Search NASA⌕ Search

SEARCH · Search NASA

Results for “Big data processing”

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 73 records · Page 4
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

In-depth analysis on parallel processing patterns for high-performance Dataframes

The Data Science domain has expanded monumentally in both research and industry communities during the past decade, predominantly owing to the Big Data revolution. Artificial Intelligence (AI) and Machine Learning (ML) are bringing more complexities to data engineering applications, which are now integrated into data processing pipelines to process terabytes of data. Typically, a significant amount of time is spent on data preprocessing in these pipelines, and hence improving its efficiency directly impacts the overall pipeline performance. The community has recently embraced the concept of Dataframes as the de-facto data structure for data representation and manipulation. However, the most widely used serial Dataframes today (R, pandas) experience performance limitations while working on even moderately large data sets. We believe that there is plenty of room for improvement by taking a look at this problem from a high-performance computing point of view. In a prior publication, we presented a set of parallel processing patterns for distributed dataframe operators and the reference runtime implementation, Cylon. In this paper, we are expanding on the initial concept by introducing a cost model for evaluating the said patterns. Furthermore, we evaluate the performance of Cylon on the ORNL Summit supercomputer.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Rahasak—Scalable blockchain architecture for enterprise applications

Blockchain-based decentralized infrastructure has been adapted in various industries to handle the sensitive data in a privacy-preserving manner without trusting third parties. However, integrating state-of-the-art blockchain platforms with the scalable, enterprise-level applications result in several challenges. Current blockchain platforms do not support high transaction throughput, lack high scalability, and cannot provide real-time transaction processing and back-pressure operation handling in high transaction throughput applications(e.g Big data, IoT). In this paper, we propose a novel permissioned blockchain platform “Rahasak” for highly scalable, enterprise applications. Rahasak blockchain adopts the Apache Kafka-based consensus on top of a “Validate-Execute-Group” blockchain architecture to handle realtime transaction execution on the blockchain. The architecture is equipped with a functional programming and actor-based smart contract platform that enables concurrent execution of transactions in the blockchain. Rahasak supports high transaction throughput, high scalability, concurrent transaction execution, data analytics features. Finally, with Rahasak, we make blockchain more scalable, secure, structured and meaningful for further data analytics.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

GeoThermalCloud framework for fusion of big data and multi-physics models in Nevada and Southwest New Mexico

Our GeoThermalCloud framework is designed to process geothermal datasets using a novel toolbox for unsupervised and physics-informed machine learning called SmartTensors. More information about GeoThermalCloud can be found at the GeoThermalCloud GitHub Repository. More information about SmartTensors can be found at the SmartTensors Github Repository and the SmartTensors page at LANL.gov. Links to these pages are included in this submission. GeoThermalCloud.jl is a repository containing all the data and codes required to demonstrate applications of machine learning methods for geothermal exploration. GeoThermalCloud.jl includes: - site data - simulation scripts - jupyter notebooks - intermediate results - code outputs - summary figures - readme markdown files GeoThermalCloud.jl showcases the machine learning analyses performed for the following geothermal sites: - Brady: geothermal exploration of the Brady geothermal site, Nevada - SWNM: geothermal exploration of the Southwest New Mexico (SWNM) region - GreatBasin: geothermal exploration of the Great Basin region, Nevada Reports, research papers, and presentations summarizing these machine learning analyses are also available and will be posted soon.

15 GEOTHERMAL ENERGY↗
DOE OSTI2023

Water narratives in local newspapers within the United States

Sustainable use of water resources continues to be a challenge across the globe. This is in part due to the complex set of physical and social behaviors that interact to influence water management from local to global scales. Analyses of water resources have been conducted using a variety of techniques, including qualitative evaluations of media narratives. This study aims to augment these methods by leveraging computational and quantitative techniques from the social sciences focused on text analyses. Specifically, we use natural language processing methods to investigate a large corpus (approx. 1.8M) of newspaper articles spanning approximately 35 years (1982–2017) for insights into human-nature interactions with water. Focusing on local and regional United States publications, our analysis demonstrates important dynamics in water-related dialogue about drinking water and pollution to other critical infrastructures, such as energy, across different parts of the country. Our assessment, which looks at water as a system, also highlights key actors and sentiments surrounding water. Extending these analytical methods could help us further improve our understanding of the complex roles of water in current society that should be considered in emerging activities to mitigate and respond to resource conflicts and climate change.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

SEAFORML (Smart Exploration and Analysis For Optimal and Robust Machine Learning)

The poster discusses data analysis of the WAVgraph database and applied machine learning methods for it. The database is a long-term project that seeks to be a comprehensive repository of information on cyber threats and is updated regularly. It was previously unanalyzed and unexplored. The goal was to learn more about it and its contents in order to have a better understanding and enable better use. The data analysis and discovery enabled further exploration through natural language processing, similarity, and clustering methods. The poster shows some of the insights from the analysis and explains the methods used for the machine learning applications.

24 - POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2018

Machine Learning Algorithms for Matching Theories, Simulations, and Observations in Cosmology (Final Project)

The search for simple and elegant equations to explain and predict observable natural phenomena has been a driving force in scientific theory for several centuries. The great successes of Newton's laws, Maxwell's equations, the Schrodinger equation, and the theory of General Relativity have encouraged this perspective, and perhaps a beautiful equation comprising a “theory of everything” remains to be discovered. But now scientists are grappling with systems of ever-increasing complexity, fraught with nonlinearity, and with the quantities of interest often only indirectly observed. Nature may resist a simple description, and the most important discoveries of the next century may be complex theories with countless variables and parameters. The era of big data opens up a promising new approach to scientific discovery in this setting. The predictions of modern theories, even if complex or nonlinear, can be examined through detailed and computationally-intensive simulations that take days or weeks to run and fill petabytes of disk space. The upcoming generation of scientific instruments will provide petabytes of observations at unprecedented resolution and depth. The challenge is to compare data to simulations so as to test theories and identify those that best match the observations. The data are numerous and rich but are subject to noise and various systematic biases. The simulations are large and detailed but are so costly that the effective sample size is small. Moreover, the mapping from data to simulation to the parameters of interest is typically complicated and ill-conditioned. Although these challenges, and the solutions we propose, apply across the sciences, we will ground our efforts by focusing on cosmology. Here, we are truly entering the era of big data in several senses. Ever larger experiments survey larger and larger cosmological volumes, resulting in enormous amounts of pixel data to process and extract the information of cosmological interest. These include large imaging surveys, which collect all the light in broad wavelength ranges over significant fractions of the sky, and spectroscopic surveys, which measure the light as a function of wavelength to map out 3D distances. These experiments are designed to shed light on the big unanswered questions in cosmology. Distilling the petabytes of data into observed quantities for comparison with theory is a daunting task. But these large experiments do not only result in large amounts of data to analyze: if we wish to compare to theories of physics, then we need increasingly extensive predictions for the observed quantities as well, which requires ever-larger cosmological simulations that take substantial -- and at times prohibitive -- computational resources to produce. Our goal is to develop statistical and machine learning methods for using observed and simulated data to advance machine learning with applications cosmology. In particular, we focus our research efforts on the following tasks: The challenge for automated science is that it is computationally impossible and statistically dangerous to consider every possible model in order to find the best one. We will develop Bayesian Optimization based active-learning methods that accelerate both the execution of the simulations and the search for best-fitting parameters. The key idea is to make the simulations adaptive -- across resolutions, time, and parameters -- using the data to search as the simulation runs; Most ML methods operate on simple finite dimensional feature vectors. However, many cosmology and other science applications require ML methods that can operate on more complex objects as inputs or outputs such as functions, distributions, or sets and point clouds. Our goal is to develop efficient ML methods for this problem and demonstrate their applicability in Cosmology, Astrophysics, and other science problems.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2019

Building complex event processing capability for intelligent environmental monitoring

Rapid evolution of Internet-of-Things is driving the increased deployment of smart sensors in environmental applications, contributing to many big data characteristics of environmental monitoring. Most of the current environmental monitoring systems are not designed to handle real-time datastreams, and the best practices for datastream processing and predictive analytics are yet to be established. This work presents a complex event processing (CEP) engine for detecting anomalies in real time, and demonstrates it using a series of real monitoring data from the geological carbon sequestration domain. We show that the service-based CEP engine is instrumental for enabling environmental intelligent monitoring systems to ingest heterogeneous datastreams with scalable performance. Our CEP framework requires minimal coding from the user and can be easily extended to other similar environmental monitoring applications.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Analytics-at-scale of Sensor Data for Digital Monitoring in Nuclear Plants (3 rd Annual Report)

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This report primarily focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 ± 0.014, 0.0026 ± 0, and 0.063 ± 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure. This report summarizes the Fiscal Year 2021 research progress encompassing the (1) data cleaning and feature selection necessary for ML applications; (2) development of short-term forecasting models to predict future plant process parameters for both single and multiple time steps ahead; and (3) validation of the feature selection methods and short-term forecasting models given new data from different systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

Development of Short-Term Forecasting Models Using Plant Asset Data and Feature Selection

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This paper focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 +- 0.014, 0.0026 +- 0, and 0.063 +- 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Predictive Data-driven Platform for Subsurface Energy Production

Subsurface energy activities such as unconventional resource recovery, enhanced geothermal energy systems, and geologic carbon storage require fast and reliable methods to account for complex, multiphysical processes in heterogeneous fractured and porous media. Although reservoir simulation is considered the industry standard for simulating these subsurface systems with injection and/or extraction operations, reservoir simulation requires spatio-temporal “Big Data” into the simulation model, which is typically a major challenge during model development and computational phase. In this work, we developed and applied various deep neural network-based approaches to (1) process multiscale image segmentation, (2) generate ensemble members of drainage networks, flow channels, and porous media using deep convolutional generative adversarial network, (3) construct multiple hybrid neural networks such as convolutional LSTM and convolutional neural network-LSTM to develop fast and accurate reduced order models for shale gas extraction, and (4) physics-informed neural network and deep Q-learning for flow and energy production. We hypothesized that physicsbased machine learning/deep learning can overcome the shortcomings of traditional machine learning methods where data-driven models have faltered beyond the data and physical conditions used for training and validation. We improved and developed novel approaches to demonstrate that physics-based ML can allow us to incorporate physical constraints (e.g., scientific domain knowledge) into ML framework. Outcomes of this project will be readily applicable for many energy and national security problems that are particularly defined by multiscale features and network systems.

58 GEOSCIENCES↗
DOE OSTI2018

Time resolved surface photovoltage measurements using a big data capture approach to KPFM

Optoelectronic behavior in materials such as organic/inorganic hybrid perovskites depend on a complex interplay between fast (electronic) and slower (ionic) processes. These processes are thought to be influenced by structural inhomogeneities (e.g. interfaces and grain boundaries) bringing forward the necessity for development of techniques capable of correlating nanostructure and photo-transport behavior. While Kelvin probe force microscopy (KPFM) is ideally suited to map surface potentials on relevant length scales, it lacks sufficient temporal resolution to extract the meaningful system dynamics. Here, we develop a time resolved surface photovoltage (SPV) measurement based on full information capture of the photodetector stream during open loop KPFM operation. G-Mode, or G-KPFM allows quantification of SPV with microsecond temporal and nanoscale spatial resolution. Using this technique, we observe concurrent spatial and fast temporal variations in the SPV generated across a methylammonium lead bromide (MAPbBr3) thin film, a possible indicator relating microstructure with heterogenous photo-transport behavior. Here, we further demonstrate the advantage of adopting big data analytics including unsupervised clustering methods to quickly discern spatial variability in the information rich SPV dataset. Beyond G-KPFM, such clustering methods will be useful for interpretation of the multidimensional datasets arising from the growing number of time resolved KPFM approaches now available.

36 MATERIALS SCIENCE↗
DOE OSTI2020

On‐site surrogates for large‐scale calibration

Abstract Motivated by a computer model calibration problem from the oil and gas industry, involving the design of a honeycomb seal, we develop a new Bayesian methodology to cope with limitations in the canonical apparatus stemming from several factors. We propose a new strategy of on‐site design and surrogate modeling for a computer simulator acting on a high‐dimensional input space that, although relatively speedy, is prone to numerical instabilities, missing data, and nonstationary dynamics. Our aim is to strike a balance between data‐faithful modeling and computational tractability in a calibration framework—tailoring the computer model to a limited field experiment. Situating our on‐site surrogates within the canonical calibration apparatus requires updates to that framework. We describe a novel yet intuitive Bayesian setup that carefully decomposes otherwise prohibitively large matrices by exploiting the sparse blockwise structure. Empirical illustrations demonstrate that this approach performs well on toy data and our motivating honeycomb example.

Huang, Jiangeng↗
DOE OSTI2021

Using machine learning and artificial intelligence to improve model-data integrated earth system model predictions of water and carbon cycle extremes

The research proposed here focuses on improving the predictive power of the land component of earth system models (ESMs) using (1) model-data fusion enabled by machine learning (ML) and artificial intelligence (AI), (2) predictive modeling through the combination of ML, AI, and big-data (comprising both model output and observations), and (3) insight of ESM structure and process mechanisms gleaned from complex data using ML and AI.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

Findings on Subtask 3.1 - Bakken Rich Gas Enhanced Oil Recovery Project

Total in-place oil for the Bakken petroleum system (BPS) (which includes the Bakken and Three Forks Formations) has been estimated to be 600 billion barrels (bbl). However, BPS wells have decline rates as high as 85% over the first 3 years of their lives, and primary recovery factors typically range from 3% to 10% of original oil in place. Given the low initial recovery rates, even small incremental productivity improvements could dramatically increase technically recoverable oil in the BPS. One potential solution is enhanced oil recovery (EOR) using gas injection, such as carbon dioxide (CO2) or hydrocarbon (HC) gases. While commonly used in conventional reservoirs, CO2 EOR in unconventional tight oil reservoirs has been limited to pilot tests. EOR using rich gas (mixture of methane, ethane, and propane) has also been employed in numerous pilots in several unconventional plays and has recently been successfully applied in the Eagle Ford play. If successful, large-scale gas-based EOR in the BPS could dramatically increase oil productivity and recovery factors and extend the life of the play for decades. While CO2 may be a technically suitable working fluid for EOR in the BPS, supplies are limited and costs for using CO2 in EOR pilots are prohibitively high. Meanwhile, produced gas flaring has presented challenges for BPS operators in North Dakota. Analysis conducted by the North Dakota Pipeline Authority indicates that the current gas-gathering infrastructure in North Dakota is insufficient to accommodate all of the associated gas that is produced from the BPS. The geographically isolated location of North Dakota relative to large natural gas markets, combined with suppressed natural gas prices, has made it economically challenging for industry to invest capital in expanding gas-gathering infrastructure in the state. These circumstances led to a research program conducted by the Energy & Environmental Research Center (EERC) in partnership with Liberty Resources Management Company LLC (LR) to examine the potential to use rich gas injection for EOR and mitigate flaring. A rich gas EOR pilot test was designed and executed by LR at its Stomping Horse development area in Williams County, North Dakota. From July 2018 through May 2019, a total of 160 million standard cubic feet (MMscf) of rich produced gas was injected into the BPS using five different wells in a sequential injection strategy. LR’s Leon–Gohrick drill spacing unit (DSU) was used as the test site. Regulatory oversight was provided by the North Dakota Industrial Commission (NDIC). Technical support was provided by the EERC through a series of laboratory, modeling, and field-based activities, and additional post-pilot research activities incorporated learnings from the test, developed new laboratory data, improved fracture modeling methods, and developed machine learning and big data analytics. The results from the Stomping Horse rich gas EOR pilot activities indicate that developing an effective, economical EOR approach for the BPS will require more field tests. Another key lesson learned from the Stomping Horse tests is that detailed pre- and posttest data on reservoir conditions and fluids production are essential. Robust reservoir characterization provides information that is crucial to creating realistic geomodels and conducting valid dynamic simulations of potential EOR scenarios. A detailed understanding of the completions and production history of offset wells is also necessary for valid test result interpretations. This knowledge is essential to designing the operational parameters of injectivity tests and interpreting the results. A conformance control strategy is also essential to success. Laboratory-based examinations of rich gas interactions with reservoir fluids and rocks were conducted, with an emphasis on determining the ability to mobilize oil in the tight reservoir rocks and shales of the BPS. Injection fluid composition was shown to have a positive impact on reducing reservoir oil minimum miscibility pressure (MMP), reducing interfacial tension (IFT), and altering wettability. IFT and contact angle measurements demonstrated that wettability can be altered in the presence of rich gas, suggesting the potential to improve oil recovery. Iterative modeling of surface infrastructure and reservoir performance using data generated by the various project activities was conducted. A geologic model of the Stomping Horse area was built; history-matched oil, gas, and water production was used in simulations of various EOR scenarios. Early programmatic modeling results were used to support LR’s design and operation of the EOR pilot and to provide insight regarding optimization of future commercial-scale BPS EOR design and operations. Post-pilot modeling focused on alternative methods of understanding complex fracture networks and accelerating simulation time. These led to improved simulation run times and provide excellent history-matching results. Several of these iterative models were used as the bases for developing algorithms into machine learning and big data analytics. History matching in reservoir simulation is time-consuming and computer processing-intensive. Machine learning algorithms were created, and an automated history-matching tool was developed. A large set of synthetic reservoir simulations were created to generate well responses (oil, gas, and water production, well bottomhole pressure [BHP], and tracer or propane breakthrough) for a set of EOR operating parameters that included offset well status (open or closed), injectate (rich gas or propane), injection rate, and injection well BHP. A user interface was developed to provide real-time visualization. Machine learning-based models were developed to provide rapid forecasting of well performance given a set of user-defined EOR operating parameters. These predictive models allow the user to modify the offset well status, injection rate, and injection well BHP and rapidly forecast future production performance. The combination of real-time visualization tools with real-time forecasting tools provides a framework for real-time control—operational changes that the EOR site operator can enact (e.g., changing gas injection rates) to affect the observed performance and potentially improve the EOR outcome. There is great reason to be optimistic about the future of EOR in the Bakken. The results of the laboratory studies suggest significant potential for high rates of oil mobilization using produced field gas injection under the right conditions. The results of the lab studies, combined with rigorous statistical analysis of well production data and associated modeling efforts, confirm the notion that fluid mobility within the reservoir is controlled by fractures. As more knowledge is gained about the nature and distribution of fracture networks in the Bakken, the industry will be in a better position to predict and, ultimately, influence fluid mobility. New field tests are necessary to develop a more complete understanding of those conditions. Thoughtful and creatively engineered field tests within a well-characterized geologic setting will yield the fundamental knowledge needed to take Bakken oil production to the next level. This subtask was cofunded through the EERC–U.S. Department of Energy Joint Program on Research and Development for Fossil Energy-Related Resources Cooperative Agreement No. DE-FE0024233. Nonfederal funding was provided by the North Dakota Industrial Commission’s Oil and Gas Research Program and Computer Modelling Group.

04 OIL SHALES AND TAR SANDS↗
DOE OSTI2022

Special Issue: Geostatistics and Machine Learning

Abstract Recent years have seen a steady growth in the number of papers that apply machine learning methods to problems in the earth sciences. Although they have different origins, machine learning and geostatistics share concepts and methods. For example, the kriging formalism can be cast in the machine learning framework of Gaussian process regression. Machine learning, with its focus on algorithms and ability to seek, identify, and exploit hidden structures in big data sets, is providing new tools for exploration and prediction in the earth sciences. Geostatistics, on the other hand, offers interpretable models of spatial (and spatiotemporal) dependence. This special issue on Geostatistics and Machine Learning aims to investigate applications of machine learning methods as well as hybrid approaches combining machine learning and geostatistics which advance our understanding and predictive ability of spatial processes.

58 GEOSCIENCES↗
DOE OSTI2021

Coordinated resource allocation to plant growth–defense tradeoffs

Summary Plant resource allocation patterns often reveal tradeoffs that favor growth (G) over defense (D), or vice versa. Ecologists most often explain G–D tradeoffs through principles of economic optimality, in which negative trait correlations are attributed to the reconciliation of fitness costs. Recently, researchers in molecular biology have developed ‘big data’ resources including multi‐omic (e.g. transcriptomic, proteomic and metabolomic) studies that describe the cellular processes controlling gene expression in model species. In this synthesis, we bridge ecological theory with discoveries in multi‐omics biology to better understand how selection has shaped the mechanisms of G–D tradeoffs. Multi‐omic studies reveal strategically coordinated patterns in resource allocation that are enabled by phytohormone crosstalk and transcriptional signal cascades. Coordinated resource allocation justifies the framework of optimality theory, while providing mechanistic insight into the feedbacks and control hubs that calibrate G–D tradeoff commitments. We use the existing literature to describe the coordinated resource allocation hypothesis (CoRAH) that accounts for balanced cellular controls during the expression of G–D tradeoffs, while sustaining stored resource pools to buffer the impacts of future stresses. The integrative mechanisms of the CoRAH unify the supply‐ and demand‐side perspectives of previous G–D tradeoff theories.

Monson, Russell K.↗
DOE OSTI2019

A Prognostics and Health Management Framework for Wind

Operation and maintenance costs are a major driver for levelized cost of energy of wind power plants and can be reduced through optimized operation and maintenance practices accomplishable by various prognostics and health management (PHM) technologies. In recent years, the wind industry has become more open to adopting PHM solutions, especially those focusing on diagnostics. However, prognostics activities are, in general, still at the research and development stage. On the other hand, the industry has a request to estimate a component's remaining useful life (RUL) when it has faulted, and this is a key output of prognostics. Systematically presenting PHM technologies to the wind industry by highlighting the RUL prediction need potentially helps speed up its acceptance and provides more benefits from PHM to the industry. In this paper, we introduce a PHM for wind framework. It highlights specifics unique to wind turbines and features integration of data and physics domain information and models. The output of the framework focuses on RUL prediction. To demonstrate its application, a data domain method for wind turbine gearbox fault diagnostics is presented. It uses supervisory control and data acquisition system time series data, normalizes gearbox temperature measurements with reference to environmental temperature and turbine power, and leverages big data analytics and machine-learning techniques to make the model scalable and the diagnostics process automatic. Another physics-domain modeling method for RUL prediction of wind turbine gearbox high-speed-stage bearings failed by axial cracks is also discussed. Bearing axial cracking has been shown to be the prevalent wind turbine gearbox failure mode experienced in the field and is different from rolling contact fatigue, which is targeted during the bearing design stage. The method uses probability of failure as a component reliability assessment and RUL prediction metric, which can be expanded to other drivetrain components or failure modes. The presented PHM for wind framework is generic and applicable to both land-based and offshore wind turbines.

17 WIND ENERGY↗
DOE OSTI2019

Ultrafast processing of pixel detector data with machine learning frameworks

Modern photon science performed at high repetition rate free-electron laser (FEL) facilities and beyond relies on 2D pixel detectors operating at increasing frequencies (towards 100 kHz at LCLS-II) and producing rapidly increasing amounts of data (towards TB/s). This data must be rapidly stored for offline analysis and summarized in real time for online feedback to the scientists. While at LCLS all raw data has been stored, at LCLS-II this would lead to a prohibitive cost; instead, enabling real time processing of pixel detector data (dark, gain, common mode, background, charge summing, subpixel position, photon counting, data summarization) allows reducing the size and cost of online processing, offline processing and storage by orders of magnitude while preserving full photon information. This could be achieved by taking advantage of the compressibility of sparse data typical for LCLS-II applications. Faced with a similar big data challenge a decade ago, computer vision stimulated revolutionary advances in machine learning hardware and software. We investigated if these developments are useful in the field of data processing for high speed pixel detectors and found that typical deep learning models and autoencoder architectures failed to yield useful noise reduction while preserving full photon information, presumably because of the very different statistics and feature sets in computer vision and radiation imaging. However, the raw performance of modern frameworks like Tensorflow inspired us to redesign in Tensorflow mathematically equivalent versions of the state-of-the-art, “classical” algorithms used at LCLS. The novel Tensorflow models resulted in elegant, compact and hardware agnostic code, gaining 1 to 2 orders of magnitude faster processing on an inexpensive consumer GPU, reducing by 3 orders of magnitude the projected cost of online analysis and compression without photon loss at LCLS-II. The novel Tensorflow models also enabled ongoing development of a pipelined hardware system expected to yield an additional 3 to 4 orders of magnitude speedup, necessary for meeting the data acquisition and storage requirements at LCLS-II, potentially enabling acquiring every single FEL pulse at full speed. Computer vision a decade ago was dominated by hand-crafted filters; their structure inspired the deep learning revolution resulting in modern deep convolutional networks; similarly, our novel Tensorflow filters provide inspiration for designing future deep learning models for ultrafast and efficient processing and classification of pixel detector images at FEL facilities.

47 OTHER INSTRUMENTATION↗