Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Continual learning”

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 307 records · Page 17

Development and assessment of hierarchical multi-reward reinforcement learning based potential for silicene with state-of-the-art models

We develop a new interatomic force field for Silicene, a 2D material with a buckled hexagonal lattice structure with high polymorphism. We introduce new parameterizations of a Tersoff model using a hierarchical multi-reward reinforcement learning (RL) methodology coupled with a continuous Monte Carlo Tree Search optimization. Our model significantly outperforms existing methods by enhancing the accuracy of predictions for the structural and thermodynamic properties of seven silicene polymorphs-including structure, energy, equation of state, elasticity, and phonon dispersion-when compared to established models. We further make a comprehensive comparison of the various models in predicting the mechanical and thermal properties of silicene. We trace the origin of the improved performance to the description of the angular dependence in the bond-order term, suggesting that modifying the angular terms in short-range models is essential to capture the structural diversity in low dimensional systems.

2D materials↗

Blueprints for Training Information Bottlenecks for Collider Analyses

Dimensionality reduction is a crucial aspect of data analysis in high energy physics, even if accompanied by information loss. Several methods, including histogram- and kernel-based analyses, are only computationally feasible for low-dimensional data. Furthermore, simulation models used in HEP can often only be validated for low-dimensional data. We provide several blueprints for using machine learning to create low-dimensional data representations (continuous event variables and discrete classification labels) for use in signal discovery and parameter estimation tasks. We also describe how to design the learned representation to facilitate a) searches with unknown model parameters and b) validation of simulation models in data control regions.

43 PARTICLE ACCELERATORS↗

The ZTF Source Classification Project. I. Methods and Infrastructure

The Zwicky Transient Facility (ZTF) has been observing the entire northern sky since the start of 2018 down to a magnitude of 20.5 (5σ for 30 s exposure) in the g, r, and i filters. Over the course of two years, ZTF has obtained light curves of more than a billion sources, each with 50–1000 epochs per light curve in g and r, and fewer in i. To be able to use the information contained in the light curves of variable sources for new scientific discoveries, an efficient and flexible framework is needed to classify them. In this paper, we introduce the methods and infrastructure that will be used to classify all ZTF light curves. Our approach aims to be flexible and modular and allows the use of a dynamical classification scheme and labels, continuously evolving training sets, and the use of different machine-learning classifier types and architectures. Finally with this setup, we are able to continuously update and improve the classification of ZTF light curves as new data become available, training samples are updated, and new classes need to be incorporated.

79 ASTRONOMY AND ASTROPHYSICS↗

Recent advances in integrated hydrologic models: Integration of new domains

Over the past several decades, hydrologic models have advanced from independent models of the surface and subsurface to integrated models that can capture the terrestrial hydrologic cycle within one framework. In recent years, these coupled frameworks have seen the inclusion of biogeochemical processes, ecohydrology, sedimentation and erosion, cold region hydrology, anthropogenic activities, and atmospheric processes. This expansion is the result of increased computational, data, and modeling capabilities and capacities, as well as improved understanding of the processes that drive these integrated systems. Here, in this study, we review these recent advances to integrate new processes and systems into existing terrestrial hydrologic models and highlight the significant challenges and opportunities that remain. We identify that with so many models currently available and in development, selecting the most appropriate model is difficult, and we suggest a path for new or novice modelers to find the most appropriate code based on their needs. In addition, data required to parameterize and calibrate these models can often constrain their applicability and usefulness. However, advances in environmental sensors and measurement technology, in addition to data assimilation of non-traditional data (e.g. remote sensing, qualitative data) are providing new ways of addressing this issue. As we expand hydrologic models to integrate more processes and systems, our computational demands also increase. Recent and emerging advances in computational platforms, including cloud and quantum computing, in addition to the use of machine learning to capture some processes, will continue to support the use of increasingly larger and more complex, process-based models. Finally, we highlight that it is critical to develop state-of-the-science models that are accessible to all model users, not just those applied for research and development. We encourage continued development of diverse modeling platforms, considering the user needs, data availability, and computational resources.

54 ENVIRONMENTAL SCIENCES↗

Power generation forecasting for solar plants based on Dynamic Bayesian networks by fusing multi-source information

A Dynamic Bayesian network (DBN) model for solar power generation forecasting in solar plants is proposed in this paper. The key idea is to fuse sensor data, operational indicators, meteorological data, lagged output power information, and model errors for more accurate short-term (e.g., hours) and mid-term (e.g., days to weeks) power generation forecasting. The proposed DBN augments automated data-driven structure learning with expert knowledge encoding using continuous and categorical data given constraints to represent causal relationships within a solar inverter system. Additionally, an error compensation mechanism is proposed to capture temporal fluctuation. The effectiveness of the DBN on solar power generation forecasting was evaluated by rolling window analysis with one-year testing data collected from a local solar plant. The proposed DBN is compared with four state-of-art methods including support-vector regression (SVR), k-nearest neighbors (kNN), artificial neural network (ANN), and long short-term memory (LSTM) models. The result show that the proposed DBN achieves better accuracy in general, and it is not as data-hungry as some neural network-based models. The proposed DBN is also shown to have robust and consistent forecasting power with different forecasting horizons. The accuracy is 92% - 95% from one hour to one week ahead forecasting.

14 SOLAR ENERGY↗

Distributed Acoustic Sensing to Estimate the Permeability

Optical fiber in a borehole can be interrogated with distributed acoustic sensors (DAS) to capture fracture displacements with the potential to map surrounding fracture networks. We designed a laboratory experiment to test the capability of DAS to determine borehole flow characteristics, and we show that for the first time DAS can be used to remotely estimate permeability. Optical fiber was wrapped around a bead filled pipe and the pressure drop and flow velocity were measured to directly calculate permeability. A machine learning model using statistical features from continuous DAS estimated the bulk permeability. Fluid interactions with the permeable material demonstrate insufficient resolution using DAS amplitude-based measurements for estimating pressure drop to infer permeability. Variations in the spectral domain relate DAS measurements to the pressure drop and provide consistent permeability estimates. Resolution with DAS is sufficient to estimate permeability and provides a reliable method to monitor at depth in borehole conditions.

58 GEOSCIENCES↗

An Intelligent Adaptable Monitoring Package. Final Report

The “Intelligent Adaptable Monitoring Package” project was a four-year effort that demonstrated the feasibility of integrated sensing packages at tidal and wave energy sites. Such integration is generally required by the breadth of sensors required to understand environmental effects at marine energy sites and the operational difficulty of deploying, maintaining, and recovering such sensors. Over the course of the project, the Adaptable Monitoring Package (AMP) was deployed in multiple settings, each corresponding to a project budget period: - Budget Period 1: Demonstration of cabled deployment at Pacific Northwest National Laboratory’s Marine Science Laboratory. The deployment highlighted AMP hardware endurance over a 4-month deployment in a tidally-dominated environment and laid the groundwork for machine learning algorithms to detect and classify targets present in active sonar data. - Budget Period 2: Demonstration of an autonomous deployment at PacWave South off the coast of Newport, Oregon. The deployment highlighted the stability of AMP hardware and software, with the autonomous package collecting data on a duty cycle over a 1.5-month deployment. - Budget Period 3: Demonstration of an autonomous deployment powered by a wave energy converter at the U.S. Navy’s Wave Energy Test Site. The deployment highlighted the potential of wave energy to power ocean observatories and led to the development of machine learning algorithms to detect and classify targets in optical camera data. In aggregate, this project’s greatest success was demonstrating the AMP’s flexibility in a range of deployment scenarios. Each budget period represented a “first of a kind” demonstration of integrated instrumentation – cabled AMP, autonomous AMP, wave-energy powered AMP – and each deployment helped to identify and set goals for the next. Further, despite the exploratory nature of these deployments, each one achieved high system up-time and proved that flexible integration of multiple sensors in a single package represents a viable strategy for marine energy environmental monitoring. The key lessons learned from the project are: - Without continuous power, either from a shore cable or in situ source, many of the benefits of integration are lost (If continuous power is not available, the ability to detect rare events is lost, as is the ability to minimize the risk of behavioral changes through adaptive sensing. However, even on a duty cycle, there is still value in being able to acquire synchronous data from multiple sensors.); and - Observations from a moving platform present substantially greater data processing challenges than those from stationary platforms. Finally, these deployments also demonstrate an important truth: successful integration alone does not guarantee that relevant data are collected. To grow the knowledge base about environmental interactions with marine energy converters, integrated systems, like the AMP, need to include the right sensor mix and connect the data pipelines to effective processing algorithms. These deployments establish a strong foundation for future collaborations with the environmental research community: not only to understand the environmental effects of marine energy, but also to improve our general ability to study life in the sea.

16 TIDAL AND WAVE POWER↗

Turboexpander for Direct Cooling in Hydrogen Vehicle Fueling Infrastructure

Hydrogen fuel cell electric vehicles (FCEVs) have been identified as one of a few options for zero carbon emissions transportation. A major advantage of FCEVs is that they can fuel quickly and follow a familiar fueling behavior to hydrocarbon-fueled vehicles. Whether light duty or heavy duty, the goal for a hydrogen dispenser is to fuel a vehicle in the same amount of time as the fossil fuel equivalent. When hydrogen is dispensed into the vehicle storage system, however, the temperature rises due to the Joule-Thomson effect and the heat of compression. Typically, vehicles store the compressed hydrogen in composite overwrapped pressure vessels that have a polymer liner with an operational temperature limit of 85°C. This temperature limit can be exceeded during fast fueling if hydrogen is not precooled. Precooling allows for a dispenser to fuel a vehicle at a faster flow rate by preventing the storage tank on the vehicle from overheating. Fueling protocols and requirements are presented in SAE J2601 Fueling Protocols for Light Duty Gaseous Hydrogen Surface Vehicles [1]. A heavy-duty equivalent is under development with similar requirements for precooling. Currently, conventional precooling for light-duty vehicle refueling uses a heat exchanger and chiller to cool the hydrogen gas to -40°C before entering the vehicle. The precooling system represents a significant part of the station capital and operating costs, so if the cost of the precooling system can be reduced by improving its efficiency, the overall station capital and operating cost can be reduced. In this project, National Renewable Energy Laboratory (NREL) and Sandia National Laboratories (SNL) researchers teamed up to investigate the turboexpander precooling application. A turboexpander is a device that places a turbine in a flow path where a pressure differential can be attained. This expansion device will extract work and lower the temperature of the fluid as the pressure reduces. While initial calculations based on established principles showed potential for a turboexpander to generate cooled gas, much work needs to be done to prove the concept. Turboexpanders typically work best under steady state conditions, while the dispenser is a very dynamic flow system. Dynamic turboexpander systems have been proven, such as a turbocharger on a gasoline vehicle. The inlet pressure at a dispenser is also much higher than any other known turboexpander system but should behave similarly to higher density fluids at lower pressures. Having both performed initial calculations, NREL and SNL researchers teamed up to investigate the turboexpander precooling application further. A project was soon built around the idea with SNL performing system modeling using previously proven capabilities and NREL performing hardware characterization with established station capabilities. Creare LLC was contracted as the turbomachinery expert to design and build the concept device. Part way through the project, however, contracting issues with the funding partner caused the project to terminate early before building and characterizing the concept device. While the project could not continue, many key findings were already learned. This paper is a summary of those findings.

08 HYDROGEN↗

Physics Informed Reinforcement Learning for Power Grid Control using Augmented Random Search

Wide adoption of deep reinforcement learning need to overcome several challenges in energy system domain, including scalability, learning from limited samples, and high-dimensional continuous state and action spaces. In this paper, we integrated physics-based information from the normal generator operation state formula in the reinforcement learning agent's neural network loss function, and applied an augmented random search agent to optimize the generator control under dynamic contingency. Simulation results demonstrated the reliability performance improvements in training speed, reward convergence, sampling efficiency, scalability, and transferability.

physics informed ML, Physics Informed Neural Netwo↗

Joint Modeling of Quasar Variability and Accretion Disk Reprocessing Using Latent Stochastic Differential Equations

Quasars are bright active galactic nuclei powered by the accretion of matter around supermassive black holes at the center of galaxies. Their stochastic brightness variability depends on the physical properties of the accretion disk and black hole. The upcoming Rubin Observatory Legacy Survey of Space and Time (LSST) is expected to observe tens of millions of quasars, so there is a need for efficient techniques like machine learning that can handle the large volume of data. Quasar variability is believed to be driven by an X-ray corona, which is reprocessed by the accretion disk and emitted as UV/optical variability. We are the first to introduce an auto-differentiable simulation of the accretion disk and reprocessing. We use the simulation as a direct component of our neural network to jointly model the driving variability and reprocessing, trained with supervised learning on simulated LSST-like 10 yr quasar light curves. We encode the light curves using a transformer encoder, and the driving variability is reconstructed using latent stochastic differential equations, a physically motivated generative deep learning method that can model continuous-time stochastic dynamics. By embedding the physical processes of the driving signal and reprocessing into our network, we achieve a model that is more robust and interpretable. We demonstrate that our model outperforms a Gaussian process regression baseline and can infer accretion disk parameters and time delays between wave bands, even for out-of-distribution driving signals. Our approach provides a powerful framework that can be adapted to solve other inverse problems in multivariate time series.

Fagin, Joshua [City Univ. of New York (CUNY), NY (↗

Neural Network Machine Learning and Dimension Reduction for Data Visualization

Neural network machine learning in computer science is a continuously developing field of study. Although neural network models have been developed which can accurately predict a numeric value or nominal classification, a general purpose method for constructing neural network architecture has yet to be developed. Computer scientists are often forced to rely on a trial-and-error process of developing and improving accurate neural network models. In many cases, models are constructed from a large number of input parameters. Understanding which input parameters have the greatest impact on the prediction of the model is often difficult to surmise, especially when the number of input variables is very high. This challenge is often labeled the "curse of dimensionality" in scientific fields. However, techniques exist for reducing the dimensionality of problems to just two dimensions. Once a problem's dimensions have been mapped to two dimensions, it can be easily plotted and understood by humans. The ability to visualize a multi-dimensional dataset can provide a means of identifying which input variables have the highest effect on determining a nominal or numeric output. Identifying these variables can provide a better means of training neural network models; models can be more easily and quickly trained using only input variables which appear to affect the outcome variable. The purpose of this project is to explore varying means of training neural networks and to utilize dimensional reduction for visualizing and understanding complex datasets.

Liles, Charles A.↗

Distributed System Design Checklist

This report describes a design checklist targeted to fault-tolerant distributed electronic systems. Many of the questions and discussions in this checklist may be generally applicable to the development of any safety-critical system. However, the primary focus of this report covers the issues relating to distributed electronic system design. The questions that comprise this design checklist were created with the intent to stimulate system designers' thought processes in a way that hopefully helps them to establish a broader perspective from which they can assess the system's dependability and fault-tolerance mechanisms. While best effort was expended to make this checklist as comprehensive as possible, it is not (and cannot be) complete. Instead, we expect that this list of questions and the associated rationale for the questions will continue to evolve as lessons are learned and further knowledge is established. In this regard, it is our intent to post the questions of this checklist on a suitable public web-forum, such as the NASA DASHLink AFCS repository. From there, we hope that it can be updated, extended, and maintained after our initial research has been completed.

Hall, Brendan↗

Evolution of Software-Only-Simulation at NASA IV and V

Software-Only-Simulations have been an emerging but quickly developing field of study throughout NASA. The NASA Independent Verification Validation (IVV) Independent Test Capability (ITC) team has been rapidly building a collection of simulators for a wide range of NASA missions. ITC specializes in full end-to-end simulations that enable developers, VV personnel, and operators to test-as-you-fly. In four years, the team has delivered a wide variety of spacecraft simulations that have ranged from low complexity science missions such as the Global Precipitation Management (GPM) satellite and the Deep Space Climate Observatory (DSCOVR), to the extremely complex missions such as the James Webb Space Telescope (JWST) and Space Launch System (SLS).This paper describes the evolution of ITCs technologies and processes that have been utilized to design, implement, and deploy end-to-end simulation environments for various NASA missions. A comparison of mission simulators are discussed with focus on technology and lessons learned in complexity, hardware modeling, and continuous integration. The paper also describes the methods for executing the missions unmodified flight software binaries (not cross-compiled) for verification and validation activities.

Embedded↗

NASA Support for Commercial Crew Launch Capabilities

Since the earliest days of U.S. human spaceflight, NASA’s Marshall Space Flight Center in Huntsville, Alabama, has played a key role in American crew launch capability, from engineering support for the first Mercury-Redstone launches, to the Saturn launches to the Moon, through Shuttle and now Artemis. Today, Marshall brings that expertise gained through decades of crewed space launches to NASA’s Commercial Crew Program (CCP), providing launch vehicle engineering and programmatic support. The team’s responsibilities have included human certification of commercial launch systems for the CCP missions, including Atlas V and Falcon 9, and verifying each launch vehicle complies with flight certification. MSFC provides expertise in nearly all aspects of launch vehicle design and performance including solid motors and liquid engines, stage propulsion, thrust vector control, structural and dynamics, safety and mission assurance. During each commercial crew launch, an engineering support team is on console at Marshall’s Huntsville Operations Support Center, which has provided launch operations support since Apollo, providing real-time oversight to safety standards for the vehicle and verifying data. Launch vehicle support for Commercial Crew has come as a paradigm shift for the MSFC team, inspiring new approaches that leverage expertise and best practices from past NASA-developed launch vehicle missions, while at the same time providing new synergies from work with commercial partners on CCP. This paper will explore the role that the Marshall launch vehicle services team plays in the Commercial Crew Program, as well as lessons learned from the program that will continue to benefit a new era of spaceflight partnerships.

Commercial Crew↗

Theoretical Development of Controller Transfer applied to Dynamical Systems

Data-driven control strategies suffer from the necessity of training and its associated computational time and cost. This motivates the continuous increase of popularity of transfer learning based methods. In this paper, we have investigated transfer learning in the context of controller for dynamical systems. First, we have derived conditions under which controller can be transferred between two linear dynamical systems. Furthermore, we have introduced a novel algorithm to design the transferable and non-transferable control components for linear systems. Secondly, we have derived conditions under which a stabilizing controller can be transferred between two different nonlinear dynamical systems. Furthermore, we have used the notion of zero dynamics to transform the nonlinear dynamics into global normal form, to derive the transferability conditions on the controller. Finally, we have numerically evaluated the performance of our transfer learning based methods for two sets of example linear and nonlinear dynamical systems.

Chakraborty, Indrasis↗

Towards a Continuous Variable Quantum Compiler

We present initial work towards an experimental implementation of a nonuniversal continuous variable quantum compiler capable of learning a linear phase operation with increased precision when quantum resources are used.

Feldman, Matthew↗

A Continuous Variable Quantum Compiler

We implement a continuous-variable quantum compiler that can learn a linear phase operation with a fourfold increase in precision and a factor of 80 reduction in time to solution when quantum resources are used.

Feldman, Matthew↗

First Estimation of Model Parameters for Neutrino-Induced Nucleon Knockout Using Simulation-Based Inference

To enable an accurate determination of oscillation parameters, accelerator-based neutrino experiments require detailed simulations of nuclear interaction physics in the GeV regime. While substantial effort from both theory and experiment is currently being invested to improve the fidelity of these simulations, their present deficiencies typically oblige experimental collaborations to resort to empirical tuning of simulation model parameters. As the precision requirements of the field continue to become more stringent, machine learning techniques may provide a powerful means of handling corresponding growth in the complexity of future neutrino interaction model tuning exercises. To study the suitability of simulation-based inference (SBI) for this physics application, in this paper we revisit a tuned configuration of the GENIE neutrino event generator that was originally developed by the MicroBooNE collaboration. Despite closely reproducing the adopted values of four physics parameters when confronted with the tuned cross-section predictions as input, we find that our trained SBI algorithm prefers modestly different values (within MicroBooNE's assigned uncertainties) and achieves slightly better goodness-of-fit when inference is run on the experimental data set originally used by MicroBooNE. We also find that our trained algorithm can create a fair approximation of an alternative neutrino scattering simulation, NuWro, that shares only a subset of its physics model parameters with GENIE.

Tame-Narvaez, Karla [Fermilab] (ORCID:000000022249↗