You are here

Combinatorial Discovery of Heterogeneous Catalysts Utilizing Emission Spectroscopy and Advanced Machine Learning

Award Information
Agency: Department of Energy
Branch: N/A
Contract: DE-SC0018887
Agency Tracking Number: 247204
Amount: $1,000,000.00
Phase: Phase II
Program: SBIR
Solicitation Topic Code: 06a
Solicitation Number: DE-FOA-0001976
Timeline
Solicitation Year: 2019
Award Year: 2019
Award Start Date (Proposal Award Date): 2019-08-19
Award End Date (Contract End Date): 2021-08-18
Small Business Information
11900 Parklawn Drive Suite 203
Rockville, MD 20852-2669
United States
DUNS: 826528809
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 Christopher Metting
 (240) 223-5400
 cmetting@accustrata.com
Business Contact
 George Atanasoff
Phone: (240) 223-5400
Email: gatanasoff@accustrata.com
Research Institution
N/A
Abstract

In this SBIR Phase II project, AccuStrata, Inc.will continue its work to create a high-throughput integrated laser induced breakdown spectroscopy (LIBS)/flame spray pyrolysis (FSP) system for the rapid, combinatorial discovery and optimization of heterogeneous catalysts.The proposal will build off the successes in Phase I by: • Creating an integrated LIBS/FSP system • Integrating controls for both LIBS and FSP into the machine learning infrastructure • Continue to acquire new data to train and optimize the machine learning algorithm • Install onto a commercial burner The proposed system will integrate these features to provide a holistic, commercialize solution for combinatorial discovery of heterogeneous catalysts.A system with these unique capabilities will be of great interest to laboratories both at the university and industry levels.Flame spray pyrolysis can be used to create catalysts from a wide array of materials.In addition, nanoparticle synthesis through FSP allows for precise control over crystallite size, crystalline phase, degree of aggregation and agglomeration, surface area and porosity, which makes it an ideal technique for heterogeneous catalysis discovery.While the technique provides incredible flexibility, complete characterization of the nanoparticles quality post-synthesis is often a slow process that hinders the discovery process Laser induced breakdown spectroscopy is a processing in-situ technology for monitoring FSP but is an especially difficult characterization method due to the various emission lines originating from the fuel, precursors and by-products.The challenge of correlating the spectra to nanoparticle properties may be resolved using advance machine learning algorithms that can correlate the spectral response to the resulting nanoparticle properties as well as the processing parameters.Once the algorithm is trained, it can be used with real-time emission data as a prescreening so that only the most “promising” candidates (as determined by the algorithm) will be flagged for further study.The goal of this SBIR phase II work will be to utilize the information gained in Phase I to create a prototype system for the metrology and algorithms approach.Additionally, because the algorithms will be agnostic to the type of features that are used to train it, the LIBS technology will be applied to commercial burner systems for using the same algorithms to identify poor quality emission from fossil fuel power plants.Successful completion of this SBIR Phase II work will lead to a commercialize technology with broad application, not only in catalysis, but in general flame by product monitoring.

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government