You are here

Use of Artificial Intelligence (Joint Optimization) to Accelerate Development of New Energetic Materials

Award Information
Agency: Department of Defense
Branch: Air Force
Contract: FA8649-21-P-0754
Agency Tracking Number: FX20C-TCSO1-0448
Amount: $49,997.00
Phase: Phase I
Program: STTR
Solicitation Topic Code: AF20C-TCSO1
Solicitation Number: X20.C
Solicitation Year: 2020
Award Year: 2021
Award Start Date (Proposal Award Date): 2021-02-10
Award End Date (Contract End Date): 2021-05-10
Small Business Information
2062 NW Thorncroft Drive, Apt. 1214
Hillsboro, OR 97124-1111
United States
DUNS: 078654177
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 Baldur Steingrimsson
 (763) 439-6905
Business Contact
 Baldur Steingrimsson
Phone: (763) 439-6905
Research Institution
 Oregon State University
 Eugene Zhang
1500 SW Jefferson Way
Corvallis, OR 97331-1111
United States

 (541) 737-8599
 Nonprofit College or University

For Focus Area RQ-05-1909, the Air Force Space Command seeks to develop technological capabilities in Multi-Mode Propulsion with Common Propellant using artificial intelligence (AI), machine learning (ML) and/or deep learning (DL) approaches to accelerate the discovery/design of new energetic in-space materials via accurate assessments of their physicochemical properties from available databases. In this project, Imagars will tailor its patent-pending ML technology (Patent Publication No. US 2020/0257933A1) to accelerate alloy design such as to enable acceleration in identification of new energetic materials (propellants with greater energy density than presently available). Enhancements to Imagars’ existing database will involve properties related to thermal coefficients, thermal diffusability, energy density, phase transformations and entropy. For this purpose, Imagars will be targeting collaboration with Prof. Liney Arnadottir, from the Department of Chemical, Biological and Environmental Engineering at Oregon State University, a recognized expert in first-principle calculations. Data-driven approaches, which include intelligent predictive capabilities, provide opportunities to accelerate the discovery of such energetic materials. Continued application of test-driven approaches may not be cost-effective, sustainable, or sufficiently responsive to today’s warfighter needs. To this end, sequential learning combines data-driven ML approaches with experimentation, for purpose of necessitating fewer experiments and decreasing cost. In addition, we present a framework for joint optimization of material properties. This framework was originally proposed for Ni-based super-alloys. But the fundamental ideas can be adapted both to high-entropy alloys (HEAs) and new energetic materials (propellant design). We intend on working with Prof. Arnadottir on fully defining the physio-chemical data sets suitable for the molecular engineering involved. In addition, we present a fallback scenario, which assumes application of the framework to joint optimization of mechanical properties of alloys, used for rocket propulsion, prior to application to energetic material (propellants), for the Air Force Space Command to consider. Our commercialization plan assumes collaboration with Lockheed Martin Space. Dr. Anand Kulkarni of Siemens is a co-author of our patent titled “Automatic Requirement Verification Engine and Analytics” as well as patent publication 2020/0257933A1. For the patenting efforts, we intend to go through a similar process with Lockheed Martin Space as we have started with Siemens. Lockheed Martin is expected to provide requirements for design of energetic materials relevant to multi-mode propulsion, in the event of a Phase 2 award. In this case, Lockheed Martin is also expected to advise on integration of the proposed product, a plugin for joint optimization into established tools used for designing new energetic materials.

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

US Flag An Official Website of the United States Government