Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Games”

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 613 records · Page 34
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Leveraging Multitime Hamilton–Jacobi PDEs for Certain Scientific Machine Learning Problems

Hamilton-Jacobi partial differential equations (HJ PDEs) have deep connections with a wide range of fields, including optimal control, differential games, and imaging sciences. By considering the time variable to be a higher dimensional quantity, HJ PDEs can be extended to the multi-time case. In this paper, we establish a novel theoretical connection between specific optimization problems arising in machine learning and the multi-time Hopf formula, which corresponds to a representation of the solution to certain multi-time HJ PDEs. Through this connection, we increase the interpretability of the training process of certain machine learning applications by showing that when we solve these learning problems, we also solve a multi-time HJ PDE and, by extension, its corresponding optimal control problem. As a first exploration of this connection, we develop the relation between the regularized linear regression problem and the Linear Quadratic Regulator (LQR). We then leverage our theoretical connection to adapt standard LQR solvers (namely, those based on the Riccati ordinary differential equations) to design new training approaches for machine learning. Lastly, we provide some numerical examples that demonstrate the versatility and possible computational advantages of our Riccati-based approach in the context of continual learning, post-training calibration, transfer learning, and sparse dynamics identification.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Foundations of automatic feature extraction at LHC–point clouds and graphs

Abstract Deep learning algorithms will play a key role in the upcoming runs of the Large Hadron Collider (LHC), helping bolster various fronts ranging from fast and accurate detector simulations to physics analysis probing possible deviations from the Standard Model. The game-changing feature of these new algorithms is the ability to extract relevant information from high-dimensional input spaces, often regarded as “replacing the expert” in designing physics-intuitive variables. While this may seem true at first glance, it is far from reality. Existing research shows that physics-inspired feature extractors have many advantages beyond improving the qualitative understanding of the extracted features. In this review, we systematically explore automatic feature extraction from a phenomenological viewpoint and the motivation for physics-inspired architectures. We also discuss how prior knowledge from physics results in the naturalness of the point cloud representation and discuss graph-based applications to LHC phenomenology.

Bhardwaj, Akanksha↗
DOE OSTI2023

Automated Adversary-in-the-Loop Cyber-Physical Defense Planning

Security of cyber-physical systems (CPS) continues to pose new challenges due to the tight integration and operational complexity of the cyber and physical components. To address these challenges, this article presents a domain-aware, optimization-based approach to determine an effective defense strategy for CPS in an automated fashion—by emulating a strategic adversary in the loop that exploits system vulnerabilities, interconnection of the CPS, and the dynamics of the physical components. Our approach builds on an adversarial decision-making model based on a Markov Decision Process (MDP) that determines the optimal cyber (discrete) and physical (continuous) attack actions over a CPS attack graph. The defense planning problem is modeled as a non-zero-sum game between the adversary and defender. We use a model-free reinforcement learning method to solve the adversary’s problem as a function of the defense strategy. We then employ Bayesian optimization (BO) to find an approximate best-response for the defender to harden the network against the resulting adversary policy. This process is iterated multiple times to improve the strategy for both players. We demonstrate the effectiveness of our approach on a ransomware-inspired graph with a smart building system as the physical process. Numerical studies show that our method converges to a Nash equilibrium for various defender-specific costs of network hardening.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Sudoku Online Testing Framework v.0.2

The Sudoku Online Testing Framework provides a configurable basis for testing user interactions to solve visualization-related problems with sudoku puzzles and games. It consists of a server, a client, and test code. The python server implements sudoku puzzle logic and board selection functions. The JavaScript client implements a graphical user interface (GUI) front-end to display the puzzles and facilitate interactions with users. Within the GUI, logical rules may be selected. Cells may be selected to “pivot” on to make a board for each possible value in the cell. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525. SAND2021-6409 O

Leger, Michelle↗
DOE OSTI2021

Exploration ToolKit (ExTK)

The Exploration Toolkit (ExTK) is a reusable Extended Reality (XR) system developed for incorporating and exploring 3-Dimensional (3-D) computer aided design (CAD) models in XR, with a primary focus on Augmented Reality (AR). The ExTK consists of a Developer Mode and a User Mode. In Developer Mode, ExTK provides developers with the ability to easily import 3-D CAD models and activate desired exploration functionality and layout. Multiple models can be added to a single instantiation of the ExTK using Unity's Scene capability. Exploration functions include scaling, rotating, explode/contract, animations, hiding parts, submodules, and measurement functions. In User Mode, ExTK provides a menu system that allows users to select models and initiate exploration functions. ExTK is architected for reusability and developers can customize the ExTK layout and functions according to application needs. ExTK is designed to be hardware agnostic, although initial development focused on the Microsoft HoloLens as the primary deployment platform. The ExTK is developed using the Unity Game Engine Development Platform. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525. SAND2021-1506 O

Klein, BrandonThorin↗
DOE OSTI2021

Sequential Training ToolKit - STTK

Sequential Training ToolKit, or STTK, is a software toolkit plugin for the Unity development platform that enables software developers to easily develop structured Sequential Training applications for gaming and extended reality (XR) environments. STTK is architected to easily import the toolkit as a plugin for the Unity platform and then interact with the graphical user interface (GUI) for drag-and-drop functionality. STTK also includes easy add-on plugins for Prefabs and auto-builds a State Machine. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525. SAND2021-3059 O

Klein, BrandonThorin↗
DOE OSTI2022

Graph-Env

The Graph-Env library provides a framework for adapting graph search problems into OpenAI Gym environments for reinforcement learning. In other words, Graph-Env enables reinforcement learning algorithms to be applied to graph search problems. Graph search problems include molecule and crystal structure design problems; route planning problems, including traveling salesperson problem; puzzles and games, such as chess and go; shortest path problems; minimum spanning tree; vehicle path generation; and others.

Tripp, Charles↗
DOE OSTI2024

Multiplayer Engineering

INL engineers developed a special purpose software framework designed to establish real-time connections between multiple running Unity instances. The framework is developed in Unity, a game engine development platform. This framework programmatically attaches functions to engineering models, enabling users to interact with, observe, and make changes to virtual models. These interactions are broadcasted through websocket connections, and received by other engineers in real-time.

Woodruff, Nathan↗
DOE OSTI2022

Network Defense Workforce Development System

The software implements the methodology of cybersecurity training architecture and is leveraged to build a turn-key based simulated cyberattack game in which the player assumes the facility manager's role and must defend the OT network from adaptive cyberattacks by directly configuring the physical network environment and implementing security policies.

Gourisetti, Sri Nikhil Gupta↗
DOE OSTI2025

POWER DATA PIPELINE

SF-25-081 Utility software for creating high-performance data pipelines to extract, load, and transform raw electric power systems measurements. For use with anomaly detection models training workflows. The software supports the project: Adaptive Cybersecurity for DER: A Game-Theoretic and Machine Learning approach for Real-Time Threat Detection and Mitigation

Plathottam, Silby Jose [Argonne National Laborator↗
DOE OSTI2021

Co-design Center for Exascale Machine Learning Technologies (ExaLearn)

We report rapid growth in data, computational methods, and computing power is driving a remarkable revolution in what variously is termed machine learning (ML), statistical learning, computational learning, and artificial intelligence. In addition to highly visible successes in machine-based natural language translation, playing the game Go, and self-driving cars, these new technologies also have profound implications for computational and experimental science and engineering, as well as for the exascale computing systems that the Department of Energy (DOE) is developing to support those disciplines. Not only do these learning technologies open up exciting opportunities for scientific discovery on exascale systems, they also appear poised to have important implications for the design and use of exascale computers themselves, including high-performance computing (HPC) for ML and ML for HPC. The overarching goal of the ExaLearn co-design project is to provide exascale ML software for use by Exascale Computing Project (ECP) applications, other ECP co-design centers, and DOE experimental facilities and leadership class computing facilities.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

Continuous removal of fission products from molten-salt-fueled reactors

A method based on separation of volatilized molten salt (MS) components, including by mass, is being developed to extract fission products (FPs) from operating molten-salt reactors. The initial application of this method is for accelerator-driven subcritical reactors fueled by (fluorinated molten salt) spent nuclear fuel (UNF) from any past, present, or future reactor. The actinides remain in the subcritical reactor to produce profitable energy and be transmuted while the extracted FPs can be buried without long-lived actinides such that a geologic repository is not necessarily needed to close the nuclear fuel cycle. By removing neutron-absorbing FPs and operating sub-critically, where the restrictive link between operation and criticality is broken, it is possible to envision complete burnup of the UNF fuel. The game-changing feature of continuously processing the molten salt inside the reactor while the reactor operates eliminates the need for a separate reprocessing plant. This feature also simultaneously improves the neutronics of the reactor, increasing the burnup of the fuel and extending its useful life for generating energy. Nuclear nonproliferation and need for geologic repositories are addressed by keeping actinides inside the reactor containment until they are consumed. (authors)

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2022

High-performance and high-fidelity Monte Carlo solutions to the BEAVRS benchmark

The BEAVRS (Benchmark for Evaluation and Validation of Reactor Simulation) benchmark is solved by PRAGMA, the GPU-based continuous energy Monte Carlo code. The resulting solutions are comprised of the detailed simulation results of two cycles, each of which consists of the zero power physics test (ZPPT) and the core depletion calculations. The ZPPT consists of characteristic parameters, such as critical boron concentration (CBC), control rod bank worth, isothermal temperature coefficients, and assembly-wise detector signal, which are compared with measured data provided by the benchmark administration. The core depletion calculations were performed for both the hot full power and the load follow modes, and the comparison was made with the measured or deduced CBCs and assembly-wise detector signals. In the load follow calculations, the operating power history was approximately applied to simulate the real operation as closely as possible. PRAGMA performed the various calculations with a tremendous number of histories ranging up to hundreds of millions per cycle, exploiting GPUs' massively parallel performance. The load follow run time was shorter than 16 hours on a single rack of computing nodes mounded with 24 gaming GPUs with a remarkable agreement with the measurements for most comparisons. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2022

PWR loading pattern optimization with reinforcement learning

The core loading pattern optimization problem belongs to the class of combinatorial optimization problem and has been studied since the dawn of commercial nuclear energy industry. It is characterized by multiple objectives and constraints, with a very high number of candidate patterns, which makes it impossible to solve explicitly. Stochastic optimization methodologies including Genetic Algorithms and Simulated Annealing are used by different nuclear utilities and vendors to perform fuel cycle reload design. Nevertheless, hand-designed solutions continue to be the prevalent method in the industry. To improve the state-of-the-art core reload patterns, we aim to create a method as scalable as possible, that agrees with the designer's goal of performance and safety. To help in this task Deep Reinforcement Learning (DRL), in particular Proximal Policy Optimization is leveraged. DRL has recently experienced a strong impetus from its successes applied to games, sometimes even reaching 'super-human' performances. This paper lays out the foundation of this method and proposes to study the behavior of several hyper-parameters that influence the DRL algorithm. The algorithm is highly dependent on multiple factors such as an exploration/exploitation trade-off that manifests through different parameters such as the number of loading patterns seen and the number of samples collected before a policy update, but also the shape of the objective function derived for the core design. Experimental results also demonstrate the effectiveness of the method in finding high-quality solutions from scratch within a reasonable amount of time. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2026

Post-fire time series of sensor and geochemistry sample data from surface water, groundwater, precipitation, soil, and vegetation across Oak Creek watershed, Washington

This dataset supports a broader study examining wildfire impacts on hydrologic connectivity across 5 sites within the Oak Creek watershed and the resulting biogeochemical impacts. Stream sites were selected using the Advanced Terrestrial Simulator (ATS) hydrologic model to identify locations with varying groundwater contributions and hydrologic responses across different burn severity scenarios. The Retreat Fire burned from July 23 to August 2 in 2024, affecting the five study sites at varying burn severities. Each site is equipped with YSI EXO2 sondes logging sub-hourly throughout the year, and grab samples are collected approximately every six weeks. YSI sondes are used to measure temporally resolved proxies for groundwater inputs (specific conductivity) and organic matter (fluorescent dissolved organic matter; fDOM) along with basic water quality and depth. Grab samples of surface water, groundwater, and precipitation are analyzed for water stable isotopes and conductivity to understand endmembers for hydrologic mixing Grab samples of surface water, groundwater, soil water, and litter/vegetation/soil leachates are analyzed for organic matter composition measured by Fourier-Transform Ion Cyclotron Resonance Mass Spectrometry (FTICR-MS) to understand organic matter dynamics. Game camera photos are provided in a separate data package available at https://data.ess-dive.lbl.gov/datasets/doi:10.15485/3018598. Future versions of this dataset will include time series data from YSI EXO2 sondes (fDOM, dissolved oxygen, temperature, depth, specific conductance, turbidity, pH), BaroTROLL sensors (air temperature and barometric pressure), rain gauges (precipitation), and data from the soil and vegetation samples. Because this study is ongoing, this data package will be updated regularly to include newly collected data and the additional data types. For details on how to navigate data packages generated by this project, see https://data.ess-dive.lbl.gov/portals/PNNLRiverCorridorSFA/About. In addition to a readme, this data package also includes a file-level metadata (FLMD) file that describes each file and a data dictionary (DD) that describes all column/row headers and variable definitions. This dataset is comprised of (1) a folder of field photos; (2) a folder of surface water sample data; (3) a folder of raw Fourier transform ion cyclotron resonance mass spectrometry (FTICR-MS) data; (4) a data checks report; (5) file-level metadata; (6) data dictionary; (7) field metadata; (8) readme; (9) international generic sample number (IGSN) mapping file; and (10) field protocols. The sample data subfolder contains (1) dissolved organic carbon (DOC, measured as non-purgeable organic carbon, NPOC) data and averages; (2) total dissolved nitrogen data and averages; (3) stable water isotopes and averages; (4) methods codes; (5) FTICR-MS methods; and (15) a subfolder of 9.4 Tesla (9.4T) FTICR-MS data. This folder contains the processed data and three subfolders, one containing the .xml files, one containing the water CoreMS output files, and the other containing instructions and scripts for processing the files in CoreMS (https://github.com/EMSL-Computing/CoreMS). All files are .csv, .pdf, .R, .xml, .d, .html, .Rmd, .py, .cal, .json, .jpg, .jpeg, .png, .mov, or .mp4.

Biogeochemistry↗
DOE OSTI2020

Fabrication and testing of high-performance all-metal neutron guides and axisymmetric mirrors by electrochemical replication

Neutron scattering is one of the most useful methods of studying the structure of matter, with applications to biomedical, structural, magnetic and energy-related materials. Neutron-scattering instruments are installed around research reactors or accelerator-based neutron sources, and neutron guides are critical components of these facilities. They are neutron-transport optical devices consisting of state-of-the-art mirrors often tens of meters long. Here we demonstrate a novel fabrication method of all-metallic neutron guides and axisymmetric mirrors by electroplating from precision mandrels. The process allows for the fabrication of single-piece all-metal guides of prismatic and axisymmetric shapes. We also demonstrate supermirror guides and axisymmetric focusing supermirrors produced with the same technology. We present the fabrication and tests of the multilayer-coated replicated guides and optic and show that the mandrel is reproduced with high fidelity and reliability. Furthermore, such supermirror optics will provide game-changing improvements in neutron techniques.

36 MATERIALS SCIENCE↗
DOE OSTI2022

graphenv: a Python library for reinforcement learning on graph search spaces

Many important and challenging problems in combinatorial optimization (CO) can be expressed as graph search problems, in which graph vertices represent full or partial solutions and edges represent decisions that connect them. Graph structure not only introduces strong relational inductive biases for learning (Battaglia et al., 2018) - in this context, by providing a way to explicitly model the value of transitioning (along edges) between one search state (vertex) and the next - but lends itself to problems both with and without clearly defined algebraic structure. For example, classic CO problems on graphs such as the Traveling Salesman Problem (TSP) can be expressed as either pure graph search or integer programs. Other problems, however, such as molecular optimization, do no have concise algebraic formulations and yet are readily implemented as a graph search (V. et al., 2022; Zhou et al., 2019). Such "model-free" problems constitute a large fraction of modern reinforcement learning (RL) research owing to the fact that it is often much easier to write a forward simulation that expresses all of the state transitions and rewards, than to write down the precise mathematical expression of the full optimization problem. In the case of molecular optimization, for example, one can use domain knowledge alongside existing software libraries to model the effect of adding a single bond or atom to an existing but incomplete molecule, and let the RL algorithm build a model of how good a given decision is by "experiencing" the simulated environment many times through. In contrast, a model-based mathematical formulation that fully expresses all the chemical and physical constraints is intractable. In recent years, RL has emerged as an effective paradigm for optimizing searches over graphs and led to state-of-the-art heuristics for games like Go and chess, as well as for classical CO problems such as the TSP. This combination of graph search and RL, while powerful, requires non-trivial software to execute, especially when combining advanced state representations such as Graph Neural Networks (GNN) with scalable RL algorithms.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Recent Cryogenic Carbon Capture™ Field Test Results

Sustainable Energy Solutions (SES) has been developing Cryogenic Carbon Capture™ (CCC) since 2008. In that time, two processes have been developed, the External Cooling Loop and Compressed Flue Gas CCC processes (CCC-ECL and CCC-CFG, respectively). The CCC-ECL process cools the flue gas with an external refrigerant loop. This process currently captures up to 1 tonne of CO2 per day (TPD). SES has tested CCC-ECL on real flue gas slip streams from subbituminous coal, bituminous coal, biomass, natural gas, shredded tires, and municipal waste fuels at field sites that include utility power stations, heating plants, cement kilns, and pilot-scale research reactors. The CO2 concentrations from these tests ranged from 5 to 22% on a dry basis. CO2 capture ranged from 95-99+% during these tests. Several other condensable species were also captured including NO2, SO2 and PMxx at 95+%. NO was also captured at a modest rate. The CCC-CFG process has been scaled up to a 0.25 ton per day system. This system has been tested on real flue gas streams including subbituminous coal, bituminous coal, and natural gas at field sites that include utility power stations, heating plants, and pilot-scale research reactors. CO2 concentrations for these tests ranged from 5 to 15% on a dry basis. CO2 capture ranged from 95-99+% during these tests. Several other condensable species were also captured including NO2, SO2, and PMxx at 95+%. NO was also captured at 90+%. Hg capture was also verified and the resulting effluent from CCC-CFG was below a 1ppt concentration. This paper will focus on discussion of the capabilities of CCC generally, the results of CCC-ECL field testing, and future steps surrounding the development of this technology. Test results that will be presented have been collected during 9 months of testing at a commercial power plant under funding from the US Department of Energy (DOE) and the host utility. Testing of one of the systems at a commercial cement plant in the United States will also be discussed. During this testing, the system captured CO2 from the cement plant and stored the CO2 in pressurized tanks. These tanks were provided to a partner company that later used the CO2 in a CO2 utilization demonstration. The CO2 was utilized to cure concrete manufactured using cement from the same plant where the CO2 was captured. This integrated capture and utilization demonstration was the first time that the cement industry has shown in the field that it can sequester its CO2 emissions in its main product stream. This represents a potential game changing solution for industrial CO2 emissions. Operational data and host-site feedback indicate that the CCC process is ideally suited for deployment into a variety of commercial environments. A few areas of de-risking remain to make sure the technology can meet very strict industrial reliability standards. These areas of de-risking are identified and discussed. The product CO2 is shown to meet specification for many uses including industrial and merchant applications. The technology is nearing readiness for deployment at commercial scale and several initial target markets have been identified.

20 FOSSIL-FUELED POWER PLANTS↗