SEARCH · Engineering Papers

Results for “data driven”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,513 records · Page 84

All sources NASA NTRS DOE OSTI

DOE OSTI2022

Grassmannian Shape Representations for Aerodynamic Applications

Airfoil shape design is a classical problem in engineering, science, and manufacturing. Our motivation is to combine principled physics-based considerations for the shape design problem with modern computational techniques informed by a data-driven approach. Traditional analyses of airfoil shapes emphasize a flow-based sensitivity to deformations which can be represented generally by affine transformations (rotation, scaling, shearing, shifting). We present a novel representation of shapes which decouples affine-style deformations from a rich set of data-driven deformations over a submanifold of the Grassmannian. The Grassmannian representation, informed by a database of physically relevant airfoils, offers (i) a rich set of novel 2D airfoil deformations not previously captured in the data, (ii) improved low-dimensional parameter domain for inferential statistics, and (iii) consistent 3D blade representation and perturbation over a sequence of nominal shapes.

blade representation↗

DOE OSTI2024

Toward Accelerating Discovery via Physics-Driven and Interactive Multifidelity Bayesian Optimization

Both computational and experimental material discovery bring forth the challenge of exploring multidimensional and often nondifferentiable parameter spaces, such as phase diagrams of Hamiltonians with multiple interactions, composition spaces of combinatorial libraries, processing spaces, and molecular embedding spaces. Often these systems are expensive or time consuming to evaluate a single instance, and hence classical approaches based on exhaustive grid or random search are too data intensive. This resulted in strong interest toward active learning methods such as Bayesian optimization (BO) where the adaptive exploration occurs based on human learning (discovery) objective. However, classical BO is based on a predefined optimization target, and policies balancing exploration and exploitation are purely data driven. In practical settings, the domain expert can pose prior knowledge of the system in the form of partially known physics laws and exploration policies often vary during the experiment. Here, we propose an interactive workflow building on multifidelity BO (MFBO), starting with classical (data-driven) MFBO, then expand to a proposed structured (physics-driven) structured MFBO (sMFBO), and finally extend it to allow human-in-the-loop interactive interactive MFBO (iMFBO) workflows for adaptive and domain expert aligned exploration. These approaches are demonstrated over highly nonsmooth multifidelity simulation data generated from an Ising model, considering spin–spin interaction as parameter space, lattice sizes as fidelity spaces, and the objective as maximizing heat capacity. Detailed analysis and comparison show the impact of physics knowledge injection and real-time human decisions for improved exploration with increased alignment to ground truth. Here, the associated notebooks allow to reproduce the reported analyses and apply them to other systems.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2016

Improved frame-based estimation of head motion in PET brain imaging

Purpose: Head motion during PET brain imaging can cause significant degradation of image quality. Several authors have proposed ways to compensate for PET brain motion to restore image quality and improve quantitation. Head restraints can reduce movement but are unreliable; thus the need for alternative strategies such as data-driven motion estimation or external motion tracking. Herein, the authors present a data-driven motion estimation method using a preprocessing technique that allows the usage of very short duration frames, thus reducing the intraframe motion problem commonly observed in the multiple frame acquisition method. Methods: The list mode data for PET acquisition is uniformly divided into 5-s frames and images are reconstructed without attenuation correction. Interframe motion is estimated using a 3D multiresolution registration algorithm and subsequently compensated for. For this study, the authors used 8 PET brain studies that used F-18 FDG as the tracer and contained minor or no initial motion. After reconstruction and prior to motion estimation, known motion was introduced to each frame to simulate head motion during a PET acquisition. To investigate the trade-off in motion estimation and compensation with respect to frames of different length, the authors summed 5-s frames accordingly to produce 10 and 60 s frames. Summed images generated from the motion-compensated reconstructed frames were then compared to the original PET image reconstruction without motion compensation. Results: The authors found that our method is able to compensate for both gradual and step-like motions using frame times as short as 5 s with a spatial accuracy of 0.2 mm on average. Complex volunteer motion involving all six degrees of freedom was estimated with lower accuracy (0.3 mm on average) than the other types investigated. Preprocessing of 5-s images was necessary for successful image registration. Since their method utilizes nonattenuation corrected frames, it is not susceptible to motion introduced between CT and PET acquisitions. Conclusions: The authors have shown that they can estimate motion for frames with time intervals as short as 5 s using nonattenuation corrected reconstructed FDG PET brain images. Intraframe motion in 60-s frames causes degradation of accuracy to about 2 mm based on the motion type.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2016

Expanding the role of reactive transport models in critical zone processes

We report that models test our understanding of processes and can reach beyond the spatial and temporal scales of measurements. Multi-component Reactive Transport Models (RTMs), initially developed more than three decades ago, have been used extensively to explore the interactions of geothermal, hydrologic, geochemical, and geobiological processes in subsurface systems. Driven by extensive data sets now available from intensive measurement efforts, there is a pressing need to couple RTMs with other community models to explore non-linear interactions among the atmosphere, hydrosphere, biosphere, and geosphere. Here we briefly review the history of RTM development, summarize the current state of RTM approaches, and identify new research directions, opportunities, and infrastructure needs to broaden the use of RTMs. In particular, we envision the expanded use of RTMs in advancing process understanding in the Critical Zone, the veneer of the Earth that extends from the top of vegetation to the bottom of groundwater. We argue that, although parsimonious models are essential at larger scales, process-based models offer tools to explore the highly nonlinear coupling that characterizes natural systems. We present seven testable hypotheses that emphasize the unique capabilities of process-based RTMs for (1) elucidating chemical weathering and its physical and biogeochemical drivers; (2) understanding the interactions among roots, micro-organisms, carbon, water, and minerals in the rhizosphere; (3) assessing the effects of heterogeneity across spatial and temporal scales; and (4) integrating the vast quantity of novel data, including “omics” data (genomics, transcriptomics, proteomics, metabolomics), elemental concentration and speciation data, and isotope data into our understanding of complex earth surface systems. In conclusion, with strong support from data-driven sciences, we are now in an exciting era where integration of RTM framework into other community models will facilitate process understanding across disciplines and across scales.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2021

Classification and regression models of audio and vibration signals for machine state monitoring in precision machining systems

Here we present a data-driven method for monitoring machine status in manufacturing processes. Audio and vibration data from precision machining are used for inference in two operating scenarios: (a) variable machine health states (anomaly detection); and (b) settings of machine operation (state estimation). Audio and vibration signals are first processed through Fast Fourier Transform and Principal Component Analysis to extract transformed and informative features. These features are then used in the training of classification and regression models for machine state monitoring. Specifically, three classifiers (K-nearest neighbors, convolutional neural networks and support vector machines) and two regressors (support vector regression and neural network regression) were explored, in terms of their accuracy in machine state prediction. It is shown that the audio and vibration signals are sufficiently rich in information about the machine that 100% state classification accuracy could be accomplished. Data fusion was also explored, showing overall superior accuracy of data-driven regression models.

42 ENGINEERING↗

DOE OSTI2022

CONGO²: Scalable Online Anomaly Detection and Localization in Power Electronics Networks

Rapid and accurate detection and localization of electronic disturbances simultaneously are important for preventing its potential damages and determining potential remedies. Existing anomaly detection methods are severely limited by the low accuracy, the expensive computational cost and the need for highly trained personnel. There is an urgent need for a scalable online algorithm for in-field analysis of large-scale power electronics networks. Here in this paper, we propose a fast and accurate algorithm for anomaly detection and localization of power electronics networks: stratified colored-node graph (CONGO2). This algorithm hierarchically models the change of correlated waveforms and then correlated sensors using the colored-node graph. By aggregating the change of each sensor with its neighbors’ inputs, we can spontaneously identify and localize the anomaly that cannot be detected by data collected from a single sensor. As our proposed method only focuses on the changes within a short time frame, it is highly computational efficient and only needs small data storage. Thus, our method is ideal for online and reliable anomaly detection and localization of large-scale power electronic networks. Compared to existing anomaly detection methods, our method is entirely data-driven without training data, highly accurate and reliable for wide-spectrum anomalies detection, and more importantly, capable of both detection and localization. Thus, it is ideal for infield deployment for large-scale power electronic networks. As illustrated by a distributed energy resources (DERs) power grid with 37-node, our method can effectively detect and localize various cyber and physical attacks.

42 ENGINEERING↗

DOE OSTI2022

Inferring plant–plant interactions using remote sensing

Rapid technological advancements and increasing data availability have improved the capacity to monitor and evaluate Earth's ecology via remote sensing. However, remote sensing is notoriously ‘blind’ to fine-scale ecological processes such as interactions among plants, which encompass a central topic in ecology. Here, we discuss how remote sensing technologies can help infer plant–plant interactions and their roles in shaping plant-based systems at individual, community and landscape levels. At each of these levels, we outline the key attributes of ecosystems that emerge as a product of plant–plant interactions and could possibly be detected by remote sensing data. We review the theoretical bases, approaches and prospects of how inference of plant–plant interactions can be assessed remotely. At the individual level, we illustrate how close-range remote sensing tools can help to infer plant–plant interactions, especially in experimental settings. At the community level, we use forests to illustrate how remotely sensed community structure can be used to infer dominant interactions as a fundamental force in shaping plant communities. At the landscape level, we highlight how remotely sensed attributes of vegetation states and spatial vegetation patterns can be used to assess the role of local plant–plant interactions in shaping landscape ecological systems. Synthesis . Remote sensing extends the domain of plant ecology to broader and finer spatial scales, assisting to scale ecological patterns and search for generic rules. Robust remote sensing approaches are likely to extend our understanding of how plant–plant interactions shape ecological processes across scales—from individuals to landscapes. Combining these approaches with theories, models, experiments, data-driven approaches and data analysis algorithms will firmly embed remote sensing techniques into ecological context and open new pathways to better understand biotic interactions.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2019

Dynamic color mapping with a multi-scale histogram: A design study with physical scientists

Many research and development activities for scientific data analysis have focused on scalability challenges and data-driven features. Conversely, data visualization that focus on models requiring human interaction rarely involve practical and largescale scientific data analysis. Therefore, a gap exists between interactive data visualization and scientific data analysis applications. In this paper, we present a design study of interactive data visualization to support scientists who visually analyze data from neutron scattering experiments. This study was conducted in multiple phases: 1) problem characterization; 2) initial design and formative evaluation; and 3) iterative design. We characterize the problems and the design requirements for the analysis of the specific physical science data. We discuss the design, development, evaluation of our visual analytics tool and as well as our iterative developments with physical scientists. We show how to bridge the gap between the two disciplines uncovering new potential to solve their challenges in this design study. We focus on a specific challenge, finding an optimal color mapping, which plays a critical role in neutron scattering science and is broadly applicable to other scientific domains. To address the challenge, we propose two interactive visualization techniques: a dynamic color scale bar (DCSB) and a multi-scale histogram (MSH).

Chae, Junghoon↗

NASA NTRS2011

Electronic Health Management

Accelerated aging methodologies for electrolytic components have been designed and accelerated aging experiments have been carried out. The methodology is based on imposing electrical and/or thermal overstresses via electrical power cycling in order to mimic the real world operation behavior. Data are collected in-situ and offline in order to periodically characterize the devices' electrical performance as it ages. The data generated through these experiments are meant to provide capability for the validation of prognostic algorithms (both model-based and data-driven). Furthermore, the data allow validation of physics-based and empirical based degradation models for this type of capacitor. A first set of models and algorithms has been designed and tested on the data.

Celaya, Jose R.↗

NASA NTRS2012

Global CO2 Distributions over Land from the Greenhouse Gases Observing Satellite (GOSAT)

January 2009 saw the successful launch of the first space-based mission specifically designed for measuring greenhouse gases, the Japanese Greenhouse gases Observing SATellite (GOSAT). We present global land maps (Level 3 data) of column-averaged CO2 concentrations (X(sub CO2)) derived using observations from the GOSAT ACOS retrieval algorithm, for July through December 2009. The applied geostatistical mapping approach makes it possible to generate maps at high spatial and temporal resolutions that include uncertainty measures and that are derived directly from the Level 2 observations, without invoking an atmospheric transport model or estimates of CO2 uptake and emissions. As such, they are particularly well suited for comparison studies. Results show that the Level 3 maps for July to December 2009 on a lO x 1.250 grid, at six-day resolution capture much of the synoptic scale and regional variability of X(sub CO2), in addition to its overall seasonality. The uncertainty estimates, which reflect local data coverage, X(sub CO2) variability, and retrieval errors, indicate that the Southern latitudes are relatively well-constrained, while the Sahara Desert and the high Northern latitudes are weakly-constrained. A probabilistic comparison to the PCTM/GEOS-5/CASA-GFED model reveals that the most statistically significant discrepancies occur in South America in July and August, and central Asia in September to December. While still preliminary, these results illustrate the usefulness of a high spatiotemporal resolution, data-driven Level 3 data product for direct interpretation and comparison of satellite observations of highly dynamic parameters such as atmospheric CO2.

Hammerling, Dorit M.↗

NASA NTRS2016

Datalist: A Value Added Service to Enable Easy Data Selection

Imagine a user wanting to study hurricane events. This could involve searching and downloading multiple data variables from multiple data sets. The currently available services from the Goddard Earth Sciences Data and Information Services Center (GES DISC) only allow the user to select one data set at a time. The GES DISC started a Data List initiative, in order to enable users to easily select multiple data variables. A Data List is a collection of predefined or user-defined data variables from one or more archived data sets. Target users of Data Lists include science teams, individual science researchers, application users, and educational users. Data Lists are more than just data. Data Lists effectively provide users with a sophisticated integrated data and services package, including metadata, citation, documentation, visualization, and data-specific services, all available from one-stop shopping. Data Lists are created based on the software architecture of the GES DISC Unified User Interface (UUI). The Data List service is completely data-driven, and a Data List is treated just as any other data set. The predefined Data Lists, created by the experienced GES DISC science support team, should save a significant amount of time that users would otherwise have to spend.

Datalist↗

NASA NTRS2017

On the Impact of Granularity of Space-Based Urban CO2 Emissions in Urban Atmospheric Inversions: A Case Study for Indianapolis, IN

Quantifying greenhouse gas (GHG) emissions from cities is a key challenge towards effective emissions management. An inversion analysis from the INdianapolis FLUX experiment (INFLUX) project, as the first of its kind, has achieved a top-down emission estimate for a single city using CO2 data collected by the dense tower network deployed across the city. However, city-level emission data, used as a priori emissions, are also a key component in the atmospheric inversion framework. Currently, fine-grained emission inventories (EIs) able to resolve GHG city emissions at high spatial resolution, are only available for few major cities across the globe. Following the INFLUX inversion case with a global 1x1 km ODIAC fossil fuel CO2 emission dataset, we further improved the ODIAC emission field and examined its utility as a prior for the city scale inversion. We disaggregated the 1x1 km ODIAC non-point source emissions using geospatial datasets such as the global road network data and satellite-data driven surface imperviousness data to a 3030 m resolution. We assessed the impact of the improved emission field on the inversion result, relative to priors in previous studies (Hestia and ODIAC). The posterior total emission estimate (5.1 MtC/yr) remains statistically similar to the previous estimate with ODIAC (5.3 MtC/yr). However, the distribution of the flux corrections was very close to those of Hestia inversion and the model-observation mismatches were significantly reduced both in forward and inverse runs, even without hourly temporal changes in emissions. EIs reported by cities often do not have estimates of spatial extents. Thus, emission disaggregation is a required step when verifying those reported emissions using atmospheric models. Our approach offers gridded emission estimates for global cities that could serves as a prior for inversion, even without locally reported EIs in a systematic way to support city-level Measuring, Reporting and Verification (MRV) practice implementation.

EIs↗

DOE OSTI2024

Industry case studies: Finance

This article, the third in a series on the U.S. Department of Energy and IDEA collaboration, focuses on financial strategies used by institutions to support district energy system modernization and decarbonization. It highlights how effective funding models, long-term cost analysis, and leadership support are critical to implementing large-scale infrastructure upgrades. The case studies show different approaches to financing. Ball State University demonstrates how life-cycle cost analysis and phased funding—supported by state funding, bonds, and grants—enabled a transition to geothermal energy. Penn State’s Hershey Medical Center emphasizes the importance of financial leadership, shifting from reactive budgeting to data-driven, proactive investment in infrastructure. The University of Washington highlights how comprehensive data collection and analytics can justify investments and even create self-sustaining funding mechanisms like green revolving funds. Overall, the article shows that combining strong financial planning, data-driven decision-making, and innovative funding approaches is essential for advancing sustainable district energy systems while managing high upfront costs.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

DOE OSTI2022

Equation‐Free Surrogate Modeling of Geophysical Flows at the Intersection of Machine Learning and Data Assimilation

Abstract There is a growing interest in developing data‐driven reduced‐order models for atmospheric and oceanic flows that are trained on data obtained either from high‐resolution simulations or satellite observations. The data‐driven models are non‐intrusive in nature and offer significant computational savings compared to large‐scale numerical models. These low‐dimensional models can be utilized to reduce the computational burden of generating forecasts and estimating model uncertainty without losing the key information needed for data assimilation (DA) to produce accurate state estimates. This paper aims at exploring an equation‐free surrogate modeling approach at the intersection of machine learning and DA in Earth system modeling. With this objective, we introduce an end‐to‐end non‐intrusive reduced‐order modeling (NIROM) framework equipped with contributions in modal decomposition, time series prediction, optimal sensor placement, and sequential DA. Specifically, we use proper orthogonal decomposition (POD) to identify the dominant structures of the flow, and a long short‐term memory network to model the dynamics of the POD modes. The NIROM is integrated within the deterministic ensemble Kalman filter (DEnKF) to incorporate sparse and noisy observations at optimal sensor locations obtained through QR pivoting. The feasibility and the benefit of the proposed framework are demonstrated for the NOAA Optimum Interpolation Sea Surface Temperature (SST) V2 data set. Our results indicate that the NIROM is stable for long‐term forecasting and can model dynamics of SST with a reasonable level of accuracy. Furthermore, the prediction accuracy of the NIROM gets improved by almost one order of magnitude by the DEnKF algorithm.

Pawar, Suraj↗

NASA NTRSDate not supplied

Developing Deep Learning Models for System Remaining Useful Life Predictions: Application to Aircraft Engines

Prognostics and health management (PHM) is an important part of ensuring reliable operations of complex safety- critical systems. System-level remaining useful life (RUL) estimation is a much more complex problem than making estimations at the component level, and system-level RUL methodologies remain sparse in the literature. Model-based approaches have traditionally worked in the past for components such as capacitors, MOSFETs, batteries, or hard-drives (to name a few examples), but developing high fidelity dynamics models of cyber physical systems that can be used to study the effects of multiple degrading components in the system remains a challenging task. Some initial work on model-based System RUL predictions was demonstrated in Khorasgani, et al [1], but, to generalize the system-level prognostics problem, we have to resort to pure data driven and hybrid approaches. In this work, we propose an end-to-end data- driven framework for developing deep learning models to predict remaining useful life of cyber physical systems operating under unknown faulty conditions. The raw data is organized with a data schema that improves the model development process and down stream data analysis tasks. Due to the unknown faulty conditions, the raw sensor data is transformed into signals that expose the underlying degradation processes, which are then used for model development. Bayesian Optimization is used to tune the model parameters prior to training and validation. We show that this approach results in accurate predictions within 3 cycles to end of life (EOL). We demonstrate the effectiveness of our approach by applying it to the N-CMAPSS turbofan engine dataset recently released by NASA, which includes high fidelity degradation modeling, real world operating conditions, and a large set of fault operating modes.

Prognostics↗

DOE OSTI2022

Accuracy of predictions made by machine learned models for biocrude yields obtained from hydrothermal liquefaction of organic wastes

Hydrothermal liquefaction (HTL) has potential for converting abundant wet organic wastes into renewable fuels. Because HTL consists of a complex reaction network, deterministic, physics-based prediction of its biocrude yield is prohibitively difficult. Data-driven methods provide an alternative to the physics-based approach; however, rigorous testing must be performed to ensure the accuracy of predictions made by data-driven methods. To this end, a data set was assembled consisting of 570 data points appearing in the open literature. The data set was divided into training, validation, and test sub-sets and used for evaluating different machine learning regression approaches to predict biocrude yield. Among the tested algorithms, Random Forest and eXtreme Gradient Boosting (XGBoost) predicted biocrude yields in a test set that had not been used for training with the greatest accuracy, with root mean square errors (RMSE) of 8.34 and 8.57, respectively. Further refinement of the Random Forest model reduced its RMSE to 8.07. In comparison, predictions of a series of literature models resulted in RMSE ranging from 9.16 in the most accurate case to 27.6 in the least accurate; most literature models yielded RMSE values > 10. Using biocrude yield predictions from the most accurate Random Forest model and a probabilistic economic analysis found that the model accuracy is sufficient to prioritize allocation of resources based on projected minimum fuel selling price. In our report the models and analysis represent a major advance in the ability to use readily available data to predict biocrude yields on new feedstocks that have not previously been studied.

42 ENGINEERING↗

DOE OSTI2019

Application of the Koopman Operator-Theoretic Framework to Power System Dynamic State Estimation

Model-based and data-driven methods are combined to develop a hierarchical decentralized, robust dynamic state estimator (DSE). A two-level hierarchy is proposed, where the lower level consists of robust, model-based, decentralized DSEs. The state estimates sent from the lower level are received at the upper level, where they are filtered by a robust data-driven DSE. The proposed hybrid framework does not depend on the centralized infrastructure of the control centers; thus it can be completely embedded into the wide-area measurement systems. This feature will ultimately facilitate the placement of hierarchical decentralized control schemes at the phasor data concentrator locations. Also, the network model is not necessary; thus, a topology processor is not required. Finally, there is no assumption on the dynamics of the electric loads. The proposed framework is tested on the 2,000-bus synthetic Texas system and shown to be capable of reconstructing the dynamic states of the generators with high accuracy, and of forecasting in the advent of missing data.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2020

Assessing Current and Future Infrastructure Hazards

Project Objective Execute intelligent analytics via an advanced analytical framework, to assess the current state of offshore infrastructure, evaluate infrastructure life, and identify technologies to reduce infrastructure hazards, costs, and extend infrastructure life. Approach & Results thus Far• Build comprehensive dataset• Perform data-driven analytics to evaluate infrastructure integrity 1. Remaining lifespan 2. Likelihood of future risk• Apply data-driven advanced spatial, statistical, and Machine Learning (ML) models to quantify existing infrastructure integrity• Release data and models through a smart, online platform hosted by Energy Data eXchange (EDX)

Romeo, Lucy F.↗