SEARCH · Engineering Papers
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.
Explore the source record for details and available documents.
We explore the trade-offs of performing linear algebra using Apache Spark, compared to traditional C and MPI implementations on HPC platforms. Spark is designed for data analytics on cluster computing platforms with access to local disks and is optimized for data-parallel tasks. We examine three widely-used and important matrix factorizations: NMF (for physical plausibility), PCA (for its ubiquity) and CX (for data interpretability). We apply these methods to 1.6TB particle physics, 2.2TB and 16TB climate modeling and 1.1TB bioimaging data. The data matrices are tall-and-skinny which enable the algorithms to map conveniently into Spark’s data parallel model. We perform scaling experiments on up to 1600 Cray XC40 nodes, describe the sources of slowdowns, and provide tuning guidance to obtain high performance.
With the growth of intermodal freight transportation, it is important that transportation planners and decision-makers are knowledgeable about freight flow data to make informed decisions. This is particularly true with Intelligent Transportation Systems (ITS) offering new capabilities for intermodal freight transportation. Specifically, ITS enables access to multiple different data sources, but they have different formats, resolutions, and time scales. Thus, knowledge of data science is essential to be successful in future ITS-enabled intermodal freight transportation systems. This chapter discusses the commonly used descriptive and predictive data analytic techniques in intermodal freight transportation applications. These techniques cover the entire spectrum of univariate, bivariate, and multivariate analyses. In addition to illustrating how to apply these techniques manually, this chapter will also show how to apply them using the statistical software R. Additional exercises are provided for those who wish to apply the described techniques to more complex problems.
Abstract—With growing dataset sizes, and as computing cycles are increasing faster than storage and wide-area bandwidths, compression appears like a promising approach for improving the performance of large-scale data analytics applications. In this context, this paper makes the following contributions. First, we develop a new compression methodology, which exploits the similarities between spatial and/or temporal neighbors in a simulation dataset, and enables high compression ratios and low decompression costs. Second, we have developed a framework that can be used to incorporate a variety of compression and decompression algorithms. This framework also supports a simple API to allow integration with an existing application or data processing middleware. Once a compression algorithm is implemented, this framework can allow multi-threaded retrieval, multi-threaded data decompression, and use of informed prefetching and caching. By integrating this framework with a data-intensive middleware, we have applied our compression methodology and framework to three applications over two datasets, including a GCRM climate model dataset. We obtained an average compression ratio of 51.68%, and up to 53.27% improvement in execution time of data analysis applications.
Conventional approaches for modeling human mobility pattern often focus on human activity and movement dynamics in their regular daily lives and cannot capture changes in human movement dynamics in response to large-scale events. With the rapid advancement of information and communication technologies, many researchers have adopted alternative data sources (e.g., cell phone records, GPS trajectory data) from private data vendors to study human movement dynamics in response to large-scale natural or societal events. Big geosocial data such as georeferenced tweets are publicly available and dynamically evolving as real-world events are happening, making it more likely to capture the real-time sentiments and responses of populations. However, precisely-geolocated geosocial data is scarce and biased toward urban population centers. In this research, we developed a big geosocial data analytical framework for extracting human movement dynamics in response to large-scale events from publicly available georeferenced tweets. The framework includes a two-stage data collection module that collects data in a more targeted fashion in order to mitigate the data scarcity issue of georeferenced tweets; in addition, a variable bandwidth kernel density estimation(VB-KDE) approach was adopted to fuse georeference information at different spatial scales, further augmenting the signals of human movement dynamics contained in georeferenced tweets. To correct for the sampling bias of georeferenced tweets, we adjusted the number of tweets for different spatial units (e.g., county, state) by population. To demonstrate the performance of the proposed analytic framework, we chose an astronomical event that occurred nationwide across the United States, i.e., the 2017 Great American Eclipse, as an example event and studied the human movement dynamics in response to this event. Finally, this analytic framework can easily be applied to other types of large-scale events such as hurricanes or earthquakes.
Predicting gas production from stimulated unconventional reservoirs has always been a challenge to oil and gas companies because the physics of fluid flow through such reservoirs is not well understood. On the other hand, modeling gas production from shale reservoirs is a complex multi-variate problem that requires proper integration of data from multiple disciplines, such as geology, petrophysics, geomechanics, completions, and surface-based measurements, etc. Here this study demonstrates the application of data-driven machine learning algorithms, integrating geoscientific, distributed acoustic sensing (DAS), distributed temperature sensing (DTS) fiber-optic, completions, flow scanner production log, and surface data to model daily gas production from a 28-stage stimulated horizontal well drilled in the Marcellus Shale of the Appalachian basin in North America. In addition, this study aims to utilize the data from a fiber-optic monitoring system, such as DAS and DTS to evaluate the well performance. We build supervised data-driven machine learning models using Random Forest (RF), Artificial Neural Network (ANN), and Support Vector Machine (SVM) algorithms to understand the well performance and forecast the daily gas production. The study compares the forecasted results, tests the level of accuracy, and addresses different issues with these machine learning algorithms. A spatio-temporal database is constructed and used to perform sensitivity analyses to identify the key drivers for gas production. The results show that RF and ANN algorithms can be used to predict daily gas production with significantly high accuracy; however, RF algorithm is the best predictor in terms of highest accuracy (96%), less computational time and cost. Based on sensitivity analysis, it appears that Poisson's ratio, minimum horizontal stress, DAS, casing pressure, gamma log are the most important parameters to predict gas production.
For decades, boiler leaks have been the leading cause of forced outages in the coal-fired unit. The leak occurrences are currently escalating since the existing plants must satisfy faster-ramping rates to support grid operation. Data analytics including Principal Component Analysis, Canonical Variate, and Fisher Discriminant Analysis were combined for detecting and characterizing the leak in a commercial 650 MW subcritical coal-fired power plant. The combined approach was shown to be highly effective in the fault investigation that would not have been easily achieved by an individual technique. The variability in both training and validation datasets was first evaluated using PCA. Then, the CV-FDA was employed to discriminate among faults, and to categorize the processed data into two main groups: no-leak (0) and leak (1), providing the timeframe and location of the leak occurrence. Furthermore, about 8,014 observations from 81 process variables were initially included in the calculation, while the variable count was reduced to 4 with less than 1% misclassification rate in total observations. Finally, the leak was isolated in the waterwall section. Thus, the outcome of this research may provide early detection and isolation of faulty operations in the coal-fired power plant that involves a considerable number of process variables.
Abstract Although of practical importance, there is no established modeling framework to accurately predict high-temperature cyclic oxidation kinetics of multi-component alloys due to the inherent complexity. We present a data analytics approach to predict the oxidation rate constant of NiCr-based alloys as a function of composition and temperature with a highly consistent and well-curated experimental dataset. Two characteristic oxidation models, i.e., a simple parabolic law and a statistical cyclic oxidation model, have been chosen to numerically represent the high-temperature oxidation kinetics of commercial and model NiCr-based alloys. We have successfully trained machine learning (ML) models using highly ranked key input features identified by correlation analysis to accurately predict experimental parabolic rate constants ( k p ). This study demonstrates the potential of ML approaches to predict oxidation kinetics of alloys over wide composition and temperature ranges. This approach can also serve as a basis for introducing more physically meaningful ML input features to predict the comprehensive cyclic oxidation behavior of multi-component high-temperature alloys with proper constraints based on the known underlying mechanisms.
Over the past decade, electric utilities have made significant progress in deploying networks of phasor measurement units (PMUs). The high-speed measurements provided by PMUs are valuable for offline analysis, but the sheer volume of data presents a challenge for utilities. The Accelerated Data Analytics for Power-System Time-Series (ADAPT) project was created to address this challenge by developing SciSync, an open-source software tool that enables utilities to rapidly read, process, analyze, and review grid measurements. SciSync was designed to provide the capabilities of Archive Walker, a research tool developed by PNNL, along with the reliability and performance of commercial-grade software.
Not Available
Machine learning (ML) can offer many advantages in predicting material properties over traditional materials development methods based solely on limited experimental investigations or physical-based simulations with the capability to reduce development cost, risk, and time. However, so far, limited efforts have been made to predict alloy oxidation kinetics and spallation behavior via ML due to the lack of consistently measured and sufficient experimental data and the inherent complexity in oxidation behavior of multicomponent high-temperature alloys. A previous study reported the ability of ML to predict oxidation kinetics of NiCr-based alloys as a function of alloy composition and operating conditions. Here, the performance of a ML model in predicting rate constants and spallation probability was evaluated in light of the roles of the data distribution of the experimental dataset (data analytics), the alloy composition, the exposure environment and the chosen oxidation approach to extracting kinetic values from the measured mass changes (but using either a simple parabolic law or a statistical cyclic oxidation model). Potential strategies to improve the predictions and enhance the extrapolative capability of the previously trained model will be discussed.
Ice-based thermal energy storage (TES) systems can shift peak cooling demand and reduce operational energy costs (with time-of-use rates) in commercial buildings. The accurate prediction of the cooling load, and the optimal control strategy for managing the charging and discharging of a TES system, are two critical elements to improving system performance and achieving energy cost savings. This study utilizes data-driven analytics and modeling to holistically understand the operation of an ice–based TES system in a shopping mall, calculating the system’s performance using actual measured data from installed meters and sensors. Results show that there is significant savings potential when the current operating strategy is improved by appropriately scheduling the operation of each piece of equipment of the TES system, as well as by determining the amount of charging and discharging for each day. A novel optimal control strategy, determined by an optimization algorithm of Sequential Quadratic Programming, was developed to minimize the TES system’s operating costs. Three heuristic strategies were also investigated for comparison with our proposed strategy, and the results demonstrate the superiority of our method to the heuristic strategies in terms of total energy cost savings. Specifically, the optimal strategy yields energy costs of up to 11.3% per day and 9.3% per month compared with current operational strategies. A one-day-ahead hourly load prediction was also developed using machine learning algorithms, which facilitates the adoption of the developed data analytics and optimization of the control strategy in a real TES system operation.
Laser-wire based Directed Energy Deposition (DED) processes are being developed at Oak Ridge National Laboratory’s Manufacturing Demonstration Facility, in collaboration with GKN Aerospace, for large volume metal additive manufacturing of metallic structures. The technology has the potential to deliver reduced costs and lead times when compared to conventional methods of manufacturing in several industries. While complex structures are being produced with relatively high deposition rates and at near-net shape, issues persist with achieving consistent geometric accuracy and thermal stability. A significant research effort is focused on developing coordinated, multi-modal sensing and control for addressing these issues. An introduction to this large-volume metal process will be provided, followed by investigations into real-time thermal monitoring capabilities that support control and data analytics frameworks. Studies focused on melt pool monitoring via infrared thermography, thermal and geometric effects on melt pool size measurement, and interactions between process variables and thermal monitoring metrics are presented.
The U.S Department of Energy Light Water Reactor Sustainability (LWRS) Program initiated research in to what is needed in order to provide a roadmap or model for Nuclear Power Plants to reference when building an architecture that can support the growing data supply and demand flowing through their networks. The Digital Architecture project published report Digital Architecture Planning Model (Oxstrand et. al, 2016) discusses things to consider when building an architecture to support the increasing needs and demands of data throughout the plant. Once the plant is able to support the data demands it still needs to be able to provide the data in an easy, quick and reliable method. A common method is to create a “one stop shop” application that a user can go to get all the data they need. The creation of this leads to the need of creating a Seamless Digital Environment (SDE) to integrate all the “siloed” data. An SDE is the desired perception that should be presented to users by gathering the data from any data source (e.g., legacy applications and work management systems) without effort by the user. The goal for FY16 was to complete a feasibility study for data mining and analytics for employing information from computer-based procedures enabled technologies for use in developing improved business analytics. The research team collaborated with multiple organizations to identify use cases or scenarios, which could be beneficial to investigate in a feasibility study. Many interesting potential use cases were identified throughout the FY16 activity. Unfortunately, due to factors out of the research team’s control, none of the studies were initiated this year. However, the insights gained and the relationships built with both PVNGS and NextAxiom will be valuable when moving forward with future research. During the 2016 annual Nuclear Information Technology Strategic Leadership (NITSL) group meeting it was identified would be very beneficial to the industry to support a research effort focused on data analytics. It was suggested that the effort would develop and evaluate use cases for data mining and analytics for employing information from plant sensors and database for use in developing improved business analytics.
Voluminous process data are available with the paradigm shift toward smart manufacturing. However, most historical data are observational, containing noncausal correlations due to confounders and mediators. Estimating causal effects from observational data remains a bottleneck in leveraging them for active applications such as optimization and control. Further, this work aims to introduce a causal modeling framework for analyzing observational process data and extracting quantitative causal information. We demonstrate a real-world application in steel manufacturing where causal inference is used to analyze observational production data and improve the steelmaking process. Additionally, we propose a novel formulation for identifying critical process parameters from observational data, where causal inference is combined with variance-based methods to estimate corresponding risks of interventions to the manufacturing system. The proposed methods are compared with statistical ones to illustrate that causally interpreting statistical correlation leads to problematic results, while the provided workflow generates satisfactory strategies for process improvement.
The National Nuclear Security Administration’s Office of Nuclear Smuggling Detection and Deterrence has deployed a fleet of radiation portal monitors (RPMs) across the world at global ports of entry including seaports, airports, and land border crossings. These RPMs are integrated into radiation detection systems (RDS) that also include fixed cameras, optical character recognition (OCR) systems, primary scanning systems (e.g., X-ray or gamma-ray), and secondary scanning systems (e.g., spectroscopic radiation portal monitors, portable radiation detection systems). The data from these sensing technologies is collected at the Central Alarm Station (CAS) where servers and computers reside to control and operate the system. Operators utilize the data collected by the CAS and declared cargo information to make decisions on how to respond to an alarm.This work explores the use of CAS-located data, looking at both the sensor data streams and operator inputs, to perform analysis which supports customs and border protection agencies to improve training capability and operational effectiveness. We focus on analyzing site level effectiveness and behavior by rolling up CAS-located data collected from individual occurrences. To-date, more than 15 sites (e.g., seaports, airports, border crossings) have been analyzed in this manner with the goal of understanding system operations to verify effectiveness and recommend potential improvements. This work first aims to provide background information on relevant CAS-located data sources and our current operational system analytics process including example results. After summarizing our current analytic techniques, we discuss how the future data analytics systems can provide key benefits to improving operational performance while minimizing the burden these detection systems place on operators.
Scaling-up scientific data analysis and machine learning algorithms for data-driven discovery is a grand challenge that we face today. Despite the growing need for analysis from science domains that are generating `Big Data' from instruments and simulations, building high-performance analytical workflows of data-intensive algorithms have been daunting because: (i) the `Big Data' hardware and software architecture landscape is constantly evolving, (ii) newer architectures impose new programming models, and (iii) data-parallel kernels of analysis algorithms and their performance facets on different architectures are poorly understood. To address these problems, we have: (i) identified scalable data-parallel kernels of popular data analysis algorithms, (ii) implemented `Mini-Apps' of those kernels using different programming models (e.g. Map Reduce, MPI, etc.), (iii) benchmarked and validated the performance of the kernels in diverse architectures. In this paper, we discuss two of those Mini-Apps and show the execution of principal component analysis built as a workflow of the Mini-Apps. We show that Mini-Apps enable scientists to (i) write domain-specific data analysis code that scales on most HPC hardware and (ii) and offers the ability (most times with over a 10x speed-up) to analyze data sizes 100 times the size of what off-the-shelf desktop/workstations of today can handle.
There are numerous applications that combine data collected from sensors with machine-learning based classification models to predict the type of event or objects observed. Both the collection of the data itself and the classification models can be tuned for optimal performance, but we hypothesize that additional gains can be realized by jointly assessing both factors together. Through this research, we used a seismic event dataset and two neural network classification models that issued probabilistic predictions on each event to determine whether it was an earthquake or a quarry blast. Real world applications will have constraints on data collection, perhaps in terms of a budget for the number of sensors or on where, when, or how data can be collected. We mimicked such constraints by creating subnetworks of sensors with both size and locational constraints. We compare different methods of determining the set of sensors in each subnetwork in terms of their predictive accuracy and the number of events that they observe overall. Additionally, we take the classifiers into account, treating them both as black-box models and testing out various ways of combining predictions among models and among the set of sensors that observe any given event. We find that comparable overall performance can be seen with less than half the number of sensors in the full network. Additionally, a voting scheme that uses the average confidence across the sensors for a given event shows improved predictive accuracy across nearly all subnetworks. Lastly, locational constraints matter, but sometimes in unintuitive ways, as better-performing sensors may be chosen instead of the ones excluded based on location. This being a short-term research effort, we offer a lengthy discussion on interesting next-steps and ties to other ongoing research efforts that we did not have time to pursue. These include a detailed analysis of the subnetwork performance broken down by event type, specific location, and model confidence. This project also included a Campus Executive research partnership with Texas A&M University. Through this, we worked with a professor and student to study information gain for UAV routing. This was an alternative way of looking at the similar problem space that includes sensor operation for data collection and the resulting benefit to be gained from it. This work is described in an Appendix.