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 631 records · Page 35

Metric Learning for Hyperspectral Image Segmentation

We present a metric learning approach to improve the performance of unsupervised hyperspectral image segmentation. Unsupervised spatial segmentation can assist both user visualization and automatic recognition of surface features. Analysts can use spatially-continuous segments to decrease noise levels and/or localize feature boundaries. However, existing segmentation methods use tasks-agnostic measures of similarity. Here we learn task-specific similarity measures from training data, improving segment fidelity to classes of interest. Multiclass Linear Discriminate Analysis produces a linear transform that optimally separates a labeled set of training classes. The defines a distance metric that generalized to a new scenes, enabling graph-based segmentation that emphasizes key spectral features. We describe tests based on data from the Compact Reconnaissance Imaging Spectrometer (CRISM) in which learned metrics improve segment homogeneity with respect to mineralogical classes.

Compact Reconnaissance Imaging Spectrometer (CRISM↗

Intelligent machines in the twenty-first century: foundations of inference and inquiry

The last century saw the application of Boolean algebra to the construction of computing machines, which work by applying logical transformations to information contained in their memory. The development of information theory and the generalization of Boolean algebra to Bayesian inference have enabled these computing machines, in the last quarter of the twentieth century, to be endowed with the ability to learn by making inferences from data. This revolution is just beginning as new computational techniques continue to make difficult problems more accessible. Recent advances in our understanding of the foundations of probability theory have revealed implications for areas other than logic. Of relevance to intelligent machines, we recently identified the algebra of questions as the free distributive algebra, which will now allow us to work with questions in a way analogous to that which Boolean algebra enables us to work with logical statements. In this paper, we examine the foundations of inference and inquiry. We begin with a history of inferential reasoning, highlighting key concepts that have led to the automation of inference in modern machine-learning systems. We then discuss the foundations of inference in more detail using a modern viewpoint that relies on the mathematics of partially ordered sets and the scaffolding of lattice theory. This new viewpoint allows us to develop the logic of inquiry and introduce a measure describing the relevance of a proposed question to an unresolved issue. Last, we will demonstrate the automation of inference, and discuss how this new logic of inquiry will enable intelligent machines to ask questions. Automation of both inference and inquiry promises to allow robots to perform science in the far reaches of our solar system and in other star systems by enabling them not only to make inferences from data, but also to decide which question to ask, which experiment to perform, or which measurement to take given what they have learned and what they are designed to understand.

Review↗

Vehicle Position Detection Based on Machine Learning Algorithms in Dynamic Wireless Charging

Dynamic wireless charging (DWC) has emerged as a viable approach to mitigate range anxiety by ensuring continuous and uninterrupted charging for electric vehicles in motion. DWC systems rely on the length of the transmitter, which can be categorized into long-track transmitters and segmented coil arrays. The segmented coil array, favored for its heightened efficiency and reduced electromagnetic interference, stands out as the preferred option. However, in such DWC systems, the need arises to detect the vehicle’s position, specifically to activate the transmitter coils aligned with the receiver pad and de-energize uncoupled transmitter coils. This paper introduces various machine learning algorithms for precise vehicle position determination, accommodating diverse ground clearances of electric vehicles and various speeds. Through testing eight different machine learning algorithms and comparing the results, the random forest algorithm emerged as superior, displaying the lowest error in predicting the actual position.

47 OTHER INSTRUMENTATION↗

Advances in Cross-Cutting Ideas for Computational Climate Science

This report presents results from the DOE-sponsored workshop titled, ``Advancing X-Cutting Ideas for Computational Climate Science Workshop,'' known as AXICCS, held on September 12--13, 2016 in Rockville, MD. The workshop brought together experts in climate science, computational climate science, computer science, and mathematics to discuss interesting but unsolved science questions regarding climate modeling and simulation, promoted collaboration among the diverse scientists in attendance, and brainstormed about possible tools and capabilities that could be developed to help address them. Emerged from discussions at the workshop were several research opportunities that the group felt could advance climate science significantly. These include (1) process-resolving models to provide insight into important processes and features of interest and inform the development of advanced physical parameterizations, (2) a community effort to develop and provide integrated model credibility, (3) including, organizing, and managing increasingly connected model components that increase model fidelity yet complexity, and (4) treating Earth system models as one interconnected organism without numerical or data based boundaries that limit interactions. The group also identified several cross-cutting advances in mathematics, computer science, and computational science that would be needed to enable one or more of these big ideas. It is critical to address the need for organized, verified, and optimized software, which enables the models to grow and continue to provide solutions in which the community can have confidence. Effectively utilizing the newest computer hardware enables simulation efficiency and the ability to handle output from increasingly complex and detailed models. This will be accomplished through hierarchical multiscale algorithms in tandem with new strategies for data handling, analysis, and storage. These big ideas and cross-cutting technologies for enabling breakthrough climate simulation advancements also need the "glue" of outreach and learning across the scientific domains to be successful. The workshop identified several strategies to allow productive, continuous engagement across those who have a broad knowledge of the various angles of the problem. Specific ideas to foster education and tools to make material progress were discussed. Examples include follow-on cross-cutting meetings that enable unstructured discussions of the types this workshop fostered. A concerted effort to recruit undergraduate and graduate students from all relevant domains and provide them experience, training, and networking across their immediate expertise is needed. This will broaden and expand their exposure to the future needs and solutions, and provide a pipeline of scientists with a diversity of knowledge and know-how. Providing real-world experience with subject matter experts from multiple angles may also motivate the students to attack these problems and even come up with the missing solutions.

54 ENVIRONMENTAL SCIENCES↗

Advances in Cross-Cutting Ideas for Computational Climate Science

This report presents results from the DOE-sponsored workshop titled, Advancing X-Cutting Ideas for Computational Climate Science Workshop,'' known as AXICCS, held on September 12--13, 2016 in Rockville, MD. The workshop brought together experts in climate science, computational climate science, computer science, and mathematics to discuss interesting but unsolved science questions regarding climate modeling and simulation, promoted collaboration among the diverse scientists in attendance, and brainstormed about possible tools and capabilities that could be developed to help address them. Emerged from discussions at the workshop were several research opportunities that the group felt could advance climate science significantly. These include (1) process-resolving models to provide insight into important processes and features of interest and inform the development of advanced physical parameterizations, (2) a community effort to develop and provide integrated model credibility, (3) including, organizing, and managing increasingly connected model components that increase model fidelity yet complexity, and (4) treating Earth system models as one interconnected organism without numerical or data based boundaries that limit interactions. The group also identified several cross-cutting advances in mathematics, computer science, and computational science that would be needed to enable one or more of these big ideas. It is critical to address the need for organized, verified, and optimized software, which enables the models to grow and continue to provide solutions in which the community can have confidence. Effectively utilizing the newest computer hardware enables simulation efficiency and the ability to handle output from increasingly complex and detailed models. This will be accomplished through hierarchical multiscale algorithms in tandem with new strategies for data handling, analysis, and storage. These big ideas and cross-cutting technologies for enabling breakthrough climate simulation advancements also need the "glue" of outreach and learning across the scientific domains to be successful. The workshop identified several strategies to allow productive, continuous engagement across those who have a broad knowledge of the various angles of the problem. Specific ideas to foster education and tools to make material progress were discussed. Examples include follow-on cross-cutting meetings that enable unstructured discussions of the types this workshop fostered. A concerted effort to recruit undergraduate and graduate students from all relevant domains and provide them experience, training, and networking across their immediate expertise is needed. This will broaden and expand their exposure to the future needs and solutions, and provide a pipeline of scientists with a diversity of knowledge and know-how. Providing real-world experience with subject matter experts from multiple angles may also motivate the students to attack these problems and even come up with the missing solutions.

54 ENVIRONMENTAL SCIENCES↗

Spacecraft COst REduction Team (SCORE): TQM/CI on a massive scale

The business of building satellites and space systems has matured. Few missions require, or can afford, excellent performance at any price. The new paradigm is doing more with less, providing quality systems at lower cost--in other words, doing our job 'Faster-Better-Cheaper.' The TRW Spacecraft COst REduction (SCORE) initiative was launched in 1990 by Daniel S. Goldin, then general manager of TRW's Space & Technology Group. The SCORE mission is to apply continuous improvement (CI) techniques to effect major reductions in the cost (our primary goal) and span time (as a corollary) required for the production of spacecraft. SCORE is a multi-year initiative that is having a profound effect on both the procedural and the cultural aspects of how we do business. The objectives of this initiative are being realized. The focus of this paper is not on the results of SCORE per se, but rather on the things we have leaned about how to do continuous improvement on a massive scale, with multilevel (hierarchical) CI teams. The following sections summarize the chronology of the SCORE initiative, from team formation to development of the year-end report for 1991. Lessons learned, the core of this presentation, are discussed--with particular focus on the unique aspects of SCORE. The SCORE initiative is continuing and, as a part of our evolving culture, will never end. It has resulted in profound insights into the way we do work and (the topic at hand) how to do CI for large and complex multidisciplinary development activities.

Bullard, Jerry D.↗

U.S. GPM Status

The joint U.S.-Japan Global Precipitation Measurement (GPM) mission, now in its tenth year of operations, continues to pursue research on scientific and operational shortcomings in algorithms for retrieving global precipitation from satellite observations. A summary of operations, including the orbit boost, processing, science, and applications is provided. This includes key improvements to the GPM products for which NASA has lead responsibility. This includes refinements to ensure continuity for each product across the boundary in 2014 between the predecessor Tropical Rainfall Measuring Mission (TRMM) and the GPM Core Observatory. Early evaluations of the U.S. Science Team’s Integrated Multi-satellitE Retrievals for GPM (IMERG) in V07 show interesting behavior across the TRMM orbit boost that is highly relevant to the planned orbit boost for the GPM Core observatory. We will present summary statistics that illustrate the tremendous demand that exists in the user community for GPM precipitation products, which on the U.S. side is primarily focused on IMERG, and end by considering major issues that might be addressed in up-coming versions. These include the use of machine learning algorithms, the operational challenge of swarms of “small”, perhaps short-lived satellites, and continuation of precessing calibration satellites after GPM.

GPM↗

Uncertainty Quantified Machine Learning for Street Level Flooding Predictions in Norfolk, Virginia

Everyday citizens, emergency responders, and critical infrastructure can be dramatically affected by street flooding caused by the increasing tidal levels and major storm events magnified by climate change. Low-level flooding, such as nuisance flooding, continues to increase in frequency, especially in cities like Norfolk, Virginia, which can expect nearly 200 flooding events by 2050 [1]. Recently, machine learning (ML) models have been leveraged to produce real-time predictions based on local weather and geographic conditions. However, ML models are known to produce unusual results when presented with data that varies from their training set. For decision-makers to determine the trustworthiness of the model's predictions, ML models need to quantify their prediction uncertainty. This study applies Deep Quantile Regression (DQR) to a previously published, LSTM-based model for hourly water depth predictions [2], and analyzes its out-of-distribution (OOD) performance.

Goldenberg, Steven↗

Integrating NASA Dryden Research Endeavors into the Teaching-Learning of Mathematics in the K-12 Classroom via the WWW

The primary goal of this project was to continue populating the currently existing web site developed in 1998 in conjunction with the NASA Dryden Flight Research Center and California Polytechnic State University, with more mathematics lesson plans and activities that K-12 teachers, students, home-schoolers, and parents could access. All of the activities, while demonstrating some mathematical topic, also showcase the research endeavors of the NASA Dryden Flight Research Center. The website is located at: http://daniel.calpoly.edu/~dfrc/Robin. The secondary goal of this project was to share the web-based activities with educators at various conferences and workshops. To address the primary goal of this project, over the past year, several new activities were posted on the web site and some of the existing activities were enhanced to contain more video clips, photos, and materials for teachers. To address the project's secondary goal, the web-based activities were showcased at several conferences and workshops. Additionally, in order to measure and assess the outreach impact of the web site, a link to the web site hitbox.com was established in April 2001, which allowed for the collection of traffic statistics against the web site (such as the domains of visitors, the frequency of visitors to this web site, etc.) Provided is a description of some of the newly created activities posted on the web site during the project period of 2001-2002, followed by a description of the conferences and workshops at which some of the web-based activities were showcased. Next is a brief summary of the web site's traffic statistics demonstrating its worldwide educational impact, followed by a listing of some of the awards and accolades the web site has received.

Ward, Robin A.↗

Weighted Composition Operators for Learning Nonlinear Dynamics

Operator theoretic methods in dynamical system have been dominated by the use of Koopman operators and their continuous time counterparts, such as Koopman Generators and Liouville Operators. The advantage gained from their use primarily stems from the ability to extract subspaces and eigenfunctions within a space of observables that are invariant with respect to the Koopman operator over that space. When this occurs, a dynamic mode decomposition of the systems state provides a linear model for the dynamical system. Not all Koopman operators have eigenfunctions that may be exploited in this manner. However, the framework can still be leveraged for approximations using other operators. In this setting, we present a different operator for the study of dynamical systems, the weighted composition operator. These operators are compact for a wide range of dynamics and spaces, and through their interactions with occupation kernels and vector valued kernels, they admit an estimation of the underlying dynamics. Here, this manuscript presents a new algorithm for the data driven study of dynamical systems from data, and also provides two numerical experiments where convergence is achieved as a proof of concept.

97 MATHEMATICS AND COMPUTING↗

Environmental cleanup of the East Tennessee Technology Park - Year three - A status report - 15522

On August 1, 2011, URS - CH2M Oak Ridge LLC (UCOR) began its five-year, $1.4 billion cleanup of the East Tennessee Technology Park (ETTP), the former Oak Ridge Gaseous Diffusion Plant, located on the U.S. Department of Energy's (DOE) Oak Ridge Reservation (Reservation) in Tennessee. Under the contract, the base period scope of work to be completed by 2016 includes demolition of both the K-25 and K-31 gaseous diffusion buildings and all demolition waste dispositioned, initiation of demolition on the remaining K-27 gaseous diffusion building, safe storage of transuranic (TRU) waste for eventual transfer to the Transuranic Waste Processing Center, previously designated -No-Path-To-Disposition Waste- dispositioned to the extent possible, and completion of design and engineering of a mercury treatment system to be installed at the Y-12 National Security Complex (Y-12). UCOR will have also managed DOE Oak Ridge Office of Environmental Management (OREM)-owned facilities at ETTP, Oak Ridge National Laboratory (ORNL), and Y-12 in a safe and cost-effective manner. Since assuming responsibilities as the ETTP and Oak Ridge Reservation cleanup contractor, UCOR has completed its life-cycle Performance Measurement Baseline; received its Earned Value Management System (EVMS) certification; completed the deactivation and demolition (D and D) of the 44-acre K-25 gaseous diffusion building; removed and disposed of a contaminated underground storage tank (Tank W-1A) at ORNL; dispositioned mercury-contaminated storage tanks at Y-12; completed closure of the Toxic Substances Control Act Incinerator; disposed of more than 158,000 cubic yards of cleanup waste while managing the on-site Environmental Management Waste Management Facility (EMWMF); and conducted operations, surveillance, and maintenance activities at 180 DOE EM facilities at ETTP, ORNL, and Y-12 in a safe and cost-effective manner. In 2014, UCOR completed the removal and disposal of all of the K-25 demolition debris; completed the removal of asbestos-laden transite siding on the K-31 gaseous diffusion building and began demolition of that 17-acre building; advanced the characterization and deactivation of the K-27 gaseous diffusion building, readying the building for the start of demolition in 2015; advanced the design and engineering of a Mercury Treatment Facility to be located at Y-12; continued the cost-effective and safe disposition of all cleanup wastes; and readied ETTP for Voluntary Protection Program Star Status Assessment in 2015. Project performance as of December 31, 2014, continued to be excellent: - Cost Performance Index - 1.12 - Schedule Performance Index - 1.02 At the same time, since safety is the foundation of all cleanup work, UCOR's safety record goes hand-in-hand with its excellent project performance. Through calendar year 2014, UCOR's recordable injury rate was 1.04 occurrences per 200,000 work hours, and the lost workday case rate was 0.52. This performance continues to be due, in large part, to the people and processes URS and CH2M HILL, the parent companies of UCOR, brought to the project. Key enablers included: - Selected and deployed experienced staff in key leadership positions throughout the organization, continually re-energizing the organization with new leaders - Implemented previously successful safety programs and initiatives from other DOE sites, such as DOE's Voluntary Protection Program - Brought fresh thinking and innovation to tackling tough project issues, such as the deactivation of the Technetium-99-contaminated areas of K-27, applying lessons learned from the D and D of K-25; and implementing a -waste factory- approach to cleanup - Maintained continuing alignment between UCOR's contract with DOE and its Performance Measurement Baseline - rapidly addressing contract changes when they arose - Maintained a readiness both from a process as well as experienced personnel perspective to support DOE OREM in performing other significant Oak Ridge Reservation cleanup activities. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Monitoring and prediction of porosity in laser powder bed fusion using physics-informed meltpool signatures and machine learning

In this work we accomplished the monitoring and prediction of porosity in laser powder bed fusion (LPBF) additive manufacturing process. This objective was realized by extracting physics-informed meltpool signatures from an in-situ dual-wavelength imaging pyrometer, and subsequently, analyzing these signatures via computationally tractable machine learning approaches. Porosity in LPBF occurs despite extensive optimization of processing conditions due to stochastic causes. Hence, it is essential to continually monitor the process with in-situ sensors for detecting and mitigating incipient pore formation. In this work a tall cuboid-shaped part (10 mm × 10 mm × 137 mm, material ATI 718Plus) was built with controlled porosity by varying laser power and scanning speed. This test caused various types of porosity, such as lack-of-fusion and keyhole formation, with varying degrees of severity in the part. The meltpool was continuously monitored using a dual-wavelength imaging pyrometer installed in the machine. Physically intuitive process signatures, such as meltpool length, temperature distribution, and ejecta (spatter) characteristics, were extracted from the meltpool images. Subsequently, relatively simple machine learning models, e.g., K-Nearest Neighbors, were trained to predict both the severity and type of porosity as a function of these physics-informed meltpool signatures. These models resulted in a prediction accuracy exceeding 95% (statistical F1-score). The same analysis was carried out with a complex, black-box deep learning convolutional neural network which directly used the meltpool images instead of physics-informed features. The convolutional neural network produced a comparable F1-score in the range of 89–97%. Finally, these results demonstrate that using pragmatic, physics-informed meltpool signatures within a simple machine learning model is as effective for flaw prediction in LPBF as using a complex and computationally demanding black-box deep learning model.

36 MATERIALS SCIENCE↗

Extreme-scale stochastic optimization and simulation via learning-enhanced decomposition and parallelization (Final Technical Report)

Stochastic optimization and simulation models ubiquitously arise in designing and operating complex service/engineering systems. They can be extreme in scale due to high-dimensional data and decisions, and can also involve decisions made sequentially in response to newly revealed data, both causing significant computational challenge. The objective of this research is to explore a unified framework that integrates machine learning with discrete optimization and risk-averse modeling, to improve the efficiency of decomposition paradigms for stochastic optimization and simulations at extreme scale. The models we consider represent a broad class of complex decision-making problems, where 0-1 or continuous decisions are made before and/or after knowing multiple sources of uncertainties that could be correlated. We will employ machine learning methods to dynamically decide and prioritize computational procedures, including cut generation, branching, and bounding of the optimal objective. Furthermore, the research will shed new lights on the traditional decomposition algorithms for extreme-scale computing. Deliverables of the research include new modeling and computational methods for advancing the state-of-the-art research in optimization and simulation, bringing many relevant risk-averse, data-driven optimization problems in practice within the range of tractability. Examples include distributed computing server scheduling and sensor deployment for monitoring critical infrastructures. Success in this effort will enable progress in solving multiple extreme-scale problems in the complex system design and operations arising from DoE missions in energy, environment, and national security.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Intelligent Machines in the 21st Century: Automating the Processes of Inference and Inquiry

The last century saw the application of Boolean algebra toward the construction of computing machines, which work by applying logical transformations to information contained in their memory. The development of information theory and the generalization of Boolean algebra to Bayesian inference have enabled these computing machines. in the last quarter of the twentieth century, to be endowed with the ability to learn by making inferences from data. This revolution is just beginning as new computational techniques continue to make difficult problems more accessible. However, modern intelligent machines work by inferring knowledge using only their pre-programmed prior knowledge and the data provided. They lack the ability to ask questions, or request data that would aid their inferences. Recent advances in understanding the foundations of probability theory have revealed implications for areas other than logic. Of relevance to intelligent machines, we identified the algebra of questions as the free distributive algebra, which now allows us to work with questions in a way analogous to that which Boolean algebra enables us to work with logical statements. In this paper we describe this logic of inference and inquiry using the mathematics of partially ordered sets and the scaffolding of lattice theory, discuss the far-reaching implications of the methodology, and demonstrate its application with current examples in machine learning. Automation of both inference and inquiry promises to allow robots to perform science in the far reaches of our solar system and in other star systems by enabling them to not only make inferences from data, but also decide which question to ask, experiment to perform, or measurement to take given what they have learned and what they are designed to understand.

Knuth, Kevin H.↗

Quantum adiabatic machine learning by zooming into a region of the energy surface

Recent work has shown that quantum annealing for machine learning, referred to as QAML, can perform comparably to state-of-the-art machine learning methods with a specific application to Higgs boson classification. Here, we propose QAML-Z, an algorithm that iteratively zooms in on a region of the energy surface by mapping the problem to a continuous space and sequentially applying quantum annealing to an augmented set of weak classifiers. Results on a programmable quantum annealer show that QAML-Z matches classical deep neural network performance at small training set sizes and reduces the performance margin between QAML and classical deep neural networks by almost 50% at large training set sizes, as measured by area under the receiver operating characteristic curve. The significant improvement of quantum annealing algorithms for machine learning and the use of a discrete quantum algorithm on a continuous optimization problem both opens a class of problems that can be solved by quantum annealers and suggests the approach in performance of near-term quantum machine learning towards classical benchmarks.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Product Distributions for Distributed Optimization

With connections to bounded rational game theory, information theory and statistical mechanics, Product Distribution (PD) theory provides a new framework for performing distributed optimization. Furthermore, PD theory extends and formalizes Collective Intelligence, thus connecting distributed optimization to distributed Reinforcement Learning (FU). This paper provides an overview of PD theory and details an algorithm for performing optimization derived from it. The approach is demonstrated on two unconstrained optimization problems, one with discrete variables and one with continuous variables. To highlight the connections between PD theory and distributed FU, the results are compared with those obtained using distributed reinforcement learning inspired optimization approaches. The inter-relationship of the techniques is discussed.

Bieniawski, Stefan R.↗

Deep-learning-based domain adaptation for cavity fault prediction at Jefferson Laboratory

Superconducting radio-frequency (SRF) cavities are the core components of the Continuous Electron Beam Accelerator Facility (CEBAF) at Jefferson Lab, providing high-power electron beams for nuclear physics experiments. The facility comprises 418 SRF cavities, and any fault in these cavities can lead to interruptions in the electron beam supply. Cavity faults are the leading cause of beam trips in CEBAF. Predicting and mitigating those faults before onset can help maintain normal operation. Existing models face challenges in distinguishing between normal and fault signals when changes occur in the underlying time-series data, from changes in control software, operational parameters, or the environment. This work proposes a deep learning domain adaptation model that leverages transfer learning to address fault prediction challenges by improving accuracy. The model is trained and fine-tuned using a dataset collected for faulty and normal operation using a data acquisition system in CEBAF. Our deep learning-based domain adaptation model achieves a prediction accuracy of 89.61% of the fault and normal signals. The developed model effectively predicts normal running signals compared to the baseline approach without domain adaptation. This capacity is essential for the fault prediction task in the CEBAF because of heavily imbalanced data containing vast amounts of normal signals. The model performs well for predicting faults several hundred milliseconds before the fault onset compared to other models where no adaptation is applied. Incorporating deep learning-based domain adaptation techniques will significantly improve the fault prediction performance.

Rahman, Md Monibor [Old Dominion Univ., Norfolk, V↗