a calculated removal profile; for each respective second substrate of a second plurality of substrates, determining a target removal profile and a plurality of state parameter values; calculating respective control parameter values to apply to the respective second substrate by applying the target removal profile and the state parameter values to the matrix; and subjecting each respective second substrate to the process using the respective process parameter values.

Semiconductor fabrication using process control parameter matrix

A chemical mechanical polishing apparatus includes a platen to support a polishing pad, a carrier head to hold a surface of a substrate against the polishing pad, a motor to generate relative motion between the platen and the carrier head so as to polish an overlying layer on the substrate, an in-situ acoustic monitoring system comprising an acoustic sensor that receives acoustic signals from the surface of the substrate, and a controller configured to determine an angular orientation of the substrate based on received acoustic signals from the in-situ acoustic monitoring system.

Determining substrate precession with acoustic signals

A body is brought into contact with a polishing pad of a polishing system, a polishing liquid is supplied to the polishing pad, relative motion between the body and the polishing pad is generated while the body contacts the polishing pad, a signal from an in-situ eddy current monitoring system during the relative motion while the body contacts the polishing pad, generating, and mechanical vibrations in the polishing system are detected based on a signal from the in-situ eddy current monitoring system.

Eddy current monitoring to detect vibration in polishing

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.

Polishing apparatus using machine learning and compensation for pad thickness

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.

Residue measurement from machine learning based processing of substrate images

During chemical mechanical polishing of a substrate, a signal value that depends on a thickness of a layer in a measurement spot on a substrate undergoing polishing is determined by a first in-situ monitoring system. An image of at least the measurement spot of the substrate is generated by a second in-situ imaging system. Machine vision processing, e.g., a convolutional neural network, is used to determine a characterizing value for the measurement spot based on the image. Then a measurement value is calculated based on both the characterizing value and the signal value.

Machine vision as input to a CMP process control algorithm

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.

System using film thickness estimation from machine learning based processing of substrate images

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.

Technique for training neural network for use in in-situ monitoring during polishing and polishing system

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.

Determination of substrate layer thickness with polishing pad wear compensation

Trained neural network in in-situ monitoring during polishing and polishing system

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.

Training spectrum generation for machine learning system for spectrographic monitoring

A method of generating a matrix to relate a plurality of controllable parameters of a chemical mechanical polishing system to a polishing rate profile includes polishing a test substrate. The test substrate is polished for a first period of time using baseline parameter values with a first parameter set to a first value, and the test substrate is polished for a second period of time using first modified parameter values with the first parameter set to a modified second value. A thickness of the test substrate is monitored during polishing, and a baseline polishing rate profile is determined for the first period of time and a first modified polishing rate profile is determined for the second period of time. The matrix is calculated based on the baseline parameter values, the first modified parameters, the baseline polishing rate profile and the first modified polishing rate profile.

Preston matrix generator

Film thickness estimation from machine learning based processing of substrate images

Growing community of inventors

Sunnyvale, CA, United States of America

Jun Qian