Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “adaptive 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 1,567 records · Page 87

The Evolution of the Pegasus Workflow Management Software

Since 2001 the Pegasus Workflow Management System has evolved into a robust and scalable system that automates the execution of a number of complex applications running on a variety of heterogeneous, distributed high-throughput, and high-performance computing environments. Pegasus was built on the principle of separation between the workflow description and workflow execution, providing the ability to port and adapt the workflow based on the target execution environment. Through its user-driven research and development it has adapted to the needs of a number of scientific communities, utilizing and developing novel algorithms and software engineering solutions. This paper describes the evolution of Pegasus over time and provides motivations behind the design decisions. The paper concludes with selected lessons learned.

97 MATHEMATICS AND COMPUTING↗

Exploring Randomly Wired Neural Networks for Climate Model Emulation

Exploring the climate impacts of various anthropogenic emissions scenarios is key to making informed decisions for climate change mitigation and adaptation. State-of-the-art Earth system models can provide detailed insight into these impacts but have a large associated computational cost on a per-scenario basis. This large computational burden has driven recent interest in developing cheap machine learning models for the task of climate model emulation. In this paper, we explore the efficacy of randomly wired neural networks for this task. We describe how they can be constructed and compare them with their standard feedforward counterparts using the ClimateBench dataset. Specifically, we replace the serially connected dense layers in multilayer perceptrons, convolutional neural networks, and convolutional long short-term memory networks with randomly wired dense layers and assess the impact on model performance for models with 1 million and 10 million parameters. We find that models with less-complex architectures see the greatest performance improvement with the addition of random wiring (up to 30.4% for multilayer perceptrons). Furthermore, of 24 different model architecture, parameter count, and prediction task combinations, only one had a statistically significant performance deficit in randomly wired networks relative to their standard counterparts, with 14 cases showing statistically significant improvement. We also find no significant difference in prediction speed between networks with standard feedforward dense layers and those with randomly wired layers. These findings indicate that randomly wired neural networks may be suitable direct replacements for traditional dense layers in many standard models.

54 ENVIRONMENTAL SCIENCES↗

A Framework for Non-Pipeline Alternatives Analysis and Review of Existing Approaches

States are increasingly interested in gas distribution system planning and the role that demand-side resources can play in maintaining an affordable, reliable, equitable, and low-carbon energy system. In particular, public utility commissions and utilities are exploring the role of non-pipeline alternatives (NPA) – an investment or activity that defers, reduces, or avoids the need to construct or replace a pipeline – in gas distribution system planning. NPAs are an emerging cost and risk mitigation tool that can provide gas utilities with an opportunity to reduce emissions, gas system costs, and customer risk by avoiding unnecessary infrastructure spending. Rather than address system issues with more costly and long-lived traditional capital projects, utilities can leverage demand-side NPA resources such as energy efficiency and electrification as well as supply-side NPA resources to meet system needs. However, there is limited guidance on performing an NPA and even fewer lessons learned. To fill this gap, the U.S. Department of Energy funded two reports on NPAs. The first report is a literature review that focuses on four states' NPA policies. The second report offers a framework for evaluating NPAs that states can adapt to meet their policy needs.

03 NATURAL GAS↗

An experimental process parameter study on the identification of defects in additively fabricated Al6061 with laser powder bed fusion

Additively fabricated metal parts using laser powder bed fusion (L-PBF) possess sophisticated morphology due to the recurrent use of laser-induced metal powder melting and solidification. The surface and 3D morphology of these parts often include defects in the form of protrusions, depressions, pores, voids, keyholes, or cracks that are known to be influenced by laser scanning paths and layer-to-layer processing. Such inconsistent part quality hampers the extensive adoption of L-PBF. Pores and cracks are detrimental to the fatigue life of the parts and components. Quantifying and controlling part defects and optimizing processing and scanning strategy parameters adaptively in real-time through in situ monitoring systems are highly desired. This study investigates the optimization of experimental process parameters (power, scan velocity, and hatch spacing) and their effects on the cracking and porosity of Al6061 alloy using machine learning techniques. Multi-objective optimization is formulated and conducted to determine the L-PBF parameters that minimize both porosity and crack densities.

36 MATERIALS SCIENCE↗

Turbulent field fluctuations in gyrokinetic and fluid plasmas

A key uncertainty in the design and development of magnetic confinement fusion energy reactors is predicting edge plasma turbulence. An essential step in overcoming this uncertainty is the validation in accuracy of reduced turbulent transport models. Drift-reduced Braginskii two-fluid theory is one such set of reduced equations that has for decades simulated boundary plasmas in experiment, but significant questions exist regarding its predictive ability. To this end, using a novel physics-informed deep learning framework, we demonstrate the first ever direct quantitative comparisons of turbulent field fluctuations between electrostatic two-fluid theory and electromagnetic gyrokinetic modelling with good overall agreement found in magnetized helical plasmas at low normalized pressure. This framework is readily adaptable to experimental and astrophysical environments, and presents a new technique for the numerical validation and discovery of reduced global plasma turbulence models.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Re-Engineering the Mission Operations System (MOS) for the Prime and Extended Mission

One of the most challenging tasks in a space science mission is designing the Mission Operations System (MOS). Whereas the focus of the project is getting the spacecraft built and tested for launch, the mission operations engineers must build a system to carry out the science objectives. The completed MOS design is then formally assessed in the many reviews. Once a mission has completed the reviews, the Mission Operation System (MOS) design has been validated to the Functional Requirements and is ready for operations. The design was built based on heritage processes, new technology, and lessons learned from past experience. Furthermore, our operational concepts must be properly mapped to the mission design and science objectives. However, during the course of implementing the science objective in the operations phase after launch, the MOS experiences an evolutional change to adapt for actual performance characteristics. This drives the re-engineering of the MOS, because the MOS includes the flight and ground segments. Using the Spitzer mission as an example we demonstrate how the MOS design evolved for both the prime and extended mission to enhance the overall efficiency for science return. In our re-engineering process, we ensured that no requirements were violated or mission objectives compromised. In most cases, optimized performance across the MOS, including gains in science return as well as savings in the budget profile was achieved. Finally, we suggest a need to better categorize the Operations Phase (Phase E) in the NASA Life-Cycle Phases of Formulation and Implementation

Extended Mission↗

Optimization of Airport Runway Configuration with Forecast-Augmented Offline Reinforcement Learning

Runway configuration Management (RCM) governs the optimal utilization of runways based on variables such as traffic and meteorological conditions, making it a daunting task in air traffic management due to its dependency on volatile operational and environmental factors. This paper improves upon our previous work [1] on using offline model-free reinforcement learning for creating a Runway Configuration Assistance (RCA) decision-support tool. A novel integration of forecast data from LAMP (Localized Aviation Model Output Statistics Program) and TAF (Terminal Area Forecast) is introduced, enhancing the tool’s accuracy and also its adaptability to quick wind changes. The performance is evaluated using two major US airports, Charlotte Douglas International Airport (CLT) and Denver International Airport (DEN). To counter scalability issues presented by the addition of discrete forecast variables, we transitioned to a continuous state space model, ensuring scalability and inclusion of longer forecast data. The results of our experiments reflect significant improvements in the RCA tool’s prediction accuracy.

Sumanth Nethi↗

OpenCGRA: An Open-Source Unified Framework for Modeling,Testing, and Evaluating CGRAs

Coarse-grained reconfigurable arrays (CGRAs),loosely defined as arrays of functional units (e.g, adder, sub-tractor, multiplier, divider, or larger multi-operation units, butsmaller than a general-purpose core) interconnected through aNetwork-on-Chip, provide higher flexibility than domain-specificASIC accelerators while offering increased hardware efficiencywith respect to fine-grained reconfigurable devices, such as FieldProgrammable Gate Arrays (FPGAs). The fast evolving fieldsof machine learning and edge computing, which are seeing acontinuous flow of novel algorithms and larger models, makeCGRAs ideal target architectures to allow domain specializationwithout loosing too much generality. They also generally offerquicker and more effective reconfigurability than FPGAs, po-tentially allowing adaptation during actual algorithm execution,and implement a dataflow programming paradigm that adaptswell to these emerging workloads. Designing and generating aCGRA, however, still requires to define the type and number ofthe specific functional units, implement their interconnect andthe network topology, and perform its simulation and validation,given a variety of workloads of interest.In this paper, we propose OpenCGRA, a Python-based unifiedframework that integrates generation, modeling, testing and eval-uation for CGRAs. OpenCGRA is the first open-source integratedframework able to support the full top-to-bottom design flow forspecializing and implementing CGRAs: modeling at different ab-straction levels (functional level, cycle level, register-transfer level),generation, simulation, testing at different granularities (unit test-ing, integration testing, property-based testing), and characteriza-tion (area, power, and timing). OpenCGRAs will be made availableon GitHub.

CGRA, synthesis↗

Lessons learned in the development of the Hubble Space Telescope software

An effort is made to document what was successful in the HST software development, and to present a retrospective analysis indicating what could have been done more efficiently. Consideration is given to systems engineering and design definition, standards and tools, system architecture and design, operational considerations, and reuse and adaptation of existing resources.

Harrington, Michael↗

A review of computing-based automated fault detection and diagnosis of heating, ventilation and air conditioning systems

We report faults in Heating, Ventilation, and Air Conditioning (HVAC) systems of buildings result in significant energy waste in building operation. With fast-growing sensing data availability and advancement in computing, computational modeling has demonstrated strong capability to detect and diagnose HVAC system faults, hence, ensuring efficient building operation. This paper comprehensively reviews the state-of-the-art computing-based fault detection and diagnosis (FDD) for HVAC systems. Overall, the reviewed computing-based FDD methods are classified as two major approaches: knowledge-based and data-driven approaches. We then identify multiple important topics, including data availability, training data size, data quality, approach generality, capability, interpretability, and required modeling efforts, along with corresponding metrics to summarize the most updated FDD development. Generally, the knowledge-based approaches are further divided as physics-based modeling, Diagnostic Bayesian Network, and performance indicator-based methods while data-driven approaches include supervised learning, unsupervised learning, and regression and statistics-based methods. State-of-the-art FDD development, remaining challenges, and future research directions are further discussed to push forward FDD in practice. Availability of fault data, capability of existing methods to deal with complex fault situations (such as simultaneous faults), modeling interpretability for data-driven methods, and required engineering efforts for physics-based methods are identified as remaining challenges in FDD development. Improving modeling fidelity and reducing modeling efforts are essential for applying physics-based methods in real buildings. Meanwhile, addressing fault data availability, increasing algorithm adaptability, and handling multiple faults are essential to further enhance the applicability of data-driven FDD approaches.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Learning to Correct Climate Projection Biases

The fidelity of climate projections is often undermined by biases in climate models due to their simplification or misrepresentation of unresolved climate processes. While various bias correction methods have been developed to post-process model outputs to match observations, existing approaches usually focus on limited, low-order statistics, or break either the spatiotemporal consistency of the target variable, or its dependency upon model resolved dynamics. We develop a Regularized Adversarial Domain Adaptation (RADA) methodology to overcome these deficiencies, and enhance efficient identification and correction of climate model biases. Instead of pre-assuming the spatiotemporal characteristics of model biases, we apply discriminative neural networks to distinguish historical climate simulation samples and observation samples. The evidences based on which the discriminative neural networks make distinctions are applied to train the domain adaptation neural networks to bias correct climate simulations. We regularize the domain adaptation neural networks using cycle-consistent statistical and dynamical constraints. An application to daily precipitation projection over the contiguous United States shows that our methodology can correct all the considered moments of daily precipitation at approximately $1^\circ$ resolution, ensures spatiotemporal consistency and inter-field correlations, and can discriminate between different dynamical conditions. Our methodology offers a powerful tool for disentangling model parameterization biases from their interactions with the chaotic evolution of climate dynamics, opening a novel avenue toward big-data enhanced climate predictions.

58 GEOSCIENCES↗

From PINNs to PIKANs: recent advances in physics-informed machine learning

Physics-Informed Neural Networks (PINNs) have emerged as a key tool in Scientific Machine Learning since their introduction in 2017, enabling the efficient solution of ordinary and partial differential equations using sparse measurements. Over the past few years, significant advancements have been made in the training and optimization of PINNs, covering aspects such as network architectures, adaptive refinement, domain decomposition, and the use of adaptive weights and activation functions. A notable recent development is the Physics-Informed Kolmogorov-Arnold Networks (PIKANS), which leverage a representation model originally proposed by Kolmogorov in 1957, offering a promising alternative to traditional PINNs. In this review, we provide a comprehensive overview of the latest advancements in PINNs, focusing on improvements in network design, feature expansion, optimization techniques, uncertainty quantification, and theoretical insights. We also survey key applications across a range of fields, including biomedicine, fluid and solid mechanics, geophysics, dynamical systems, heat transfer, chemical engineering, and beyond. Lastly, we review computational frameworks and software tools developed by both academia and industry to support PINN research and applications.

Kolmogorov-Arnold networks↗

Constrained GAN-Generated X-Ray CT Data For Self-Supervised And Foundation-Model Segmentation Of Concrete Microstructures

Three-dimensional characterization of materials using X-ray computed tomography (XCT) is challenging due to the complexity of internal structures, noise, and variations in resolution. Traditional computer vision models often struggle to accurately segment these images, particularly in domain-specific applications like materials science. While supervised deep learning approaches have been developed to address the limitations of conventional algorithms, they typically require large amounts of labeled training data and often fail to generalize across different datasets. Self-supervised, few-and zero-shot learning methods have gained prominence in natural image processing and segmentation tasks, but their application to scientific imaging remains limited due to the unique structural complexity, noise, and textural artifacts present in materials science data. In this work, we investigate how domain adaptation, leveraging physics-based and GAN-generated synthetic data, impacts segmentation performance. We introduce a modified Contrastive Unpaired Translation (CUT) model designed to generate realistic labeled data, which can be used for training, pre-training, and fine-tuning segmentation models for real XCT microstructure data. We evaluate the performance of two segmentation approaches: a self-supervised network (SSL-ALPNet) and a foundation model (Segment Anything Model), assessing their improvements when pre-trained and/or fine-tuned on the synthesized data. Our results demonstrate that leveraging synthetic data significantly enhances segmentation performance, particularly in challenging materials science applications.

Ziabari, Amir [ORNL] (ORCID:000000034776457X)↗

F-Hash: Feature-Based Hash Design for Time-Varying Volume Visualization via Multi-Resolution Tesseract Encoding

Interactive time-varying volume visualization is challenging due to its complex spatiotemporal features and sheer size of the dataset. Recent works transform the original discrete time-varying volumetric data into continuous Implicit Neural Representations (INR) to address the issues of compression, rendering, and super-resolution in both spatial and temporal domains. However, training the INR takes a long time to converge, especially when handling large-scale time-varying volumetric datasets. In this work, we proposed F-Hash, a novel feature-based multi-resolution Tesseract encoding architecture to greatly enhance the convergence speed compared with existing input encoding methods for modeling time-varying volumetric data. The proposed design incorporates multi-level collision-free hash functions that map dynamic 4D multi-resolution embedding grids without bucket waste, achieving high encoding capacity with compact encoding parameters. Our encoding method is agnostic to time-varying feature detection methods, making it a unified encoding solution for feature tracking and evolution visualization. Experiments show the F-Hash achieves state-of-the-art convergence speed in training various time-varying volumetric datasets for diverse features. We also proposed an adaptive ray marching algorithm to optimize the sample streaming for faster rendering of the time-varying neural representation.

deep learning↗

Robust Uncertainty Quantification using Response Surface Approximations of Discontinuous Functions

This paper considers response surface approximations for discontinuous quantities of interest. Our objective is not to adaptively characterize the manifold defining the discontinuity. Instead, we utilize an epistemic description of the uncertainty in the location of a discontinuity to produce robust bounds on sample-based estimates of probabilistic quantities of interest. We demonstrate that two common machine learning strategies for classification, one based on nearest neighbors (Voronoi cells) and one based on support vector machines, provide reasonable descriptions of the region where the discontinuity may reside. In higher dimensional spaces, we demonstrate that support vector machines are more accurate for discontinuities defined by smooth manifolds. We also show how gradient information, often available via adjoint-based approaches, can be used to define indicators to effectively detect a discontinuity and to decompose the samples into clusters using an unsupervised learning technique. Numerical results demonstrate the epistemic bounds on probabilistic quantities of interest for simplistic models and for a compressible fluid model with a shock-induced discontinuity.

97 MATHEMATICS AND COMPUTING↗

Pairwise Association of Seismic Arrivals with Convolutional Neural Networks

Correctly determining the association of seismic phases across a network is crucial for developing accurate earthquake catalogs. Nearly all established methods use travel time information as the main criterion for determining associations, and in problems in which earthquake rates are high and many false arrivals are present, many standard techniques may fail to resolve the problem accurately. As an alternative approach, in this work we apply convolutional neural networks (CNNs) to the problem of associations; we train CNNs to read earthquake waveform arrival pairs between two stations and predict the binary classification of whether the two waveforms are from a common source or different sources. Applying the method to a large training dataset of previously cataloged earthquakes in Chile, we obtain >80% true positive prediction rates for high-frequency data (>2 Hz) and stations separated in excess of 100 km. As a secondary benefit, the output of the neural network can also be used to infer predicted phase types of arrivals. Here, the method is ideally applied in conjunction with standard travel-time-based association routines and can be adapted for arbitrary network geometries and applications, so long as sufficient training data are available.

58 GEOSCIENCES↗

Surgical Force-Measuring Probe

Aerodynamic balance adapted to medical use. Electromechanical probe measures forces and moments applied to human tissue during surgery. Measurements used to document optimum forces and moments for surgical research and training. In neurosurgical research, measurements correlated with monitored responses of nerves. In training, students learn procedures by emulating forces used by experienced surgeons. Lightweight, pen-shaped probe easily held by surgeon. Cable feeds output signals to processing circuitry.

Tcheng, Ping↗

Effects of Motion Cues on the Training of Multi-Axis Manual Control Skills

The study described in this paper investigated the effects of two different hexapod motion configurations on the training and transfer of training of a simultaneous roll and pitch control task. Pilots were divided between two groups which trained either under a baseline hexapod motion condition, with motion typically provided by current training simulators, or an optimized hexapod motion condition, with increased fidelity of the motion cues most relevant for the task. All pilots transferred to the same full-motion condition, representing motion experienced in flight. A cybernetic approach was used that gave insights into the development of pilots use of visual and motion cues over the course of training and after transfer. Based on the current results, neither of the hexapod motion conditions can unambiguously be chosen as providing the best motion for training and transfer of training of the used multi-axis control task. However, the optimized hexapod motion condition did allow pilots to generate less visual lead, control with higher gains, and have better disturbance-rejection performance at the end of the training session compared to the baseline hexapod motion condition. Significant adaptations in control behavior still occurred in the transfer phase under the full-motion condition for both groups. Pilots behaved less linearly compared to previous single-axis control-task experiments; however, this did not result in smaller motion or learning effects. Motion and learning effects were more pronounced in pitch compared to roll. Finally, valuable lessons were learned that allow us to improve the adopted approach for future transfer-of-training studies.

flight simulators↗