Engineering Papers⌕ Search

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.

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

At least 1,747 records · Page 97

FAST: Using Federal Fleet Data for Decision-Making

This presentation provides an overview of the information currently being collected by the US Department of Energy, US General Services Administration, and US Energy Information Administration about the federal government's fleet of motor vehicles. The recent transition to collecting this information at the individual vehicle level provides new ways of visualizing the fleet and its operation and of using the information to support new forms of data-driven decision-making about the fleet. This presentation provides three examples of the types of analysis and decision-making this dataset supports.

99 GENERAL AND MISCELLANEOUS↗

Predictive multiscale modeling for Unidirectional Carbon Fiber Reinforced Polymers

This paper presents a predictive multiscale modeling scheme for Unidirectional (UD) Carbon Fiber Reinforced Polymers (CFRP). A bottom-up modeling procedure is discussed for predicting the performance of UD structures. UD material responses are computed from high fidelity Representative Volume Elements (RVEs). A data-driven Reduced Order Modeling approach compresses RVEs into Reduced Order Models so material responses can be computed in a concurrent fashion along with the structural level simulation. The approach presented in this paper is validated against experimental data and is believed to provide design guidance for future fiber reinforced polymers development.

36 MATERIALS SCIENCE↗

Digitalization of an experimental electrochemical reactor via the smart manufacturing innovation platform

The exponential increase in data produced over the last two decades has revolutionized the way we collect, store, process, analyze, model, and interpret information to improve profitability. Manufacturing is no exception. How- ever, Smart Manufacturing, the digital practice, organization, workforce, and infrastructure transformation for collection and deployment of data and models at scale and at all levels of manufacturing, is a complex, costly, and labor-intensive journey that is still seeing slow adoption. The Clean Energy Smart Manufacturing Innovation Institute (CESMII), a national Manufacturing USA public-private partnership sponsored by the Department of Energy, is addressing this scaled use of data and modeling in manufacturing. CESMII has focused on how to col- lect and use operating data for numerous applications that improve productivity, precision, and performance of manufacturing operations from factory floor to supply chain using process simulation, predictive analytics, mon- itoring and control, and real-time optimization. Because contextualized data are key, CESMII has developed the Smart Manufacturing Innovation Platform (SMIP) to lower the barriers to the data that are needed to accelerate data-based model building, improve data visualization, and more quickly gain insights. Reusable, standards-based ways of doing data collection, ingestion, and contextualization are particularly important for scaling access and use of data. The SMIP uses a standards-based definition and construct for reusable information models called an SM Profile. When an SM Profile is used in conjunction with the SMIP, the SMIP ensures the availability of contextualized, operational data for model building. The present work demonstrates Smart Manufacturing and the application of the SMIP for building several data-centered models for the operation and control of an ex- perimental electrochemical reactor that reduces carbon dioxide (CO 2 ) gas to valuable liquid and gas chemicals, such as alcohols, olefins, and syngas. We describe how the SMIP plays a central role in more effective model building and we demonstrate how the electochemical reactor can be controlled and optimized for the desired products. Use of the SMIP involves the transmission of real-time sensor measurements to a cloud resource so that the operating data are available to all model building experts. The data collection and transmission process is fully automated to greatly reduce the need for manual manipulation of the data. Data-driven machine learning models are used for advanced real-time state estimation, real-time optimization, and model-based feedback control for the reactor. The application models are implemented as a system to monitor the data flow and control the electrochemical reactor with a single visualization interface. SM Profiles are used to demonstrate reusability of the information models for the reactor and the instrumentation. The application packages, algorithms, and user interfaces developed are cast as Docker images in a library to facilitate reusability of the application models.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Autonomous Inverter Controls for Resilient and Secure Grid Operation: Vector Control Design for Grid Forming

The project addresses both fundamental and practical challenges of GFM/GFL inverter control for the power grids with high inverter based resources (IBRs) penetration. A data- driven modeling technique is applied to accurately model dynamics of PWM inverters, including electromagnetic-transient (EMT). Systematic and integrative designs of grid- forming (GFM) and grid-following (GFL) primary controls are developed to guarantee system performance under either normal or abnormal operating conditions without violating constraints. This modeling and control framework provides black-start capability in case of an outage without relying on rotating generators, and its secondary control is also shown to enhance resilience against cyber-physical attacks.

14 SOLAR ENERGY↗

Bayesian learning with Gaussian processes for low-dimensional representations of time-dependent nonlinear systems

This work presents a data-driven method for learning low-dimensional time-dependent physics-based surrogate models whose predictions are endowed with uncertainty estimates. We use the operator inference approach to model reduction that poses the problem of learning low-dimensional model terms as a regression of state space data and corresponding time derivatives by minimizing the residual of reduced system equations. Standard operator inference models perform well with accurate training data that are dense in time, but producing stable and accurate models when the state data are noisy and/or sparse in time remains a challenge. Another challenge is the lack of uncertainty estimation for the predictions from the operator inference models. Our approach addresses these challenges by incorporating Gaussian process surrogates into the operator inference framework to (1) probabilistically describe uncertainties in the state predictions and (2) procure analytical time derivative estimates with quantified uncertainties. The formulation leads to a generalized least-squares regression and, ultimately, reduced-order models that are described probabilistically with a closed-form expression for the posterior distribution of the operators. The resulting probabilistic surrogate model propagates uncertainties from the observed state data to reduced-order predictions. Furthermore, we demonstrate the method is effective for constructing low-dimensional models of two nonlinear partial differential equations representing a compressible flow and a nonlinear diffusion–reaction process, as well as for estimating the parameters of a low-dimensional system of nonlinear ordinary differential equations representing compartmental models in epidemiology.

Data-driven model reduction↗

Open data sets for assessing photovoltaic system reliability

Photovoltaic (PV) systems have become a cornerstone of renewable energy strategies, particularly due to the significant reduction in solar power costs over the past decade. However, the long-term reliability of PV installations presents a persistent challenge, requiring the development of advanced monitoring and predictive maintenance strategies. A wide range of data types is used to evaluate the health of PV systems, including environmental conditions, electrical performance, and inspection imagery. These data enable methodologies such as machine learning (ML) models for lifetime prediction and computer vision techniques for defect detection. However, the acquisition of high-quality and comprehensive data is difficult, particularly in terms of long-term consistency and data variety. Publicly available data sets serve as valuable resources for addressing these challenges, but they often suffer from fragmentation and are difficult to access. This paper presents a comprehensive review of existing open-source data sets related to PV degradation, analyzing their features, functionalities, and potential applications. We categorize these data sets based on the specific aspects of PV system information they cover, such as environmental conditions, operational monitoring, image inspection and module materials, and propose relevant tools and ML models for processing them. In addition, we propose practices for future data collection and usage, while also discussing potential directions in data-driven research. Our aim is to enhance data utilization and publication among researchers and industry professionals, promoting a deeper understanding of the role of data in enhancing the performance and durability of PV systems.

14 SOLAR ENERGY↗

Real-Time Automated Hazard Detection Framework for Health Information Technology Systems

An increase in the reliability of Health Information Technology (HIT) will facilitate institutional trust and credibility of the systems. Here, we present an end-to-end framework for improving the reliability and performance of HIT systems. Specifically, we describe the system model, present some of the methods that drive the model, and discuss an initial implementation of two of the proposed methods using data from the Veterans Affairs HIT and Corporate Data Warehouse systems. The contributions of this work, thus, include (1) the design of a system model for monitoring and detecting hazards in HIT systems, (2) a data-driven approach for analysing the health care data warehouse, (3) analytical methods for characterising and analysing failures in HIT systems, and (4) a tool architecture for generating and reporting hazards in HIT systems. Our goal is to work towards an automated system that will help identify opportunities for improvements in HIT systems.

97 MATHEMATICS AND COMPUTING↗

Electron neutrino appearance in the NOvA experiment

NOvA is an off-axis, two-detector experiment studying neutrino oscillations with the ν(µ) beam from Fermilab. This paper describes the ν e appearance analysis, including data-driven constraints from Near Detector measurements. The data set corresponds to an exposure equivalent to 6.05 × 10 20 protons-on-target in the Far Detector. Here, we observed 33 ν e candidates with a predicted background of 8.2 ± 0.8 (syst.), for a significance of appearance higher than 8σ. Preliminary results for the allowed values of δ CP and θ 23 in both hierarchies are presented.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Online Event Detection in Synchrophasor Data with Graph Signal Processing

Online detection of anomalies is crucial to enhancing the reliability and resiliency of power systems. We propose a novel data-driven online event detection algorithm with synchrophasor data using graph signal processing. In addition to being extremely scalable, our proposed algorithm can accurately capture and leverage the spatio-temporal correlations of the streaming PMU data. This paper also develops a general technique to decouple spatial and temporal correlations in multiple time series. Finally, we develop a unique framework to construct a weighted adjacency matrix and graph Laplacian for product graph. Case studies with real-world, large-scale synchrophasor data demonstrate the scalability and accuracy of our proposed event detection algorithm. Compared to the state-of-the-art benchmark, the proposed method not only achieves higher detection accuracy but also yields higher computational efficiency.

Event detection↗

Search for light neutral particles decaying promptly into collimated pairs of electrons or muons in pp collisions at $\sqrt{s}$ = 13 TeV with the ATLAS detector

A search for a dark photon, a new light neutral particle, which decays promptly into collimated pairs of electrons or muons is presented. The search targets dark photons resulting from the exotic decay of the Standard Model Higgs boson, assuming its production via the dominant gluon-gluon fusion mode. The analysis is based on 140 fb -1 of data collected with the ATLAS detector at the Large Hadron Collider from proton-proton collisions at a center-of-mass energy of 13 TeV. Events with collimated pairs of electrons or muons are analysed and background contributions are estimated using data-driven techniques. No significant excess in the data above the Standard Model background is observed. Upper limits are set at 95% confidence level on the branching ratio of the Higgs boson decay into dark photons between 0.001% and 5%, depending on the assumed dark photon mass and signal model.

Aad, G. [Aix-Marseille Université] (ORCID:00000002↗

Provenance infrastructure for multimodal x-ray experiments and reproducible analysis

Exploring relationships between material structures and desired properties for material discovery and synthesis requires mining machine-readable databases and linking experimental data with sufficiently rich annotations. There are vast gaps both in these data sources and in the connections between them. We present a provenance-based data management and analysis framework that enables capturing, persisting, and reanalyzing experimental data from the BNL National Synchrotron Light Source II (NSLS-II). Our system leverages NSLS-II Bluesky for experimental data acquisition, captures analysis parameters, and enriches the search space with results from the scientific literature. We describe in detail the challenges and benefits of data-driven approaches when comparing computational and experimental data, such as the multiple possible scenarios of interest in often ill-posed inverse problems and missing data. Our infrastructure utilizes the NSLS-II event model and includes discovery mechanisms across multiple beamlines. A text and data mining module using natural language processing classification techniques extracts relevant information from the literature that is added to data sources. We describe a provenance acquisition and analysis rerun workflow based on a directed acyclic graph that keeps track of process and data provenance and allows to replay analysis.

97 MATHEMATICS AND COMPUTING↗

Statistical Treatment of Convolutional Neural Network Superresolution of Inland Surface Wind for Subgrid-Scale Variability Quantification

Abstract Machine learning models have been employed to perform either physics-free data-driven or hybrid dynamical downscaling of climate data. Most of these implementations operate over relatively small downscaling factors because of the challenge of recovering fine-scale information from coarse data. This limits their compatibility with many global climate model outputs, often available between ∼50- and 100-km resolution, to scales of interest such as cloud resolving or urban scales. This study systematically examines the capability of a type of superresolving convolutional neural network (SR-CNNs) to downscale surface wind speed data over land from different coarse resolutions (25-, 48-, and 100-km resolution) to 3 km. For each downscaling factor, we consider three convolutional neural network (CNN) configurations that generate superresolved predictions of fine-scale wind speed, which take between one and three input fields: coarse wind speed, fine-scale topography, and diurnal cycle. In addition to fine-scale wind speeds, probability density function parameters are generated through which sample wind speeds can be generated, accounting for the intrinsic stochasticity of wind speed. For assessing generalization to new data, CNN models are tested on regions with different topography and climate that are unseen during training. The evaluation of superresolved predictions focuses on subgrid-scale variability and the recovery of extremes. Models with coarse wind and fine topography as inputs exhibit the best performance when compared with other model configurations, operating across the same downscaling factor. Our diurnal cycle encoding results in lower out-of-sample generalizability when compared with other input configurations.

17 WIND ENERGY↗

Data Assessment and Assimilation for Atmospheric Radiation Measurement Data Using Dynamic Bayesian Networks

A data-driven machine learning approach to scientific sensor data assessment may automatically learn directly from the structural and temporal patterns in abundant observations. The project has developed data assessment and assimilation models to screen datasets using dynamic Bayesian network (DBN) and deep learning (DL) methods, which rely on correlations between variables, across time, and between spatial locations, to detect poor or invalid data with a high degree of confidence.

97 MATHEMATICS AND COMPUTING↗

Smart Meter Data: A Gateway for Reducing Solar Soft Costs with Model-Free Hosting Capacity Maps

Public-facing solar hosting capacity (HC) maps, which show the maximum amount of solar energy that can be installed at a location without adverse effects, have proven to be a key driver of solar soft cost reductions through a variety of pathways (e.g., streamlining interconnection, siting, and customer acquisition processes). However, current methods for generating HC maps require detailed grid models and time-consuming simulations that limit both their accuracy and scalability—today, only a handful out of almost 2,000 utilities provide these maps. This project developed and validated data-driven algorithms for calculating solar HC using data from AMI without the need of detailed grid models or simulations. The algorithms were validated on utility datasets and incorporated as an application into NRECA’s Open Modeling Framework (OMF.coop) for the over 260 coops and vendors throughout the US to use. The OMF is free and open-source for everyone.

14 SOLAR ENERGY↗

Novel Analysis and Visualization of Chemical Events for Public Health Surveillance

Pacific Northwest National Laboratory hosted an intern-based web application development contest in the summer of 2016 centered around developing novel chemical surveillance applications to aid in health situational awareness. Making up the three teams were three graduate students (n=9) from various US schools majoring in non-public health domains, such as computer science and user design. The interns successfully developed three applications that demonstrated a value-add to chemical surveillance—ChemAnalyzer (text analytics), RetroSpect (retrospective analysis of chemical events),and ToxicBusters (geo-based trend analytics). These applications will be the basis for the first chemical surveillance application to be incorporated into the DTRA Biosurveillance Ecosystem (BSVE).Pacific Northwest National Laboratory (PNNL), on behalf the Defense Threat Reduction Agency (DTRA; project number CB10190), hosts an annual intern- based web app development contest. Previous competitions have focused on mobile biosurveillance. The 2016 competition pivoted away from biosurveillance to focus on addressing challenges within the field of chemical surveillance and increasing public health chemical situational awareness. The result of the app will be integrated within the DTRA BSVE. PNNL hosted nine graduate interns for a 10-week period in the summer of 2016 as participants in a summer web application development contest. Students were drawn from such fields as software engineering and user experience and design and placed into three teams of three students. The challenge presented to the interns was to design and develop a fully-functional web application that would address a critical need within the chemical surveillance community. The interns developed their own ideas (vetted by PNNL and DTRA), discovered and integrated their own data sources, and produced their own visualizations and analytics, independent of any assistance outside of that provided in an advisory capacity. The competition end with a judging event with a panel of subject matter experts and cash awards were distributed to the teams. Each team produced a unique application. Although there was mild overlap between some of the ideas, the applications were developed independently and each reflected the unique contributions of the teams. ChemAnalyzer is a text-analytics platform designed to facilitate more data-driven decision, given a corpus of text data about a chemical event. Their platform provided the ability to automatically identify and highlight key words in documents related to chemical events. The keywords are drawn from an ontology installed with the system, as well as any user-identified keywords. The ChemAnalyzer team finished in third place. The RetroSpect team developed a visual analytic tool for performing retrospective analysis and monitoring of chemical events. Their app provided the ability to search and analyze past events, as well as visualization of state and county information for the recorded chemical events. The RetroSpect team finished in second place. The Toxic busters team - the winners of the competition - created a geo-based situational awareness tool for tracking chemical events. Their app featured an updateable map overlay, search functionality for finding specific or related events, incident and city/state/national-level statistics and trends, as well as news and social media integration based on keywords related to chemical surveillance. Each of the apps developed by the teams provides value to an analyst tasked with monitoring chemical events. The apps integrated unique data sources to provides a full picture of a chemical event, and its effects upon the surrounding population. This integrated analytics provides a valuable benefit over existing workflows, where analysts must monitor news, social, and other information sources manually for real-time information. The apps developed by these interns are designed to enable identification and analysis of the incident as quickly as possible, allowing for more timely assessments of the incident and its impacts. The web app development contest provided a unique opportunity for students to learn about the emerging needs in chemical surveillance as it relates to health situational awareness. Students were drawn from a variety of fields and were tasked with developing novel web apps addressing some of the most pressing challenges in the field of chemical surveillance. The ideas generated by the students will help form the basis for future chemical surveillance application development to be integrated with the DTRABSVE.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Online Event Detection in Synchrophasor Data with Graph Signal Processing

Online detection of anomalies is crucial to enhancing the reliability and resiliency of power systems. We propose a novel data-driven online event detection algorithm with synchrophasor data using graph signal processing. In addition to being extremely scalable, our proposed algorithm can accurately capture and leverage the spatio-temporal correlations of the streaming PMU data. This paper also develops a general technique to decouple spatial and temporal correlations in multiple time series. Finally, we develop a unique framework to construct a weighted adjacency matrix and graph Laplacian for product graph. Case studies with real-world, large-scale synchrophasor data demonstrate the scalability and accuracy of our proposed event detection algorithm. Compared to the state-of-the-art benchmark, the proposed method not only achieves higher detection accuracy but also yields higher computational efficiency.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Data Curation for Machine Learning Applied to Geothermal Power Plant Operational Data for GOOML: Geothermal Operational Optimization with Machine Learning: Preprint

Geothermal Operational Optimization with Machine Learning (GOOML) is a transferable and extensible component-based geothermal asset modeling framework that considers complex steamfield relationships and identifies optimization prospects using a data-driven approach to physics-guided, data-centric machine learning. This framework has been used to develop digital twins that provide steamfield operators with operational environments to analyze and understand historical and forecasted power production, explore new steamfield configuration possibilities, and seek optimal asset management in real world applications. To create, test, and apply the GOOML framework, diverse time-series datasets spanning multiple years were sourced from various geothermal power plant components within several complex real-world geothermal operations. These operations are based in the United States and New Zealand and include a variety of technologies, end-uses and configurations, collectively covering nearly all relevant operating conditions for modern geothermal fields. Datasets were acquired from multiple sources to ensure that machine learning experiments generalized properly to various operating conditions. It was found that the data varied in quality, format, and completeness. To ensure consistency between the various datasets, a standardized data curation process was developed to reliably streamline data preparation. This paper will discuss best practices as learned from the GOOML data curation process which takes the following steps: 1) acquisition of large quantities of data from power plant operators, 2) digestion of data to gain an initial understanding of what is included, 3) data transformation, which includes converting the data into a standardized machine-readable format so that they can be visualized, quality checked, and cleaned, 4) quality assurance and quality control, involving identification of significant data gaps and apparent anomalies through mapping of data features to real world componentry via the GOOML historical model, followed by discussion with modelers and power plant operators to identify additional data needs and to resolve issues, 5) use in machine learning algorithms, and 6) repetition of steps one through five until all data needs are met and data are deemed suitable for producing trustworthy modeling results which may be disseminated, ideally along with the curated dataset. This iterative process is focused on improving the quality of the data rather than tuning machine learning model parameters and supports a shift towards data-centric AI as a means to improving real-world applicability of geothermal machine learning projects.

access↗

Projection pursuit adaptation on polynomial chaos expansions

Here, the present work addresses the issue of accurate stochastic approximations in high-dimensional parametric space using tools from uncertainty quantification (UQ). The basis adaptation method and its accelerated algorithm in polynomial chaos expansions (PCE) were recently proposed to construct low-dimensional approximations adapted to specific quantities of interest (QoI). The present paper addresses one difficulty with these adaptations, namely their reliance on quadrature point sampling, which limits the reusability of potentially expensive samples. Projection pursuit (PP) is a statistical tool to find the “interesting” projections in high-dimensional data and thus bypass the curse-of-dimensionality. In the present work, we combine the fundamental ideas of basis adaptation and projection pursuit regression (PPR) to propose a novel method to simultaneously learn the optimal low-dimensional spaces and PCE representation from given data. While this projection pursuit adaptation (PPA) can be entirely data-driven, the constructed approximation exhibits mean-square convergence to the solution of an underlying governing equation and thus captures the supports and probability distributions associated with the physics constraints. The proposed approach is demonstrated on a borehole problem and a structural dynamics problem, demonstrating the versatility of the method and its ability to discover low-dimensional manifolds with high accuracy with limited data. In addition, the method can learn surrogate models for different quantities of interest while reusing the same data set.

97 MATHEMATICS AND COMPUTING↗