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.
Abstract:
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.
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.
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:
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.
Abstract:
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.
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 for polishing dies locations on a substrate with a polishing module. A thickness at selected locations on the substrate is premeasured at a metrology station, each location corresponding to a location of a single die. The thickness obtained by the metrology station for the selected locations of the substrate is provided to a controller of a polishing module. The thickness corrections for each selected location on the substrate are determined. A polishing step in a polishing recipe is formed from the thickness correction for each selected location. A polishing parameter for each die location is calculated for the recipe.
Abstract:
A method of generating reference spectra includes polishing a first substrate in a polishing apparatus, measuring a sequence of spectra from the first substrate during polishing with an in-situ optical monitoring system, for each spectrum in the sequence of spectra, determining a best matching reference spectrum from a first plurality of first reference spectra to generate a sequence of reference spectra, calculating a value of a metric of fit of the sequence of spectra to the sequence of reference spectra, comparing the value of the metric of fit to a threshold value and determining whether to generate a second library based on the comparison, and if the second library is determined to be generated, storing the sequence of spectra as a second plurality of reference spectra.
Abstract:
A method for controlling the residue clearing process of a chemical mechanical polishing (“CMP”) process is provided. Dynamic in-situ profile control (“ISPC”) is used to control polishing before residue clearing starts, and then a new polishing recipe is dynamically calculated for the clearing process. Several different methods are disclosed for calculating the clearing recipe. First, in certain implementations when feedback at T0 or T1 methods are used, a post polishing profile and feedback offsets are generated in ISPC software. Based on the polishing profile and feedback generated from ISPC before the start of the clearing process, a flat post profile after clearing is targeted. The estimated time for the clearing step may be based on the previously processed wafers (for example, a moving average of the previous endpoint times). The calculated pressures may be scaled to a lower (or higher) baseline pressure for a more uniform clearing.