Search NASA⌕ Search

SEARCH · Search NASA

Results for “Genetic algorithm”

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 127 records · Page 7
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Aerial drone fleet deployment optimization with endogenous battery replacements for direct delivery of time-sensitive products

Aerial drones offer a distinct potential to reduce the delivery time and energy consumption for the delivery of time-sensitive and small products. However, there is still a need in the relevant industry to understand the performance of drone-based delivery under different business needs and drone operating conditions. We studied a drone deployment optimization problem for direct delivery of time-sensitive products with release dates to customers maintaining a specified time window. This paper presents a new mixed-integer programming model, new valid inequalities, a new greedy heuristic algorithm, and a Genetic algorithm to help business owners optimally schedule and route their drone fleet minimizing the required fleet size, the required number of additional batteries, and total energy consumption. A realistic feature of the optimization method is that instead of replacing the drone battery after each return to the depot, it keeps track of the remaining energy in the drone battery and decides on battery replacements accounting for the drone routing and the user-specified minimum required battery energy. Numerical results based on real data from drone flight tests and prepared food delivery industry provide insights into the effect of different practical drone operating parameters on the required fleet size, the required number of battery replacements, and energy consumption. Here, results demonstrate that the proposed heuristic algorithm substantially outperforms the accelerated CPLEX in runtime while sacrificing the solution quality by a small amount. Additionally, results show that using a mixed fleet of hexacopter and quadcopter drones reduces the total energy consumption by 48.52% compared to using a homogeneous fleet of only hexacopters.

Drone energy consumption↗
DOE OSTI2026

Digital Twin Based Condition Monitoring of LCC-LCC Inductive Power Transfer Systems

Inductive power transfer (IPT) systems provide a flexible, hands-free charging opportunity to electric vehicles (EV). The resonant network components and the transmitter and receiver coils are often subjected to high voltages or currents. Component aging in the compensation network and coils of resonant IPT systems is detrimental to the reliability and power transfer efficiency of the IPT system. Monitoring the component health of such multi-element complex systems requires robust optimization algorithms. This paper discusses condition monitoring of a resonant IPT system for an EV charger using a digital twin model. A hybrid estimation algorithm based on genetic algorithms and adaptive particle swarm optimization is developed to estimate the parameters of the digital twin model. Simulation results are used to verify the monitoring capabilities of the developed algorithm under various operating conditions of the IPT system.

Weldehawaryat, Lidya Mussie [graduate research ass↗
DOE OSTI2025

Explainable and Differentiable Reinforcement Learning for Multi-objective Optimization in Particle Accelerators

Operating particle accelerators involves optimizing multiple goals simultaneously, which can be challenging due to trade-offs among objectives. While evolutionary algorithms like the genetic algorithm (GA) have been used for various Multi-Objective Optimization (MOO) tasks, they are not inherently suited for complex control problems. This talk highlights two variations of Reinforcement Learning (RL) for concurrently optimizing heat load and trip rates at the Continuous Electron Beam Accelerator Facility (CEBAF). The problem involves strict constraints on individual states, actions, and overall energy requirements of the beam. First, this talk highlights how differentiability can be harnessed through a Deep Differentiable Reinforcement Learning (DDRL) approach to address MOO issues within particle accelerators. We examine the DDRL method alongside Model Free Reinforcement Learning (MFRL), GA, and Bayesian Optimization (BO). The performance of these methods is assessed by generating a Pareto-front for two objectives. Our findings indicate that DDRL excels in handling high-dimensional problems more effectively than MFRL, BO, and GA. Next, we will show integration of explainable physics-based constraints into RL algorithms to enhance trans- parency and trust in decision-making processes by enabling users to verify that agents adhere to established physical principles. This surrogate function can be modeled using neural networks or sparse dictionary mod- els. By examining the mathematical form of the learned constraint function, we are able to confirm the agent has learned to use the established physics of each environment provided but the surrogate model. In addi- tion, we find that the introduction of a mathematical functional dictionary based surrogate model enables our reinforcement learning algorithms to reliably converge for difficult high-dimensional accelerator controls environments.

Rajput, Kishansingh [Thomas Jefferson National Acc↗
DOE OSTI2025

RLMolLM: Reinforcement Learning-Enhanced Language Model Framework for Inverse Molecular Design

Inverse molecular design faces significant challenges due to vast chemical space and complex property requirements. While language models show promise for molecular generation, they struggle with validity, multi-property optimization, and structural constraints. This work presents RLMolLM, a reinforcement learning framework combining Proximal Policy Optimization (PPO) with genetic algorithms to address these limitations. Our approach optimizes multiple user-specified properties including quantitative estimates of drug-likeness (QED), synthetic accessibility (SA), and ADMET (absorption, distribution, metabolism, excretion, and toxicity) endpoints without requiring complete model retraining, while maintaining capability for scaffold-constrained generation where specific substructures must be preserved. We outperform state-of-the-art methods for molecular optimization, achieving best QED scores across GDB13, Moses, and Zinc datasets with up to 31% improvement over previous methods while maintaining excellent validity, uniqueness, and novelty metrics. For simultaneous multi-property optimization, our framework achieves substantial improvements in ADMET properties including 4.5-fold reduction in hERG toxicity and enhanced Caco-2 permeability compared to Moses dataset. Under structural constraints, the framework significantly improves molecular validity while preserving scaffolds and effectively optimizing properties. In conclusion, this versatile solution advances pharmaceutical and materials molecular design through effective integration of reinforcement learning and genetic algorithms with multi-property optimization and scaffold preservation.

Genetic algorithms↗
DOE OSTI2021

Optimization of microwave emission from laser filamentation with a machine learning algorithm

We demonstrate that is it possible to optimize the yield of microwave radiation from plasmas generated by laser filamentation in atmosphere through manipulation of the laser wavefront. A genetic algorithm controls a deformable mirror that reconfigures the wavefront using the microwave waveform amplitude as feedback. Optimization runs performed as a function of air pressure show that the genetic algorithm can double the microwave field strength relative to when the mirror surface is flat. Here, an increase in the volume and brightness of the plasma fluorescence accompanies the increase in microwave radiation, implying an improvement in the laser beam intensity profile through the filamentation region due to the optimized wavefront.

Englesbe, Alexander↗
DOE OSTI2024

Linac_Gen: Integrating Machine Learning and Particle-in-Cell Methods for Enhanced Beam Dynamics at Fermilab

Here, we introduce Linac_Gen, a tool developed at Fermilab, which combines machine learning algorithms with Particle-in-Cell methods to advance beam dynamics in linacs. Linac_Gen employs techniques such as Random Forest, Genetic Algorithms, Support Vector Machines, and Neural Networks, achieving a tenfold increase in speed for phase-space matching in Linacs over traditional methods, through the use of genetic algorithms. Crucially, Linac_Gen's adept handling of 3D field maps elevates the precision and realism in simulating beam instabilities and resonances, marking a key advancement in the field. Benchmarked against established codes, Linac_Gen demonstrates not only improved efficiency and precision in beam dynamics studies but also in the design and optimization of Linac systems, as evidenced in its application to Fermilab's PIP-II Linac project. This work represents a notable advancement in accelerator physics, marrying ML with PIC methods to set new standards for efficiency and accuracy in accelerator design and research. Linac_Gen exemplifies a novel approach in accelerator technology, offering substantial improvements in both theoretical and practical aspects of beam dynamics.

43 PARTICLE ACCELERATORS↗
DOE OSTI2024

Linac_Gen: integrating machine learning and particle-in-cell methods for enhanced beam dynamics at Fermilab

Here, we introduce Linac_Gen, a tool developed at Fermilab, which combines machine learning algorithms with Particle-in-Cell methods to advance beam dynamics in linacs. Linac_Gen employs techniques such as Random Forest, Genetic Algorithms, Support Vector Machines, and Neural Networks, achieving a tenfold increase in speed for phase-space matching in linacs over traditional methods through the use of genetic algorithms. Crucially, Linac_Gen's adept handling of 3D field maps elevates the precision and realism in simulating beam instabilities and resonances, marking a key advancement in the field. Benchmarked against established codes, Linac_Gen demonstrates not only improved efficiency and precision in beam dynamics studies but also in the design and optimization of linac systems, as evidenced in its application to Fermilab's PIP-II linac project. This work represents a notable advancement in accelerator physics, marrying ML with PIC methods to set new standards for efficiency and accuracy in accelerator design and research. Linac_Gen exemplifies a novel approach in accelerator technology, offering substantial improvements in both theoretical and practical aspects of beam dynamics.

43 PARTICLE ACCELERATORS↗
DOE OSTI2021

Gradient-Informed Design Optimization of Select Nuclear Systems

In this work, we present a gradient-informed design optimization of nuclear reactor core components based on neutronics objectives with both continuous and discrete materials. The main argument in favor of using gradient-informed design optimization is that it scales well with increasing dimensionality of the design space. First, a challenge problem with 121 free parameters is solved with a gradient-informed method and then with a genetic algorithm. Then, a challenge problem to optimize the flux profile of a simplified assembly with eight axial zones is solved. Both challenge problems are solved using directly calculated derivatives from Tools for Sensitivity and Uncertainty Analysis Methodology Implementation (TSUNAMI) in the SCALE package. Furthermore, we demonstrate how a discrete optimization problem—selection of materials for 121 voxels—can be lifted into a continuous problem with mixed materials. In the continuous space, adjoint-based gradients are well-defined, and gradient descent is applicable. Then, a forcing function is introduced that with the selection of an appropriately sized hyperparameter can be used to guide the optimized continuous solution back into a discrete solution. This paper presents an account of the challenges that were faced when applying a gradient-informed optimization algorithm using a Monte Carlo calculation to estimate the gradient information and compares a gradient descent optimization method to a genetic algorithm optimization of the same geometry. Overall, this work demonstrates the potential use of adjoint-based gradient calculations in design optimization of nuclear systems.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2020

Proposed design and optimization of a higher harmonic cavity for ALS-U

Higher harmonic cavities (HHCs), also known as Landau cavities, have been proposed to increase the beam lifetime and Landau damping by lengthening the bunch and increasing the synchrotron tune spread. Here, we present an optimized 1.5 GHz normal conducting HHC design for the Advanced Light Source Upgrade project at Lawrence Berkeley National Lab with a superconducting-like geometry for lower R/Q. The optimization goal is to reach the required shunt impedance while maintaining a relatively high Q value of the cavities. A multi-objective genetic algorithm (MOGA)-based optimization process is applied to optimize the radio frequency (RF) design. This study serves as an example of how a genetic algorithm can be used to optimize RF cavities. Detailed exploration and characterization of the MOGA-based RF cavity optimization have been demonstrated from the aspects of minimizing the coupled bunch instabilities and analyzing the higher-order modes and the corresponding impedance of the HHC.

Feng, H. (ORCID:0000000319392692)↗
DOE OSTI2024

Reducing Richtmyer–Meshkov instability jet velocity via inverse design

In this work, we detail a novel application of inverse design and advanced manufacturing to rapidly develop and experimentally validate modifications to a shaped charge jet analog. The shaped charge jet analog comprises a copper liner, a high explosive (HE), and a silicone buffer. Here, we apply a genetic algorithm to determine an optimal buffer design that can be placed between the liner and the HE that results in the largest possible change in jet velocity. The use of a genetic algorithm allows for discoveries of unintuitive, complex, yet optimal buffer designs. Experiments using the optimal design verified the effectiveness of the buffer and validated the machine learning approach to hydrodynamic design optimization.

36 MATERIALS SCIENCE↗
DOE OSTI2022

HPS-RL: Hyperparameter tuning for deep RL applications (HPS-RL) v1

Genetic Algorithms meets Deep RL for Hyperparameters Hyperparameter optimization and architecture search can easily become cumbersome and finding the right hyperparameters can seriously impact the robustness of the deep RL application being developed. We use genetic algorithms to evolve optimum deep RL architectures in a scalable manner. HPS-RL is designed to work with multiple gym enviornments, allow users to test their own optimization functions and tune multi-objective parameters in multiple deep RL algorithms. HPS-RL uses multi-threading and is being extended with mpipy for distributed processing on HPC. https://arxiv.org/abs/2201.11182

Kiran, Mariam↗
DOE OSTI2026

Accelerating Traction Motor Optimization Design with AI Surrogate Models

The advancement of artificial intelligence systems enables the use of data-driven physics-based surrogate models to explore design spaces rapidly and deeply for engineering projects. This work presents a surrogate model workflow that accelerates electric traction motor design optimization by replacing finite element analysis (FEA) with an artificial neural network (ANN) and using this model in a genetic algorithm for design optimization. A baseline interior permanent-magnet motor is parameterized and sampled to generate FEA-labeled training data, after which a feed-forward ANN predicts key outputs (e.g., loss components and weight). The validated surrogate enables genetic-algorithm optimization and deep search over the design space without new FEA runs, producing Pareto-optimal trade-offs between weight and losses and set of optimized designs for rapid downselection of manufacturable motor designs.

Ribeiro, Pedro [ORNL] (ORCID:0009000921026641)↗
DOE OSTI2024

Correlated Anion Disorder in Heteroanionic Cubic TiOF 2

Resolving anion configurations in heteroanionic materials is crucial for understanding and controlling their properties. For anion-disordered oxyfluorides, conventional Bragg diffraction cannot fully resolve the anionic structure, necessitating alternative structure determination methods. We have investigated the anionic structure of anion-disordered cubic (ReO 3 -type) TiOF 2 using X-ray pair distribution function (PDF), 19 F MAS NMR analysis, density functional theory (DFT), cluster expansion modeling, and genetic-algorithm structure prediction. Our computational data predict short-range anion ordering in TiOF 2 , characterized by predominant cis-[O 2 F 4 ] titanium coordination, resulting in correlated anion disorder at longer ranges. To validate our predictions, we generated partially disordered supercells using genetic-algorithm structure prediction and computed simulated X-ray PDF data and 19 F MAS NMR spectra, which we compared directly to experimental data. To construct our simulated 19 F NMR spectra, we derived new transformation functions for mapping calculated magnetic shieldings to predicted magnetic chemical shifts in titanium (oxy)fluorides, obtained by fitting DFT-calculated magnetic shieldings to previously published experimental chemical shift data for TiF 4 . We find good agreement between our simulated and experimental data, which supports our computationally predicted structural model and demonstrates the effectiveness of complementary experimental and computational techniques in resolving anionic structure in anion-disordered oxyfluorides. From additional DFT calculations, we predict that increasing anion disorder makes lithium intercalation more favorable by, on average, up to 2 eV, highlighting the significant effect of variations in short-range order on the intercalation properties of anion-disordered materials.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Model-informed, Adaptive Physical Vapor Deposition to Fabricate Hierarchical Binary-alloy Thin-films

Designing next generation thin films, tailor-made for specific applications, relies on the availability of robust processing-structure-property relationships. Traditional structure zone diagrams are limited to low-dimensional mappings, with machine-learning methods only recently attempting to relate multiple processing parameters to the final microstructure. Despite this progress, structure-processing relationships are unknown for processing conditions that vary during thin-film deposition, limiting the range of microstructures and properties achievable. In this project, we employed a phase-field computational model combined with a genetic algorithm (GA) to identify and design time-dependent processing protocols that achieve tailor-made microstructures. We simulate the physical vapor deposition of a binary-alloy thin film by employing a phase-field model, where deposition rates and diffusivities are controlled via the genetic algorithm. Our GA-guided protocols achieve targeted microstructures with lateral and vertical concentration modulations, as well as more complex, hierarchical microstructures previously not described in simple structure zone diagrams. Our algorithm provides insight to experimentalists looking for additional avenues to design novel thin-film microstructures.

36 MATERIALS SCIENCE↗
DOE OSTI2026

GBOpt: Grain boundary structure optimization using Monte Carlo and evolutionary algorithms

Polycrystalline materials are made of many small crystals separated by grain boundaries (GBs), whose atomic structure strongly influences material properties. Because the structure of a GB determines its properties, the optimal structure must be known in order to determine those impacts. There are many ways of placing atoms in the GB region, but the optimal structure is defined as the one that gives the lowest value of a target property (typically energy). GB structure optimization has been successfully demonstrated using stochastic and evolutionary methods, but no reusable, community-maintained open-source workflow has been developed. GBOpt (Grain Boundary Optimization) is an open-source Python package that creates that workflow, where we have presently implemented two approaches: Markov Chain Monte Carlo, and genetic algorithm based on elite selection. We demonstrate this capability by successfully reproducing the known optimal structures of a specific GB in two materials, and point interested readers to the GitHub repository for additional examples, including optimization for different properties. Both of the implemented approaches recovered the known structures, with the genetic algorithm approach finding the optimal structure faster on average.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2021

Filament-induced breakdown spectroscopy signal enhancement using optical wavefront control

Filament-induced breakdown spectroscopy (FIBS) is an analytical method that holds significant promise for remote sensing. In FIBS, it is desirable to maximize the intensity and improve the reproducibility of a selected spectroscopic feature. Here, we demonstrate the use of wavefront control in conjunction with a genetic algorithm in FIBS of metallic copper and show that this approach can increase the efficacy of filament-induced breakdown signal production. Through wavefront optimization, we enhance the intensity of a chosen characteristic spectroscopic feature of copper by a factor of approximately 3 when performing filamentation over a 1-meter distance. The relative standard deviation of signal intensity is reduced from ~17% to ~12% after optimization. We find that modification of the wavefront by introduction of astigmatism and coma maximizes the signal intensity, and these aberrations appear in two distinct trials of the genetic algorithm. We compare these findings to previous work on multiple filament control and discuss the possible mechanisms that lead to signal enhancement associated with both the beam amplitude and phase profile. A broader use of wavefront control with feedback may improve the performance of FIBS in remote sensing applications.

42 ENGINEERING↗
DOE OSTI2023

Stochastic optimization of a uranium oxide reaction mechanism using plasma flow reactor measurements

Abstract In this work, a coupled Monte Carlo Genetic Algorithm (MCGA) approach is used to optimize a gas phase uranium oxide reaction mechanism based on plasma flow reactor (PFR) measurements. The PFR produces a steady Ar plasma containing U, O, H, and N species with high temperature regions (3000–5000 K) relevant to observing UO formation via optical emission spectroscopy. A global kinetic treatment is used to model the chemical evolution in the PFR and to produce synthetic emission signals for direct comparison with experiments. The parameter space of a uranium oxide reaction mechanism is then explored via Monte Carlo sampling using objective functions to quantify the model-experiment agreement. The Monte Carlo results are subsequently refined using a genetic algorithm to obtain an experimentally corroborated set of reaction pathways and rate coefficients. Out of 12 reaction channels targeted for optimization, four channels are found to be well constrained across all optimization runs while another three channels are constrained in select cases. The optimized channels highlight the importance of the OH radical in oxidizing uranium in the PFR. This study comprises a first step toward producing a comprehensive experimentally validated reaction mechanism for gas phase uranium molecular species formation.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Language models for the prediction of SARS-CoV-2 inhibitors

The COVID-19 pandemic highlights the need for computational tools to automate and accelerate drug design for novel protein targets. We leverage deep learning language models to generate and score drug candidates based on predicted protein binding affinity. We pre-trained a deep learning language model (BERT) on ∼9.6 billion molecules and achieved peak performance of 603 petaflops in mixed precision. Our work reduces pre-training time from days to hours, compared to previous efforts with this architecture, while also increasing the dataset size by nearly an order of magnitude. For scoring, we fine-tuned the language model using an assembled set of thousands of protein targets with binding affinity data and searched for inhibitors of specific protein targets, SARS-CoV-2 Mpro and PLpro. We utilized a genetic algorithm approach for finding optimal candidates using the generation and scoring capabilities of the language model. Our generalizable models accelerate the identification of inhibitors for emerging therapeutic targets.

Blanchard, Andrew E.↗