Applied Materials, Inc.

Sivakumar Dhandapani

Jun Qian

Dominic J Benvegnu

Benjamin Cherian

Jeffrey Drue David

Harry Q Lee

Charles C Garretson

Boguslaw A Swedek

Gregory E Menk

Kiran Lall Shrestha

Arash Alahgholipouromrani

Stan D Tsai

Thomas H Osterheld

Jason Garcheung Fung

Shou-Sung Chang

Sameer Deshpande

Christopher Cocca

Hung Chih Chen

Doyle E Bennett

Daxin Mao

Thomas Li

Asheesh Jain

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

Controlling a polishing system includes receiving from an in-situ monitoring system, for each region of a plurality of regions on a substrate being processed by the polishing system, a sequence of characterizing values for the region. For each region, a polishing rate is determined for the region, and an adjustment is calculated for at least one processing parameter. Calculation of the adjustment includes minimizing a cost function that includes, for each region, i) a difference between a current characterizing value or an expected characterizing value at an expected endpoint time and a target characterizing value for the region, and ii) a plurality of a projected future pressure changes over time for the region and/or a plurality of differences between projected future pressures over time and a baseline pressure for the region.

Control of processing parameters during substrate polishing using cost function

In one embodiment, a method is provided for polishing a substrate. The method generally includes receiving a plurality of dwell times of a pad conditioning disk, wherein the plurality of dwell times are to be used in a pad conditioning process performed on a pad disposed on a platen, and each dwell time corresponding to a zone of a plurality of zones of the pad disposed on the platen, determining a plurality of total pad conditioning disk cut times to be used in the pad conditioning process, each total pad conditioning disk cut time corresponding to a zone of the plurality of zones, and generating a first pad wear removal model based on a set of parameters, including the plurality of dwell times and the plurality of total pad conditioning disk cut times.

Methods of modeling and controlling pad wear

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

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 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

Controlling a polishing system includes receiving from an in-situ monitoring system, for each region of a plurality of regions on a substrate being processed by the polishing system, a sequence of characterizing values for the region. For each region, a polishing rate is determined for the region, and an adjustment is calculated for at least one processing parameter. For each of a plurality of parameter update times, an adjustment is calculated for at least one processing parameter, wherein calculation of the adjustment for a particular parameter update time from the plurality of parameter update times includes calculation of expected future parameter changes for one or more future parameter update times subsequent to the particular parameter update time.

Control of processing parameters during substrate polishing using expected future parameter changes

A method of controlling polishing includes polishing a substrate, monitoring the substrate during polishing with an in-situ monitoring system, filtering a signal from the monitoring system to generate a filtered signal, and determining at least one of a polishing endpoint or an adjustment for a polishing rate from the filtered signal. The filtering includes modelling a plurality of periodic disturbances at a plurality of different frequencies using a plurality of disturbance states, modelling an underlying signal using a plant state, and applying a linear prediction filter to the plant state and the plurality of disturbance states to generate a filtered signal representing the underlying signal.

Filtering during in-situ monitoring of polishing

Controlling a polishing system includes receiving from an in-situ monitoring system, for each region of a plurality of regions on a substrate being processed by the polishing system, a sequence of characterizing values for the region. For each region, a polishing rate is determined for the region, and an adjustment is calculated for at least one processing parameter. Calculation of the adjustment includes minimizing a cost function that includes, for each region, a difference between a current characterizing value or an expected characterizing value at an expected endpoint time and a target characterizing value for the region, and optimization of the cost function is subject to at least one constraint.

Control of processing parameters during substrate polishing using constrained cost function

Film thickness estimation from machine learning based processing of substrate images

An apparatus for chemical mechanical polishing includes a platen having a surface to support a polishing pad, a carrier head to hold a substrate against a polishing surface of the polishing pad, a pad conditioner to hold a conditioning disk against the polishing surface, an in-situ polishing pad thickness monitoring system, and a controller. The controller is configured to store data associating each of a plurality of conditioner disk products with a respective threshold value, receive an input selecting a conditioner disk product from the plurality of conditioner disk products, determine a particular threshold value associated with the selected conditioner disk product, receive a signal from the monitoring system, generate a measure of a pad cut rate from the signal, and generate an alert if the pad cut rate falls beyond the particular threshold value.

Pad conditioner cut rate monitoring

An apparatus for chemical mechanical polishing includes a platen having a surface to support a polishing pad, a carrier head to hold a substrate against a polishing surface of the polishing pad, a pad conditioner to hold a conditioning disk against the polishing surface, an in-situ polishing pad thickness monitoring system; and, a controller configured to receive a signal from the monitoring system and generate a measure of polishing pad wear rate by applying a predictive filter to the signal.

Growing community of inventors

San Jose, CA, United States of America

Sivakumar Dhandapani