Search NASA⌕ Search

SEARCH · Search NASA

Results for “Network Models”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,297 records · Page 72

Physics-guided Machine Learning: from Supervised Deep Networks to Unsupervised Lightweight Models [Slides]

Machine learning yields great potentials in improving imaging performance (i.e., accuracy and efficiency). The incorporation of governing equation will improve generalization and alleviate label scarcity. Employ physical properties can reduce model complexity and significantly save training cost without compromising accuracy. Combining SciML imaging and edge computing would allow broader applications in energy, medicine, and other domains.

97 MATHEMATICS AND COMPUTING↗

Enhancing Carbon Fixation by Metabolic Engineering: A Model System of Complex Network Modulation

In the first two years of this research we focused on the development of a DNA microarray for transcriptional studies in the photosynthetic organism Synechocystis and the elucidation of the metabolic pathway for biopolymer synthesis in this organism. In addition we also advanced the molecular biological tools for metabolic engineering of biopolymer synthesis in Synechocystis and initiated a series of physiological studies for the elucidation of the carbon fixing pathways and basic central carbon metabolism of these organisms. During the last two-year period we focused our attention on the continuation and completion of the last task, namely, the development of tools for basic investigations of the physiology of these cells through, primarily, the determination of their metabolic fluxes. The reason for this decision lies in the importance of fluxes as key indicators of physiology and the high level of information content they carry in terms of identifying rate limiting steps in a metabolic pathway. While flux determination is a well-advanced subject for heterotrophic organisms, for the case of autotrophic bacteria, like Synechocystis, some special challenges had to be overcome. These challenges stem mostly from the fact that if one uses {sup 13}C labeled CO{sub 2} for flux determination, the {sup 13}C label will mark, at steady state, all carbon atoms of all cellular metabolites, thus eliminating the necessary differentiation required for flux determination. This peculiarity of autotrophic organisms makes it imperative to carry out flux determination under transient conditions, something that had not been accomplished before. We are pleased to report that we have solved this problem and we are now able to determine fluxes in photosynthetic organisms from stable isotope labeling experiments followed by measurements of label enrichment in cellular metabolites using Gas Chromatography-Mass Spectrometry. We have conducted extensive simulations to test the method and also are presently validating it experimentally using data generated in collaboration with a research group at Purdue University. As result of these studies we can now determine, for the first time, fluxes in photosynthetic organisms and, eventually, in plants.

59 BASIC BIOLOGICAL SCIENCES↗

A New Perspective of Post-Weld Baking Effect on Al-Steel Resistance Spot Weld Properties through Machine Learning and Finite Element Modeling

The root cause of post-weld baking on the mechanical performance of Al-steel dissimilar resistance spot welds (RSWs) has been determined by machine learning (ML) and finite element modeling (FEM) in this study. A deep neural network (DNN) model was constructed to associate the spot weld performance with the joint attributes, stacking materials, and other conditions, using a comprehensive experimental dataset. The DNN model positively identified that the post-weld baking reduces the joint performance, and the extent of degradation depends on the thickness of stacking materials. A three-dimensional finite element (FE) model was then used to investigate the root cause and the mechanism of the baking effect. It revealed that the formation of high thermal stresses during baking, from the mismatch of thermal expansion between steel and Al alloy, causes damage and cracking of the brittle intermetallic compound (IMC) formed at the interface of the weld nugget during welding. This in turn reduces the joint performance by promoting undesirable interfacial fracture when the welds were subjected to externally applied loads. The FEM model further revealed that increase in structural stiffness, because of increase in steel sheet thickness, reduces the thermal stresses at the interface caused by the thermal expansion mismatch and consequently lessens the detrimental effect of post-weld baking on the joint performance.

36 MATERIALS SCIENCE↗