Engineering Papers⌕ Search

SEARCH · Engineering Papers

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.

At least 325 records · Page 18

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.↗

A Novel Resilience-Oriented Cellular Grid Formation Approach for Distribution Systems with Behind-the-Meter Distributed Energy Resources

This paper presents a resilience-oriented cellular grid formation approach to achieve scalable and reconfigurable community microgrid operations for distribution systems with behind-the-meter distributed energy resources. A set of interconnected solar photovoltaics, energy storage systems, and load is termed as a cell, implying a subset of the grid that can operate independently using its own resources. Cells are identified such that each cell inherently has sufficient energy resources to black start and can provide a certain level of backup power for its load under the loss of utility power supply. The proposed cell formation approach builds on a unique self-organizing map-based method (SomRes) to quantify a system's resilience. Using SomRes and a non-dominated sorting-based genetic algorithm (NSGA-II), a fast and efficient cell formation algorithm is developed to identify cells in a distribution system that are resilient against extreme events. The efficacy of the proposed approach is demonstrated on a numerical model of a real distribution feeder in Colorado, United States.

distributed energy resource↗

Structures and stability of metal-doped Ge n M (n = 9, 10) clusters

The lowest-energy structures of neutral and cationic Ge n M (n = 9, 10; M = Si, Li, Mg, Al, Fe, Mn, Pb, Au, Ag, Yb, Pm and Dy) clusters were studied by genetic algorithm (GA) and first-principles calculations. The calculation results show that doping of the metal atoms and Si into Ge 9 and Ge 10 clusters is energetically favorable. Most of the metal-doped Ge cluster structures can be viewed as adding or substituting metal atom on the surface of the corresponding ground-state Ge n clusters. However, the neutral and cationic FeGe 9,10 ,MnGe 9,10 and Ge 10 Al are cage-like with the metal atom encapsulated inside. Such cage-like transition metal doped Ge n clusters are shown to have higher adsorption energy and thermal stability. Our calculation results suggest that Ge 9,10 Fe and Ge 9 Si would be used as building blocks in cluster-assembled nanomaterials because of their high stabilities.

77 NANOSCIENCE AND NANOTECHNOLOGY↗

Structures and magnetic properties of Co-Zr-B magnets studied by first-principles calculations

The structures and magnetic properties of Co-Zr-B alloys near the composition of Co{sub 5}Zr with B at. % ≤6% were studied using adaptive genetic algorithm and first-principles calculations. The energy and magnetic moment contour maps as a function of chemical composition were constructed for the Co-Zr-B magnet alloys through extensive structure searches and calculations. We found that Co-Zr-B system exhibits the same structure motif as the “Co{sub 11}Zr{sub 2}” polymorphs, and such motif plays a key role in achieving strong magnetic anisotropy. Boron atoms were found to be able to substitute cobalt atoms or occupy the “interruption” sites. First-principles calculations showed that the magnetocrystalline anisotropy energies of the boron-doped alloys are close to that of the high-temperature rhombohedral Co{sub 5}Zr phase and larger than that of the low-temperature Co{sub 5.25}Zr phase. Our calculations provide useful guidelines for further experimental optimization of the magnetic performances of these alloys.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Prediction of crystal structures and motifs in the Fe–Mg–O system at Earth’s core pressures

Abstract Fe, Mg, and O are among the most abundant elements in terrestrial planets. While the behavior of the Fe–O, Mg–O, and Fe–Mg binary systems under pressure have been investigated, there are still very few studies of the Fe–Mg–O ternary system at relevant Earth’s core and super-Earth’s mantle pressures. Here, we use the adaptive genetic algorithm (AGA) to study ternary Fe x Mg y O z phases in a wide range of stoichiometries at 200 GPa and 350 GPa. We discovered three dynamically stable phases with stoichiometries FeMg 2 O 4 , Fe 2 MgO 4, and FeMg 3 O 4 with lower enthalpy than any known combination of Fe–Mg–O high-pressure compounds at 350 GPa. With the discovery of these phases, we construct the Fe–Mg–O ternary convex hull. We further clarify the composition- and pressure-dependence of structural motifs with the analysis of the AGA-found stable and metastable structures. Analysis of binary and ternary stable phases suggest that O, Mg, or both could stabilize a BCC iron alloy at inner core pressures.

Wang, Renhai↗

DeepHyper: Asynchronous Hyperparameter Search for Deep Neural Networks

Hyperparameters employed by deep learning (DL) methods play a substantial role in the performance and reliability of these methods in practice. Unfortunately, finding performance-optimizing hyperparameter settings is a notoriously difficult task. Hyperparameter search methods typically have limited production-strength implementations or do not target scalability within a highly parallel machine, portability across different machines, experimental comparison between different methods, and tighter integration with workflow systems. In this paper, we present DeepHyper, a Python package that provides a common interface for the implementation and study of scalable hyperparameter search methods. It adopts the Balsam workflow system to hide the complexities of running large numbers of hyperparameter configurations in parallel on high-performance computing (HPC) systems. We implement and study asynchronous model-based search methods that consist of sampling a small number of input hyperparameter configurations and progressively fitting surrogate models over the input-output space until exhausting a user-defined budget of evaluations. We evaluate the efficacy of these methods relative to approaches such as random search, genetic algorithms, Bayesian optimization, and hyperband on DL benchmarks on CPU- and GPU-based HPC systems.

Balaprakash, Prasanna↗

Digital twin framework for PIP-II linac: AI-driven multi-scale modeling from ion source to 800 MeV

The PIP-II superconducting linac at Fermilab is designed to deliver multi-megawatt proton beams for neutrino physics and other high-intensity applications. To expedite commissioning and enhance operational reliability, we have developed an EPICS-based data flow framework that seamlessly integrates digital twins (DT) with physical twins (PT). These digital twins comprise high-fidelity beam dynamics models or data-driven surrogate models connected to their physical counterparts through real-time diagnostics and advanced machine-learning algorithms.Central to this framework is Linac_Gen, an accelerated simulation tool that incorporates convolutional neural networks, random forests, and genetic algorithms to provide up to a tenfold speedup in optimizing the accelerator geometry model. An EPICS translator layer ensures interoperability by efficiently mapping lattice parameters across diverse simulation platforms.Our EPICS-based framework supports multiple operational modes—monitoring, passive learning, closed-loop control, and online learning—covering the entire machine lifecycle. By leveraging HPC resources and multi-objective optimization techniques, the digital twin enables adaptive trajectory correction, real-time fault detection, and predictive modeling of beam stability. This comprehensive approach paves the way for robust, high-intensity operation and data-driven accelerator R&D at Fermilab.

Pathak, Abhishek [Fermilab]↗

Developing a Descriptor-Based Approach for CO and NO Adsorption Strength to Transition Metal Sites in Zeolites

The discovery of new materials tailored for a given application typically requires the screening of a large number of compounds, and this process can be significantly accelerated by computational analysis. In such an approach the performance of a compound is correlated to a materials property, a so-called descriptor. Here we develop a descriptor-based approach for the adsorption of CO and NO to Cu, Ni, Co, and Fe sites in zeolites. Here we start out by discussing a possible design strategy for zeolite catalysts, define the studied test set of sites in the zeolites SSZ-13 and mordenite, and define a set of appropriate descriptors. In a subsequent step we use these descriptors in single-parameter, two-parameter, and multiparameter regression analysis and finally use a machine-learning genetic algorithm to reduce the number of variables. We find that one or two descriptors are not sufficient to accurately capture the interactions between molecules and metal centers in zeolites, and indeed a multiparameter approach is necessary. Even though many of the descriptors are directly correlated, we identify the position of the s orbital and the number of valence electrons of the active site as well as the HOMO–LUMO gap of the adsorbate as most important descriptors. Furthermore, the reconstruction of the active sites upon adsorption plays a crucial role, and when it is explicitly included in the analysis, correlations improve significantly. In the future we expect that the fundamental methodology developed here will be adapted and transferred to selected problems in adsorption and catalysis and will assist the rational design of materials for the given application.

36 MATERIALS SCIENCE↗

Augmenting Microarray Data with Literature-Based Knowledge to Enhance Gene Regulatory Network Inference

Gene regulatory networks are a crucial aspect of systems biology in describing molecular mechanisms of the cell. Various computational models rely on random gene selection to infer such networks from microarray data. While incorporation of prior knowledge into data analysis has been deemed important, in practice, it has generally been limited to referencing genes in probe sets and using curated knowledge bases. We investigate the impact of augmenting microarray data with semantic relations automatically extracted from the literature, with the view that relations encoding gene/protein interactions eliminate the need for random selection of components in non-exhaustive approaches, producing a more accurate model of cellular behavior. A genetic algorithm is then used to optimize the strength of interactions using microarray data and an artificial neural network fitness function. The result is a directed and weighted network providing the individual contribution of each gene to its target. For testing, we used invasive ductile carcinoma of the breast to query the literature and a microarray set containing gene expression changes in these cells over several time points. Our model demonstrates significantly better fitness than the state-of-the-art model, which relies on an initial random selection of genes. Comparison to the component pathways of the KEGG Pathways in Cancer map reveals that the resulting networks contain both known and novel relationships. The p53 pathway results were manually validated in the literature. 60% of nonKEGG relationships were supported (74% for highly weighted interactions). The method was then applied to yeast data and our model again outperformed the comparison model. Our results demonstrate the advantage of combining gene interactions extracted from the literature in the form of semantic relations with microarray analysis in generating contribution-weighted gene regulatory networks. This methodology can make a significant contribution to understanding the complex interactions involved in cellular behavior and molecular physiology.

59 BASIC BIOLOGICAL SCIENCES↗

Optimal sensor placement for reconstructing wind pressure field around buildings using compressed sensing

Deciding how to optimally deploy sensors in a large, complex, and spatially extended structure is critical to ensure that the surface pressure field is accurately captured for subsequent analysis and design. In some cases, reconstruction of missing data is required in downstream tasks such as the development of digital twins. Here, this paper presents a data-driven sparse sensor selection algorithm, aiming to provide the most information contents for reconstructing aerodynamic characteristics of wind pressures over tall building structures parsimoniously. The algorithm first fits a set of basis functions to the training data, then applies a computationally efficient QR algorithm that ranks existing pressure sensors in order of importance based on the state reconstruction to this tailored basis. The findings of this study show that the proposed algorithm successfully re- constructs the aerodynamic characteristics of tall buildings from sparse measurement locations, generating stable and optimal solutions across a range of conditions. As a result, this study serves as a promising first step toward leveraging the success of data-driven and machine learning algorithms to supplement traditional genetic algorithms currently used in wind engineering.

42 ENGINEERING↗

Storage ring nonlinear dynamics optimization with multi-objective multi-generation Gaussian process optimizer

Nonlinear beam dynamics optimization is essential in a low emittance storage ring design. Multi-objective optimization algorithms are needed in order to simultaneously optimize the dynamic aperture and the momentum aperture. In this study we demonstrate the application of a highly efficient stochastic optimization algorithm, the multi-generation Gaussian process optimizer (MG-GPO), to storage ring nonlinear dynamics optimization by successfully applying the method to the SPEAR3 upgrade lattice. It is shown that the new method, owing to its capability of selecting high rank candidates from a large number of trial solutions, converges significantly faster than the commonly used traditional algorithms, multi-objective genetic algorithms (MOGA) and particle swarm optimization (PSO).

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Comments on “Failure analysis of corroded hydrogen-blended natural gas pipelines based on finite element analysis and genetic algorithm-back propagation neural network” [262 (2025) 111174]

This is a brief commentary paper to highlight and discuss the determination of hydrogen concentration in pipeline steel, effect of hydrogen embrittlement (HE) on the mechanical properties of the material, burst strength of corroded pipelines using finite element analysis (FEA) simulations, and curve-fit models for assessing remaining strength of X80 corroded pipelines for transporting hydrogen blended natural gas. Recently, Xie et al. [1] proposed a methodology to quantify the impact of HE on material properties and numerically determined burst pressure of X80 corroded pipelines. However, their HE quantification overestimated the degradation of tensile strength for hydrogen blending ratios beyond the original data range, and their FEA results of burst pressure are nonconservative. This work thus recharacterized the hydrogen concentration in the steel pipeline and the effect of HE on tensile strength, and then redetermined burst pressures for a set of typical corrosion defect cases considered by Xie et al. [1] based on an experimentally validated FEA modelling method. With the new FEA results, two empirical corrosion models were proposed for X80 corroded pipelines for hydrogen service. At zero hydrogen blending ratio, the novel empirical models predict burst pressures to be consistent with the industry-accepted corrosion models. Furthermore, both the numerical simulation method and the novel corrosion models are significant contributions to the pipeline industry and the hydrogen community. Application of these results will enhance the safety, reliability, and integrity of natural gas pipelines when used to transport hydrogen.

Burst pressure prediction↗

Ambient temperature modelling with soft computing techniques

This paper proposes a hybrid approach based on soft computing techniques in order to estimate monthly and daily ambient temperature. Indeed, we combine the back-propagation (BP) algorithm and the simple Genetic Algorithm (GA) in order to effectively train artificial neural networks (ANN) in such a way that the BP algorithm initialises a few individuals of the GA's population. Experiments concerned monthly temperature estimation of unknown places and daily temperature estimation for thermal load computation. Results have shown remarkable improvements in accuracy compared to traditional methods. (author)

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

A simulation-optimization model for Stone column-supported embankment stability considering rainfall effect

Landslide due to rainfall has been and continues to be one of the most important concerns of geotechnical engineering. The paper presents the variation of factor of safety of stone column-supported embankment constructed over soft soil due to change in water level for an incessant period of rainfall. A combined simulation-optimization based methodology has been proposed to predict the critical surface of failure of the embankment and to optimize the corresponding factor of safety under rainfall conditions using an evolutionary genetic algorithm NSGA-II (Non-Dominated Sorted Genetic Algorithm-II). It has been observed that the position of water table can be reliably estimated with varying periods of infiltration using developed numerical method. The parametric study is presented to study the optimum factor of safety of the embankment and its corresponding critical failure surface under the steady-state infiltration condition. Results show that in case of floating stone columns, period of infiltration has no effect on factor of safety. Even critical failure surfaces for a particular floating column length remain same irrespective of rainfall duration.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Automatic Layout Design for Power Module

The layout of power modules is one of the key points in power module design, especially for high power densities, where couplings are increased. In this paper, along with the design example, an automatic design processes by using a genetic algorithm are presented. Some practical considerations and implementations are introduced in the optimization of module layout design.

42 ENGINEERING↗

Evaluating Optimization Strategies for Engine Simulations Using Machine Learning Emulators

This work evaluates different optimization algorithms for computational fluid dynamics (CFD) simulations of engine combustion. Due to the computational expense of CFD simulations, emulators built with machine learning algorithms were used as surrogates for the optimizers. Two types of emulators were used: a Gaussian process (GP) and a weighted variety of machine learning methods called SuperLearner (SL). The emulators were trained using a dataset of 2048 CFD simulations that were run concurrently on a supercomputer. The design of experiments (DOE) for the CFD runs was obtained by perturbing nine input parameters using a Monte-Carlo method. The CFD simulations were of a heavy duty engine running with a low octane gasoline-like fuel at a partially premixed compression ignition mode. Ten optimization algorithms were tested, including types typically used in research applications. Each optimizer was allowed 800 function evaluations and was randomly tested 100 times. The optimizers were evaluated for the median, minimum, and maximum merits obtained in the 100 attempts. Some optimizers required more sequential evaluations, thereby resulting in longer wall clock times to reach an optimum. The best performing optimization methods were particle swarm optimization (PSO), differential evolution (DE), GENOUD (an evolutionary algorithm), and micro-genetic algorithm (GA). These methods found a high median optimum as well as a reasonable minimum optimum of the 100 trials. Moreover, all of these methods were able to operate with less than 100 successive iterations, which reduced the wall clock time required in practice. Two methods were found to be effective but required a much larger number of successive iterations: the DIRECT and MALSCHAINS algorithms. A random search method that completed in a single iteration performed poorly in finding optimum designs but was included to illustrate the limitation of highly concurrent search methods. The last three methods, Nelder–Mead, bound optimization by quadratic approximation (BOBYQA), and constrained optimization by linear approximation (COBYLA), did not perform as well.

Probst, Daniel M.↗

A multiple-alignment based primer design algorithm for genetically highly variable DNA targets

Background: Primer design for highly variable DNA sequences is difficult, and experimental success requires attention to many interacting constraints. The advent of next-generation sequencing methods allows the investigation of rare variants otherwise hidden deep in large populations, but requires attention to population diversity and primer localization in relatively conserved regions, in addition to recognized constraints typically considered in primer design. Results: Design constraints include degenerate sites to maximize population coverage, matching of melting temperatures, optimizing de novo sequence length, finding optimal bio-barcodes to allow efficient downstream analyses, and minimizing risk of dimerization. To facilitate primer design addressing these and other constraints, we created a novel computer program (PrimerDesign) that automates this complex procedure. We show its powers and limitations and give examples of successful designs for the analysis of HIV-1 populations. Conclusions: PrimerDesign is useful for researchers who want to design DNA primers and probes for analyzing highly variable DNA populations. It can be used to design primers for PCR, RT-PCR, Sanger sequencing, next generation sequencing, and other experimental protocols targeting highly variable DNA samples.

59 BASIC BIOLOGICAL SCIENCES↗