SEARCH · Search NASA
Results for “Genetic Algorithms”
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.
Investigating energetics of Au8 on graphene/Ru(0001) using a genetic algorithm and density functional theory
Explore the source record for details and available documents.
A genetic algorithm based approach for multi-objective hardware/software co-optimization
Not Available
Inverse Design of Tetracene Polymorphs with Enhanced Singlet Fission Performance by Property-Based Genetic Algorithm Optimization
Not Available
Cluster-MLP: An Active Learning Genetic Algorithm Framework for Accelerated Discovery of Global Minimum Configurations of Pure and Alloyed Nanoclusters
Not Available
Modeling Metallic Halide Local Structures in Salt Melts Using a Genetic Algorithm
Not provided.
Pursuit of the Ultimate Regression Model for Samarium(III), Europium(III), and LiCl Using Laser-Induced Fluorescence, Design of Experiments, and a Genetic Algorithm for Feature Selection
Not Available
Quantum-inspired genetic algorithm for designing planar multilayer photonic structure
Not Available
Conceptual optimization using genetic algorithms for tube in tube structures
The purpose of this article is to optimize the tube in tube structural systems for tall buildings under the horizontal wind loads. It is well-known that the horizontal wind loads is the main criteria when choosing the structural system, the types and the dimensions of structural elements in the majority of tall buildings. Thus, the structural response of tall buildings under the horizontal wind loads will be analyzed for 40 story buildings and a total height of 120 meters; the horizontal dimensions will be 30m × 30m for the first two optimization problems and 15m × 15m for the third. The optimization problems will have the following as objective function the cross section area, as restrictions the displacement of the building< the admissible displacement (H/500), and as variables the cross section dimensions of the structural elements.
Communication: Analytical optimal pulse shapes obtained with the aid of genetic algorithms: Controlling the photoisomerization yield of retinal
We recently proposed a Quantum Optimal Control (QOC) method constrained to build pulses from analytical pulse shapes [R. D. Guerrero et al., J. Chem. Phys. 143(12), 124108 (2015)]. This approach was applied to control the dissociation channel yields of the diatomic molecule KH, considering three potential energy curves and one degree of freedom. In this work, we utilized this methodology to study the strong field control of the cis-trans photoisomerization of 11-cis retinal. This more complex system was modeled with a Hamiltonian comprising two potential energy surfaces and two degrees of freedom. The resulting optimal pulse, made of 6 linearly chirped pulses, was capable of controlling the population of the trans isomer on the ground electronic surface for nearly 200 fs. The simplicity of the pulse generated with our QOC approach offers two clear advantages: a direct analysis of the sequence of events occurring during the driven dynamics, and its reproducibility in the laboratory with current laser technologies.
Genetic algorithm enhanced by machine learning in dynamic aperture optimization
Not Available
Online storage ring optimization using dimension-reduction and genetic algorithms
Not Available
Computational design of nanoclusters by property-based genetic algorithms: Tuning the electronic properties of ( TiO 2 ) n clusters
Not Available
Simultaneous optimization of the cavity heat load and trip rates in linacs using a genetic algorithm
Not Available
Co-Optimization of Boost Converter Reliability and Volumetric Power Density Using Genetic Algorithm.
Abstract not provided.
AN AUTOMATED MACHINE LEARNING-GENETIC ALGORITHM FRAMEWORK WITH ACTIVE LEARNING FOR DESIGN OPTIMIZATION
The use of machine learning (ML)-based surrogate models is a promising technique to significantly accelerate simulation-driven design optimization of internal combustion (IC) engines, due to the high computational cost of running computational fluid dynamics (CFD) simulations. However, training the ML models requires hyperparameter selection, which is often done using trial-and-error and domain expertise. Another challenge is that the data required to train these models are often unknown a priori. In this work, we present an automated hyperparameter selection technique coupled with an active learning approach to address these challenges. The technique presented in this study involves the use of a Bayesian approach to optimize the hyperparameters of the base learners that make up a super learner model. In addition to performing hyperparameter optimization (HPO), an active learning approach is employed, where the process of data generation using simulations, ML training, and surrogate optimization is performed repeatedly to refine the solution in the vicinity of the predicted optimum. The proposed approach is applied to the optimization of a compression ignition engine with control parameters relating to fuel injection, in-cylinder flow, and thermodynamic conditions. It is demonstrated that by automatically selecting the best values of the hyperparameters, a 1.6% improvement in merit value is obtained, compared to an improvement of 1.0% with default hyperparameters. Overall, the framework introduced in this study reduces the need for technical expertise in training ML models for optimization while also reducing the number of simulations needed for performing surrogate-based design optimization.