Patents by Inventor Subramanian Sankaranarayanan
Subramanian Sankaranarayanan has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20230260602Abstract: A system can include one or more processors configured to access at least one parameter of a material, generate a plurality of structures of the material using the at least one parameter, determine a state of each structure of the plurality of structures using the at least one parameter, determine a difference between the state of each structure of the plurality of structures and a ground state value, evaluate a convergence condition responsive to determining the difference between the state of each structure of the plurality of structures and the ground state value, and output at least one structure of the plurality of structures responsive to the convergence condition being satisfied.Type: ApplicationFiled: April 25, 2023Publication date: August 17, 2023Applicant: Uchicago Argonne, LLCInventors: Subramanian Sankaranarayanan, Troy David Loeffler, Henry Chan, Mathew J. Cherukara, Srilok Srinivasan
-
Patent number: 11710038Abstract: A method for active learning using sparse training data can include training a machine learning model using less than ten first training data points to generate a candidate machine learning model. The method can include performing a Monte Carlo process to sample one or more first outputs of the candidate machine learning model. The method can include testing the one or more first outputs to determine if each of the one or more first outputs satisfy a respective convergence condition. The method can include, responsive to at least one first output not satisfying the respective convergence condition, training the candidate machine learning model using at least one second training data point corresponding to the at least one first output. The method can include, responsive to the one or more first outputs each satisfying the respective convergence condition, outputting the candidate machine learning model.Type: GrantFiled: April 13, 2020Date of Patent: July 25, 2023Assignee: UChicago Argonne, LLCInventors: Subramanian Sankaranarayanan, Troy David Loeffler, Henry Chan
-
Patent number: 11663494Abstract: A method for optimizing objective functions can include selecting an objective function based at least on a hierarchy, applying parameters to the objective function to generate an output, responsive to the output not satisfying a tolerance condition, assigning a penalty to the set of parameters and evaluating a convergence condition using the set of parameters and the penalty, responsive to the output satisfying the tolerance condition, evaluating an additional objective function using the parameters in an order corresponding to the hierarchy or evaluating the convergence condition responsive to the selected objective function being a final objective function, modifying the set of parameters using a genetic algorithm responsive to the set of parameters not satisfying the convergence condition, and outputting the set of parameters responsive to the set of parameters satisfying the convergence condition.Type: GrantFiled: December 5, 2019Date of Patent: May 30, 2023Assignee: UChicago Argonne, LLCInventors: Henry Chan, Mathew J. Cherukara, Badri Narayanan, Subramanian Sankaranarayanan, Stephen K. Gray, Troy David Loeffler
-
Patent number: 11651839Abstract: A system can include one or more processors configured to access at least one parameter of a material, generate a plurality of structures of the material using the at least one parameter, determine a state of each structure of the plurality of structures using the at least one parameter, determine a difference between the state of each structure of the plurality of structures and a ground state value, evaluate a convergence condition responsive to determining the difference between the state of each structure of the plurality of structures and the ground state value, and output at least one structure of the plurality of structures responsive to the convergence condition being satisfied.Type: GrantFiled: March 2, 2020Date of Patent: May 16, 2023Assignee: UChicago Argonne, LLCInventors: Subramanian Sankaranarayanan, Troy David Loeffler, Henry Chan, Mathew J. Cherukara, Srilok Srinivasan
-
Patent number: 11232241Abstract: A method for designing new materials for superlubricity comprises developing, on a computational system, a computational supercell comprising x unit cells of a base material, each unit cell comprising y atoms of the base material. The computational system replaces randomly chosen z atoms of the base material with an impurity atom of an impurity material to form a candidate material. The computational system determines volumetric strain of the candidate material. In response to the volumetric strain exceeding a predetermined threshold, the computational system determines that the candidate material has superlubricity. The computational system displays the candidate material to a user if the candidate material has superlubricity.Type: GrantFiled: July 16, 2018Date of Patent: January 25, 2022Assignee: UChicago Argonne, LLCInventors: Badri Narayanan, Subramanian Sankaranarayanan, Anirudha V. Sumant, Mathew J. Cherukara, Diana Berman
-
Publication number: 20210319308Abstract: A method for active learning using sparse training data can include training a machine learning model using less than ten first training data points to generate a candidate machine learning model. The method can include performing a Monte Carlo process to sample one or more first outputs of the candidate machine learning model. The method can include testing the one or more first outputs to determine if each of the one or more first outputs satisfy a respective convergence condition. The method can include, responsive to at least one first output not satisfying the respective convergence condition, training the candidate machine learning model using at least one second training data point corresponding to the at least one first output. The method can include, responsive to the one or more first outputs each satisfying the respective convergence condition, outputting the candidate machine learning model.Type: ApplicationFiled: April 13, 2020Publication date: October 14, 2021Applicant: UCHICAGO ARGONNE, LLCInventors: Subramanian Sankaranarayanan, Troy David Loeffler, Henry Chan
-
Publication number: 20210272658Abstract: A system can include one or more processors configured to access at least one parameter of a material, generate a plurality of structures of the material using the at least one parameter, determine a state of each structure of the plurality of structures using the at least one parameter, determine a difference between the state of each structure of the plurality of structures and a ground state value, evaluate a convergence condition responsive to determining the difference between the state of each structure of the plurality of structures and the ground state value, and output at least one structure of the plurality of structures responsive to the convergence condition being satisfied.Type: ApplicationFiled: March 2, 2020Publication date: September 2, 2021Applicant: UCHICAGO ARGONNE, LLCInventors: Subramanian Sankaranarayanan, Troy David Loeffler, Henry Chan, Mathew J. Cherukara, Srilok Srinivasan
-
Publication number: 20210174215Abstract: A method for optimizing objective functions can include selecting an objective function based at least on a hierarchy, applying parameters to the objective function to generate an output, responsive to the output not satisfying a tolerance condition, assigning a penalty to the set of parameters and evaluating a convergence condition using the set of parameters and the penalty, responsive to the output satisfying the tolerance condition, evaluating an additional objective function using the parameters in an order corresponding to the hierarchy or evaluating the convergence condition responsive to the selected objective function being a final objective function, modifying the set of parameters using a genetic algorithm responsive to the set of parameters not satisfying the convergence condition, and outputting the set of parameters responsive to the set of parameters satisfying the convergence condition.Type: ApplicationFiled: December 5, 2019Publication date: June 10, 2021Applicant: UCHICAGO ARGONNE, LLCInventors: Henry Chan, Mathew J. Cherukara, Badri Narayanan, Subramanian Sankaranarayanan, Stephen K. Gray, Troy David Loeffler
-
Patent number: 11020711Abstract: A membrane for filtering one or more hydrophobic organic contaminants can include a porous nanostructure that includes one or more of a metal, a metal oxide, and a metal alloy nanostructure component functionalized with one or more amphiphilic ligands.Type: GrantFiled: September 28, 2018Date of Patent: June 1, 2021Assignee: UCHICAGO ARGONNE, LLCInventors: Xiao-Min Lin, Kun Wu, Subramanian Sankaranarayanan
-
Patent number: 10839195Abstract: A method of identifying grains in polycrystalline materials, the method including (a) identifying local crystal structure of the polycrystalline material based on neighbor coordination or pattern recognition machine learning, the local crystal structure including grains and grain boundaries, (b) pre-processing the grains and the grain boundaries using image processing techniques, (c) conducting grain identification using unsupervised machine learning; and (d) refining a resolution of the grain boundaries.Type: GrantFiled: August 8, 2017Date of Patent: November 17, 2020Assignee: UChicago Argonne, LLCInventors: Subramanian Sankaranarayanan, Mathew J. Cherukara, Badri Narayanan, Henry Chan
-
Publication number: 20200101425Abstract: A membrane for filtering one or more hydrophobic organic contaminants can include a porous nanostructure that includes one or more of a metal, a metal oxide, and a metal alloy nanostructure component functionalized with one or more amphiphilic ligands.Type: ApplicationFiled: September 28, 2018Publication date: April 2, 2020Inventors: Xiao-Min Lin, Kun Wu, Subramanian Sankaranarayanan
-
Publication number: 20200019656Abstract: A method for designing new materials for superlubricity comprises developing, on a computational system, a computational supercell comprising x unit cells of a base material, each unit cell comprising y atoms of the base material. The computational system replaces randomly chosen z atoms of the base material with an impurity atom of an impurity material to form a candidate material. The computational system determines volumetric strain of the candidate material. In response to the volumetric strain exceeding a predetermined threshold, the computational system determines that the candidate material has superlubricity. The computational system displays the candidate material to a user if the candidate material has superlubricity.Type: ApplicationFiled: July 16, 2018Publication date: January 16, 2020Applicant: UCHICAGO ARGONNE, LLCInventors: Badri Narayanan, Subramanian Sankaranarayanan, Anirudha V. Sumant, Mathew J. Cherukara, Diana Berman
-
Publication number: 20190050628Abstract: A method of identifying grains in polycrystalline materials, the method including (a) identifying local crystal structure of the polycrystalline material based on neighbor coordination or pattern recognition machine learning, the local crystal structure including grains and grain boundaries, (b) pre-processing the grains and the grain boundaries using image processing techniques, (c) conducting grain identification using unsupervised machine learning; and (d) refining a resolution of the grain boundaries.Type: ApplicationFiled: August 8, 2017Publication date: February 14, 2019Inventors: Subramanian SANKARANARAYANAN, Mathew J. CHERUKARA, Badri NARAYANAN, Henry CHAN
-
Patent number: 8835805Abstract: The invention provides a simple and inexpensive method to assemble nanomaterials into millimeter lengths. The method can be used to generate optical, sensing, electronic, magnetic and or catalytic materials. Also provided is a substrate comprised of fused nanoparticles. The invention also provides a diode comprised of assembled nanoparticles.Type: GrantFiled: September 30, 2011Date of Patent: September 16, 2014Assignee: UChicago Argonne, LLCInventors: John T. Bahns, Liaohai Chen, Stephen K. Gray, Subramanian Sankaranarayanan
-
Publication number: 20130084451Abstract: The invention provides a simple and inexpensive method to assemble nanomaterials into millimeter lengths. The method can be used to generate optical, sensing, electronic, magnetic and or catalytic materials. Also provided is a substrate comprised of fused nanoparticles. The invention also provides a diode comprised of assembled nanoparticles.Type: ApplicationFiled: September 30, 2011Publication date: April 4, 2013Applicant: UCHICAGO ARGONNE, LLCInventors: John T. Bahns, Liaohai Chen, Stephen K. Gray, Subramanian Sankaranarayanan