Abstract: A method of polishing includes holding a substrate with a carrier head against a polishing surface of a polishing pad, generating relative motion between the substrate and polishing pad, applying a first pressure modulated by a first modulation function to a first region of the substrate, applying a second pressure modulated by a second modulation function that is orthogonal to the first modulation function to a second region of the substrate, during polishing of the substrate monitoring the substrate with an in-situ friction monitoring system to generate a sequence of measured values, and determining a relative contribution to the sequence of measured value from the first region and second region based on distinguishing the first frequency from the second frequency.

Abstract: 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.

Abstract: A method of polishing includes holding a substrate with a carrier head against a polishing surface of a polishing pad, generating relative motion between the substrate and polishing pad, applying a first pressure in a first cyclic waveform having a first frequency to a first region of the substrate, applying a second pressure in a second cyclic waveform having a different second frequency to a different second region of the substrate, during polishing of the substrate, monitoring the substrate with an in-situ motor torque monitoring system to generate a sequence of measured values, and determining a relative contribution to the sequence of measured values from the first region and second region based on distinguishing the first frequency from the second frequency.

Abstract: Monitoring operations of a polishing system includes obtaining a time-based sequence of reference images of a component of the polishing system performing operations during a test operation of the polishing system, receiving from a camera a time-based sequence of monitoring images of an equivalent component of an equivalent polishing system performing operations during polishing of a substrate, determining a difference value for the time-based sequence of monitoring images by comparing the time-based sequence of reference images to the time-based sequence of monitoring image using an image processing algorithm, determining whether the difference value exceeds a threshold, and in response to determining the difference value exceeds the threshold, indicating an excursion.

Abstract: 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.

Abstract: Monitoring operations of a polishing system includes obtaining a time-based sequence of reference images of a component of the polishing system performing operations during a test operation of the polishing system, receiving from a camera a time-based sequence of monitoring images of an equivalent component of an equivalent polishing system performing operations during polishing of a substrate, determining a difference value for the time-based sequence of monitoring images by comparing the time-based sequence of reference images to the time-based sequence of monitoring image using an image processing algorithm, determining whether the difference value exceeds a threshold, and in response to determining the difference value exceeds the threshold, indicating an excursion.

Abstract: A method of training a neural network for spectrographic monitoring includes polishing a test substrate, measuring by an in-situ spectrographic monitoring system a sequence of test spectra of light reflected from the substrate and measuring by an in-situ non-optical monitoring system a sequence of test values from the substrate during polishing of the test substrate, measuring at least one of an initial characterizing value for the substrate before polishing or a final characterizing value for the substrate after polishing, inputting the sequence of test values and the initial characterizing value and/or final characterizing value into a thickness predictive model that outputs a sequence of training values with each respective training value in the sequence of training values associated with a respective test spectrum from the sequence of test spectra, and training an artificial neural network using the plurality of training spectra and the plurality of training values.

Abstract: 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.

Abstract: Generating a recipe for controlling a polishing system includes receiving a target removal profile that includes a target thickness to remove for a plurality of locations on a substrate that are angularly distributed around the substrate, and storing a first function defining a polishing rate for a zone from a plurality of pressurizable zones of a carrier head that are angularly distributed around a the carrier head. The first function defines polishing rates as a function of pressures. For each particular zone of the plurality of zones a recipe defining a pressure for the particular zone over time is calculated by calculating an expected thickness profile after polishing using the first function, and minimizing a cost function that incorporates a first term representing a difference between the expected thickness profile and a target thickness profile.

Abstract: Generating a recipe for a polishing process includes receiving a target removal profile that includes a target thickness to remove for locations spaced angularly around a center of a substrate, storing a first function providing substrate orientation relative to a carrier head over time, storing a second function defining a polishing rate below a zone of the zone as a function of one or more pressures of one or more zones of the carrier head, and for each particular zone of the plurality of zones, calculate a recipe defining a pressure for the particular zone over time. Calculating the recipe includes calculating an expected thickness profile after polishing from the second function defining the polishing rate and the first function providing substrate orientation relative to the zone over time, and applying a minimizing algorithm to reduce a difference between the expected thickness profile and the target thickness profile.

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.

Abstract: A method of controlling polishing includes polishing a stack of adjacent conductive layers on a substrate, measuring with an in-situ eddy current monitoring system a sequence of characterizing values for the substrate during polishing, calculating a polishing rate from the sequence of characterizing values repeatedly during polishing, calculating one or more adjustments for one or more polishing parameters based on a current polishing rate using a first control algorithm for an initial time period, detecting a change in the polishing rate that indicates exposure of the underlying conductive layer, and calculating one or more adjustments for one or more polishing parameters based on the polishing rate using a different second control algorithm for a subsequent time period after detecting the change in the polishing rate.

Abstract: During polishing of a stack of adjacent conductive layers on a substrate, an in-situ eddy current monitoring system measures sequence of characterizing values. A polishing rate is repeatedly calculated from the sequence of characterizing values repeatedly, one or more adjustments for one or more polishing parameters are repeatedly calculated based on a current polishing rate using a first control algorithm for an initial time period, a change in the polishing rate that meets at least one first predetermined criterion that indicates exposure of the underlying conductive layer is detected, and one or more adjustments for one or more polishing parameters are calculated based on the polishing rate using a different second control algorithm for a subsequent time period after detecting the change in the polishing rate.

Abstract: During polishing of a stack of adjacent layers, a plurality of instances of a profile control algorithm are executed on a controller with different instances having different values for a control parameter. A first instance receives a sequence of characterizing values from an in-situ monitoring system during an initial time period to control a polishing parameter, and a second instance receives the sequence of characterizing values during the initial time period and a subsequent time period to control the polishing parameter. Exposure of the underlying layer is detected based on the sequence of characterizing values from the in-situ monitoring system.

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.

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.

Abstract: A method of polishing a layer on the substrate at a polishing station includes the actions of monitoring the layer during polishing at the polishing station with an in-situ monitoring system to generate a plurality of measured signals for a plurality of different locations on the layer; generating, for each location of the plurality of different locations, an estimated measure of thickness of the location, the generating including processing the plurality of measured signals through a neural network; and at least one of detecting a polishing endpoint or modifying a polishing parameter based on each estimated measure of thickness.

Abstract: A method of polishing a layer on the substrate at a polishing station includes the actions of monitoring the layer during polishing at the polishing station with an in-situ monitoring system to generate a plurality of measured signals for a plurality of different locations on the layer; generating, for each location of the plurality of different locations, an estimated measure of thickness of the location, the generating including processing the plurality of measured signals through a neural network; and at least one of detecting a polishing endpoint or modifying a polishing parameter based on each estimated measure of thickness.

Abstract: A method of operating a polishing system includes training a plurality of models using a machine learning algorithm to generate a plurality of trained models, each trained model configured to determine a characteristic value of a layer of a substrate based on a monitoring signal from an in-situ monitoring system of a semiconductor processing system, storing the plurality of trained models, receiving data indicating a characteristic of a substrate to be processed, selecting one of the plurality of trained models based on the data, and passing the selected trained model to the processing system.

Abstract: Operating a substrate processing system includes receiving a plurality of sets of training data, storing a plurality of machine learning models, storing a plurality of physical process models, receiving a selection of a machine learning model from the plurality of machine learning models and a selection of a physical process model from the plurality of physical process models, generating an implemented machine learning model according to the selected machine learning model, calculating a characterizing value for each training spectrum in each set of training data thereby generating a plurality of training characterizing values with each training characterizing value associated with one of the plurality of training spectra, training the implemented machine learning model using the plurality of training characterizing values and plurality of training spectra to generate a trained machine learning model, and passing the trained machine learning model to a control system of the substrate processing system.