Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Predictive Data analytics”

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 37 records · Page 2

Cross-property deep transfer learning framework for enhanced predictive analytics on small materials data

Abstract Artificial intelligence (AI) and machine learning (ML) have been increasingly used in materials science to build predictive models and accelerate discovery. For selected properties, availability of large databases has also facilitated application of deep learning (DL) and transfer learning (TL). However, unavailability of large datasets for a majority of properties prohibits widespread application of DL/TL. We present a cross-property deep-transfer-learning framework that leverages models trained on large datasets to build models on small datasets of different properties. We test the proposed framework on 39 computational and two experimental datasets and find that the TL models with only elemental fractions as input outperform ML/DL models trained from scratch even when they are allowed to use physical attributes as input, for 27/39 (≈ 69%) computational and both the experimental datasets. We believe that the proposed framework can be widely useful to tackle the small data challenge in applying AI/ML in materials science.

36 MATERIALS SCIENCE↗

Predicting Execution Times for Disk-based and In-Situ Parallel Data Analytics (Final Technical Report)

In recent years, there has been a significant amount of interests in in-situ analytics on simulation programs. For a variety of reasons, it is desirable to be able to predict the execution time of an analytics program. At the same time, frameworks such as MapReduce have become popular for scientific data analytics. This paper focuses on developing performance models for predicting execution time of parallel data analytics, with a special emphasis on in-situ analytics. We take two distinct approach towards performance prediction. We first expand SKOPE (a SKeleton framewOrk for Performance Exploration) with performance models for disk data read, cache performance, and page fault penalty. Second, an analytical performance model is also developed. We have evaluated our performance prediction framework as well as the analytical model on three hardware setups with well-known data mining algorithms implemented in three programming paradigms, MapReduce, MATE (a MapReduce-like parallel system with an alternate API for multi-core environments) and Smart (a MapReduce-like framework for in-situ analytics). Results show that our performance prediction framework along with the incorporated performance models are capable of accurately predicting execution times for parallel scientific analytics on different hardware setups.

97 MATHEMATICS AND COMPUTING↗

Clustering-Based Predictive Analytics to Improve Scientific Data Discovery

Given the sheer volume of scientific data archived within the data-intensive projects at the US Department of Energy's Oak Ridge National Laboratory, finding precisely what data we are looking for may not be a trivial task; conversely, we may also miss a more prominent data product. To address such issues, we propose improving the data discovery system and using data analytics methods to comprehend what specific users might be interested in based on their physiological state, search patterns, and past data usage history. This work's primary goal is to prune the complexity, increase the visibility of popular data products, and direct users toward the data that best meet their needs. The proposed algorithm constructs a user profile based on the user's explicit or implicit interactions with the system, such as items they are currently looking at on-site and the key metadata mappings related to the data set. The pattern is then used to build a training data set, which will help find relevant data to recommend to the user.

Devarakonda, Ranjeet↗

Materials Characterization, Prediction and Control Project: Summary Report on Data Analytics Framework

This report summarizes the activities performed under the data analytics Vertex in the Materials Characterization, Prediction and Control Project funded under laboratory directed research and development at Pacific Northwest National Laboratory. The data analytics Vertex developed models for associating global or local process parameters, microstructural features, and performance properties of friction-stir-processed 316L stainless steel plates. Statistical, machine learning, and deep learning models, as well as generative artificial intelligence approaches, were used to develop the associations between the process-structure-property data streams. These associations formed the basis for predicting global properties of parts manufactured under different process envelopes, providing a basis for predicting performance using data driven as well as physics-informed and physics-constrained approaches. Additionally, the associations were used to predict local process parameters and microstructural features of the product, predictive relationships that have the potential to form the basis of a control framework that could eventually modulate a friction-stir process to maintain product quality.

316L stainless steel↗

Where Big Data and Prediction Meet

Our ability to assemble and analyze massive data sets, often referred to under the title of “big data”, is an increasingly important tool for shaping national policy. This in turn has introduced issues from privacy concerns to cyber security. But as IBM’s John Kelly emphasized in the last Innovation, making sense of the vast arrays of data will require radically new computing tools. In the past, technologies and tools for analysis of big data were viewed as quite different from the traditional realm of high performance computing (HPC) with its huge models of phenomena such as global climate or supporting the nuclear test moratorium. Looking ahead, this will change with very positive benefits for both worlds. Societal issues such as global security, economic planning and genetic analysis demand increased understanding that goes beyond existing data analysis and reduction. The modeling world often produces simulations that are complex compositions of mathematical models and experimental data. This has resulted in outstanding successes such as the annual assessment of the state of the US nuclear weapons stockpile without underground nuclear testing. Ironically, while there were historically many test conducted, this body of data provides only modest insight into the underlying physics of the system. A great deal of emphasis was thus placed on the level of confidence we can develop for the predictions. As data analytics and simulation come together, there is a growing need to assess the confidence levels in both data being gathered and the complex models used to make predictions. An example of this is assuring the security or optimizing the performance of critical infrastructure systems such as the power grid. If one wants to understand the vulnerabilities of the system or impacts of predicted threats, full scales tests of the grid against threat scenarios are unlikely. Preventive measures would need to be predicated on well-defined margins of confidence in order to take mitigating actions that could have wide ranging impacts. There is a rich opportunity for interaction and exchange between the HPC simulation and data analytics communities.

97 MATHEMATICS AND COMPUTING↗

High Performance Data Analytics on a Commodity Private Cloud

Sandia is researching novel methods of analysis for large datasets. The term “Big Data” has been used frequently in recent years to describe a discipline of computer science that attempts to distil an increasing quantity of data into a result or meaningful subset that can be easily visualized and acted upon by human consumers. These data are frequently characterized by one or more of the following: high volume, velocity, variety, and veracity. Sandia scientists and researchers are no strangers to large datasets, which often typify the result of high-performance computing workloads. The challenge for Sandia data scientists, however, comes at the arrival of exascale computing, which has become mandated by executive order for national computing centers. Because of power and networking limitations, exascale computing precludes the movement of datasets at exascale from data production to data analysis. Such analysis must be done in-situ, to mitigate the time and power costs of network transport. Currently, many of Sandia’s data analytics environments exist as independent entities, often specialized for individual use cases, interconnected to other data analytics, high-performance computing, and storage systems. Sandia is procuring, installing, and researching future platforms for such data analytics. A memory footprint of 256 GB per node, fourteen data rate (FDR) InfiniBand networking, PCIe connected non-volatile memory (NVMe) data storage, and an object data store will characterize the coming institutional data analytics platforms. The combined systems will contain 300 compute nodes. A cloud-inspired software stack resulting from collaboration between the Sandia centers will allow the systems to support a flexible mix of user and system-facing workloads and use cases including code development and testing in R and Python, Apache Hadoop and Spark, distributed in-memory databases, graph analytics, emulytics, system log and predictive analytics, and data visualization for institutional and mission customers. These systems will arrive at the end of FY 2015 and production is planned by the spring of FY 2016.

97 MATHEMATICS AND COMPUTING↗

Analytical models of the strength and ductility of CNT reinforced metal matrix nano composites under elevated temperatures

Carbon nanotubes (CNTs) can greatly enhance the strength of metal matrix composites while resulting in ductility loss. This strength-ductility tradeoff dilemma always confines the development of material design and real-life applications. Here in this work, a temperature dependent strengthening analytical model is proposed for CNT reinforced metal matrix composites which considers three common strengthening mechanisms: Orowan looping effect, thermal expansion mismatch effect, and load bearing effect. The proposed model can predict composite material strength with different volume fractions of CNTs and under different temperatures. Combining the strengthening model with the stress based modified Mohr-Coulomb (sMMC) ductile fracture model, a ductility analytical model is then derived. This ductility analytical model includes the influences of temperature, multi-axial stress loading conditions, as well as the aforementioned three strengthening mechanisms. A good agreement has been achieved between literature published experimental data and analytical predictions for both composite material strength and ductility loss. The proposed two analytical models can provide a straightforward way to study the strength-ductility relationship for CNT reinforced metal matrix composites over a wide range of temperatures and different stress states, and then provide guidance on new material design and processing.

36 MATERIALS SCIENCE↗

Enabling Efficient Surveillance, Control, and Automation of Geothermal Operations with Advanced Predictive Analytics

Automation and control of geothermal energy production and operations require reliable and efficient predictive tools. While physics-based simulation offers a comprehensive tool for predicting energy production performance in geothermal systems, predicting the behavior of geothermal reservoirs involves complex multi-physics processes with coupling effects, highly uncertain input parameters and subsurface descriptions. Moreover, building, running, and integrating simulation models into standard model calibration and optimization workflows entail significant technical and computational efforts. An emerging alternative to physics-based simulation is data-driven predictive analytics models that have gained popularity in energy industry. In this report, we develop novel predictive models for integration into real-time fault diagnosis and model predictive control algorithms to improve the efficiency of energy production operations in geothermal reservoirs. The report includes two major research Thrust Areas, that is, the surface power plant and the subsurface reservoir.

15 GEOTHERMAL ENERGY↗

Effect of the thickness of electron beams on the gyrotron efficiency

In this paper the effect of the spread in the radii of electron guiding centers on the gyrotron efficiency is studied. First, the analytical theory is developed for describing this effect in gyrotrons operating in regimes of soft and hard self-excitations. Then, study of this effect in a 670 GHz gyrotron is carried out both analytically and numerically with the use of the available nonstationary self-consistent code. Comparison of results demonstrates very reasonable agreement between numerical data and analytical predictions. It was found that in the case of beam injection at the inner peak of the function describing the beam coupling to the wave the spread in electron guiding center radii can be significantly larger than is usually allowed. This fact greatly alleviates the design of electron guns for terahertz-range gyrotrons.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

High-precision determination of low-energy effective parameters for a two-dimensional Heisenberg quantum antiferromagnet

The two-dimensional (2D) spin-(1/2) Heisenberg antiferromagnet with exchange coupling J is investigated on a periodic square lattice of spacing a at very small temperatures using the loop-cluster algorithm. Monte Carlo data for the staggered and uniform susceptibilities are compared with analytic results obtained in the systematic low-energy effective field theory for the staggered magnetization order parameter. The low-energy parameters of the effective theory, i.e., the staggered magnetization density M{sub s}=0.307 43(1)/a{sup 2}, the spin stiffness {rho}{sub s}=0.180 81(11)J, and the spin wave velocity c=1.6586(3)Ja, are determined with very high precision. Our study may serve as a test case for the comparison of lattice quantum chromodynamics Monte Carlo data with analytic predictions of the chiral effective theory for pions and nucleons, which is vital for the quantitative understanding of the strong interaction at low energies.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

Research and Education in Computational Science and Engineering

Over the past two decades the field of computational science and engineering (CSE) has penetrated both basic and applied research in academia, industry, and laboratories to advance discovery, optimize systems, support decision-makers, and educate the scientific and engineering workforce. Informed by centuries of theory and experiment, CSE performs computational experiments to answer questions that neither theory nor experiment alone is equipped to answer. CSE provides scientists and engineers of all persuasions with algorithmic inventions and software systems that transcend disciplines and scales. Carried on a wave of digital technology, CSE brings the power of parallelism to bear on troves of data. Mathematics-based advanced computing has become a prevalent means of discovery and innovation in essentially all areas of science, engineering, technology, and society; and the CSE community is at the core of this transformation. However, a combination of disruptive developments— including the architectural complexity of extreme-scale computing, the data revolution that engulfs the planet, and the specialization required to follow the applications to new frontiers—is redefining the scope and reach of the CSE endeavor. This report describes the rapid expansion of CSE and the challenges to sustaining its bold advances. The report also presents strategies and directions for CSE research and education for the next decade.

computational science and engineering↗

ALUMINUM READINESS EVALUATION FOR ALUMINUM REMOVAL AND SODIUM HYDROXIDE REGENRATION FROM HANFORD TANK WASTE BY LITHIUM HYDROTALCITE PRECIPITATION

A Technology Readiness Evaluation (TRE) performed by AREV A Federal Services, LLC (AFS) for Washington River Protection Solutions, LLC (WRPS) shows the lithium hydrotalcite (LiHT) process invented and patented (pending) by AFS has reached an overall Technology Readiness Level (TRL) of 3. The LiHT process removes aluminum and regenerates sodium hydroxide. The evaluation used test results obtained with a 2-L laboratory-scale system to validate the process and its critical technology elements (CTEs) on Hanford tank waste simulants. The testing included detailed definition and evaluation for parameters of interest and validation by comparison to analytical predictions and data quality objectives for critical subsystems. The results of the TRE would support the development of strategies to further mature the design and implementation of the LiHT process as a supplemental pretreatment option for Hanford tank waste.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Improving Additive Manufactured Component Performance through Multi-Scale Microstructure Simulation and Process Optimization

The purpose of this project was to utilize computational tools to understand the relationships between processing, microstructure, and properties for additively manufactured (AM) aluminum alloys for automotive applications, and to provide an engineering solution for helping to optimize process conditions. The project leverages ORNL developments in computational modeling, including AM process modeling, phase-field based microstructure evolution predictions, and data analytics techniques for mapping process conditions to material outcomes. The project utilized an Al-Cu-Mn-Zr alloy as a model material for studying formation of defects and microstructural features in response to variations in process conditions. Based on both pre-existing experimental data and simulation results, statistical process maps were constructed to identify regions of process space with minimal defect formation and advantageous microstructures and properties. The software tools used for this purpose were successful disseminated to GM, who were able to successful compile the relevant HPC codes within their own computing ecosystem and perform initial calculations to reproduce ORNL results.

36 MATERIALS SCIENCE↗

Machine Tool Data Analytics for Digital Twin and Machine Predictive Maintenance

The primary objective of this project is to improve machining process performance using in-process machining data from the machine tool controller and external sensors. Advances in the Industrial Internet of Things (IIoT) enable monitoring of machines using controller data. Examples of the data provided by a controller include execution status of the controller, part count, block of code being executed, door status, tool position, the spindle and axis load, etc. MTConnect and OPC-UA are the two common protocols for capturing machine information. In this collaboration, methods for retrieving the machine controller data from selected machine tool controls and making these data accessible in different subsystems (such as digital twins and machine maintenance portals, etc.) will be developed and tested. In addition, analytics to improve machining process performance (by increasing productivity and reducing downtime) will be developed.

42 ENGINEERING↗