Semiconductor fabrication using machine learning approach to generating process control parameters
A method for 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; generating a plurality of removal profiles, training an artificial neural network by backpropagation using the plurality of groups of process parameter and plurality of removal profiles as training data where the artificial neural network has a plurality of input nodes to receive respective removal values from the removal profile and a plurality of output nodes to output control parameter values, for each respective second substrate of a second plurality of substrates determining a target removal profile, determining respective control parameter values to apply by applying the target removal profile to the input nodes, and subjecting each respective second substrate to the process using the respective control parameter values.
1 . A method of polishing substrates, comprising:
subjecting each respective first substrate of a first plurality of substrates to a polishing process that modifies a thickness of an outer layer of the respective first substrate;
for each respective first substrate, recording a group of polishing process parameter values used for the polishing process, thus generating a plurality of groups of polishing process parameter values, and recording at least one state parameter value used for the polishing process, thus generating a plurality of state parameter values;
for each respective first substrate, measuring a removal profile of the outer layer during or after the polishing process with a monitoring system, thus generating a plurality of removal profiles;
training an artificial neural network by backpropagation using the plurality of groups of polishing process parameter values, the plurality of state parameter values, and the plurality of removal profiles as training data, the artificial neural network having a plurality of input nodes with at least two of the input nodes configured to receive respective removal values from the removal profile and one or more of the input nodes configured to receive one or more state parameter values, a plurality of output nodes to output control parameter values, and a plurality of hidden nodes connecting the input nodes to the output nodes;
for each respective second substrate of a second plurality of substrates, determining a target removal profile and an operating state parameter value, wherein the target removal profile is a radially-dependent desired change in thickness of a layer on the substrate due to the polishing process;
for each respective second substrate, determining respective control parameter values to apply to the respective second substrate from the output nodes of the artificial neural network by applying the target removal profile and the operating state parameter value for the respective second substrate to the input nodes of the artificial neural network; and
subjecting each respective second substrate to the polishing process using the respective control parameter values, wherein the respective control parameter values comprises pressures of chambers in a carrier head to hold a substrate against a polishing pad.
2 . The method of claim 1 , wherein the polishing process comprises chemical mechanical polishing.
3 . The method of claim 2 , wherein the respective control parameter values comprise one or more of a platen rotation rate, carrier head rotation rate, or polishing time.
4 . The method of claim 2 , wherein the plurality of state parameter values comprise one or more of a retaining ring life, or a polishing pad life.
5 . The method of claim 1 , wherein the monitoring system comprises an in-line metrology system.
6 . The method of claim 5 , wherein the in-line metrology system comprises an optical monitoring system.
7 . The method of claim 1 , wherein determining the target removal profile comprises storing a desired thickness profile, receiving a measured thickness profile of the respective second substrate, and determining a difference between the measured thickness profile and the desired thickness profile.
8 . The method of claim 7 , wherein receiving the measured thickness profile comprises measuring a thickness profile of the respective second substrate with the monitoring system.