Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Machine”

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 1,603 records · Page 89

Energy Recovery Linac: Machine Protection System

The Machine Protection System (MPS) is a device‐safety system that is designed to prevent damage to hardware by generating interlocks, based upon the state of input signals generated by selected sub‐system. It exists to protect key machinery such as the 50 kW and 1 MW RF Systems. When a fault state occurs, the MPS is capable of responding with an interlock signal within several microseconds. The Machine Protection System inputs are designed to be fail‐safe. In addition, all fault conditions are latched and time‐stamped.

43 PARTICLE ACCELERATORS↗

A Simple Crunching of the AGS "bare" machine ORM Data - February 2007 - to extract some aspects of AGS Transverse Coupling at Injection and Extraction

The objective of this note is to (once again) explore the AGS “ORM” (orbit response matrix) data taken (by Operations) early during the 2007 run with an AGS bare machine and gold beam. Indeed the present motivation is to extract as much information about the AGS inherent transverse coupling as possible - from general arguments and the copious ORM data. And taking this one step further, (though not accomplished yet) the goal really should be to tell the model how to describe this coupling. “Bare” as used here means the AGS with no quadrupole, sextupole or octupole magnets powered. Only the main (combined-function) magnet string and dipole bumps necessary to optimize beam survival are powered. “ORM data” means the systematic recording of the equilibrium orbit beam position monitor response to powering individual dipole corrector magnets. The “matrix” results from looking at the effect of each of the (12 superperiods X 4 dipoles per superperiod) “kicks” on each of the (12 X 6) pick up electrodes (pues) in each transverse plane. So then we have two (48X72) matrices of numbers from the ORM data. (Though “pue” usually refers to the hardware in the vacuum chamber and “bpm” to the beam position monitoring system, the two labels will be used casually here.) The exercise is carried out at two magnet rigidities, injection (AGS field ~434 Gauss) and extraction to RHIC (~9730 Gauss), - a ratio of rigidities of about 22.4. Since we stick with a bare machine, we are also stuck with the bare tunes which means the tunes are rather close together and near 8.75. (Injection : (h,v) ~ (8.73, 8.76).

43 PARTICLE ACCELERATORS↗

Hot Coordinate Measuring Machine Technical Specifications and Requirements (U)

The goal of this document is to outline the technical specifications and requirements for a new Hot Coordinate Measuring Machine at TA-55. This document should be used in conjunction with the information provided from TA-55 Hot CMM Location Study and TA-55 Hot CMM Technology Assessment. All three documents will guide the user to the optimal coordinate measuring machine selection.

42 ENGINEERING↗

Evaluation Of Electrochemical Machining Technology For Surface Improvements In Additive Manufactured Components

ORNL Manufacturing Demonstration Facility worked with ECM Technologies LLC to investigate the use of precision electro-chemical machining technology to polish the surface of parts created by Arcam electron beam melting. The goals for phase one of this project have been met. The project goal was to determine whether electro-chemical machining is a viable method to improve the surface finish of Inconel 718 parts fabricated using the Arcam EBM method. The project partner (ECM) demonstrated viability for parts of both simple and complex geometry. During the course of the project, detailed process knowledge was generated. This project has resulted in the expansion of United States operations for ECM Technologies.

42 ENGINEERING↗

Using Machine Learning in Adversarial Environments.

Intrusion/anomaly detection systems are among the first lines of cyber defense. Commonly, they either use signatures or machine learning (ML) to identify threats, but fail to account for sophisticated attackers trying to circumvent them. We propose to embed machine learning within a game theoretic framework that performs adversarial modeling, develops methods for optimizing operational response based on ML, and integrates the resulting optimization codebase into the existing ML infrastructure developed by the Hybrid LDRD. Our approach addresses three key shortcomings of ML in adversarial settings: 1) resulting classifiers are typically deterministic and, therefore, easy to reverse engineer; 2) ML approaches only address the prediction problem, but do not prescribe how one should operationalize predictions, nor account for operational costs and constraints; and 3) ML approaches do not model attackers’ response and can be circumvented by sophisticated adversaries. The principal novelty of our approach is to construct an optimization framework that blends ML, operational considerations, and a model predicting attackers reaction, with the goal of computing optimal moving target defense. One important challenge is to construct a realistic model of an adversary that is tractable, yet realistic. We aim to advance the science of attacker modeling by considering game-theoretic methods, and by engaging experimental subjects with red teaming experience in trying to actively circumvent an intrusion detection system, and learning a predictive model of such circumvention activities. In addition, we will generate metrics to test that a particular model of an adversary is consistent with available data.

97 MATHEMATICS AND COMPUTING↗

Efficient Machine Learning Approach for Optimizing Scientific Computing Applications on Emerging HPC Architectures

Efficient parallel implementations of scientific applications on multi-core CPUs with accelerators such as GPUs and Xeon Phis is challenging. This requires - exploiting the data parallel architecture of the accelerator along with the vector pipelines of modern x86 CPU architectures, load balancing, and efficient memory transfer between different devices. It is relatively easy to meet these requirements for highly structured scientific applications. In contrast, a number of scientific and engineering applications are unstructured. Getting performance on accelerators for these applications is extremely challenging because many of these applications employ irregular algorithms which exhibit data-dependent control-ow and irregular memory accesses. Furthermore, these applications are often iterative with dependency between steps, and thus making it hard to parallelize across steps. As a result, parallelism in these applications is often limited to a single step. Numerical simulation of charged particles beam dynamics is one such application where the distribution of work and memory access pattern at each time step is irregular. Applications with these properties tend to present significant branch and memory divergence, load imbalance between different processor cores, and poor compute and memory utilization. Prior research on parallelizing such irregular applications have been focused around optimizing the irregular, data-dependent memory accesses and control-ow during a single step of the application independent of the other steps, with the assumption that these patterns are completely unpredictable. We observed that the structure of computation leading to control-ow divergence and irregular memory accesses in one step is similar to that in the next step. It is possible to predict this structure in the current step by observing the computation structure of previous steps. In this dissertation, we present novel machine learning based optimization techniques to address the parallel implementation challenges of such irregular applications on different HPC architectures. In particular, we use supervised learning to predict the computation structure and use it to address the control-ow and memory access irregularities in the parallel implementation of such applications on GPUs, Xeon Phis, and heterogeneous architectures composed of multi-core CPUs with GPUs or Xeon Phis. We use numerical simulation of charged particles beam dynamics simulation as a motivating example throughout the dissertation to present our new approach, though they should be equally applicable to a wide range of irregular applications. The machine learning approach presented here use predictive analytics and forecasting techniques to adaptively model and track the irregular memory access pattern at each time step of the simulation to anticipate the future memory access pattern. Access pattern forecasts can then be used to formulate optimization decisions during application execution which improves the performance of the application at a future time step based on the observations from earlier time steps. In heterogeneous architectures, forecasts can also be used to improve the memory performance and resource utilization of all the processing units to deliver a good aggregate performance. We used these optimization techniques and anticipation strategy to design a cache-aware, memory efficient parallel algorithm to address the irregularities in the parallel implementation of charged particles beam dynamics simulation on different HPC architectures. Experimental result using a diverse mix of HPC architectures shows that our approach in using anticipation strategy is effective in maximizing data reuse, ensuring workload balance, minimizing branch and memory divergence, and in improving resource utilization.

Arumugam, Kamesh↗

Weekly Update - Neutron Imaging Machine Build

The neutron imaging machine build effort continues to make solid progress in installing equipment, wiring up subsystems, and aligning the overall machine in anticipation of performing the accelerator readiness review for the authorization safety basis.

42 ENGINEERING↗

Workshop Report on Basic Research Needs for Scientific Machine Learning: Core Technologies for Artificial Intelligence

Scientific Machine Learning (SciML) and Artificial Intelligence (AI) will have broad use and transformative effects across the Department of Energy. Accordingly, the January 2018 Basic Research Needs workshop identified six Priority Research Directions (PRDs). The first three PRDs describe foundational research themes that correspond to the need for domain-awareness (PRD #1), interpretability (PRD #2), and robustness (PRD #3). The other three PRDs describe capability research themes and correspond to the three major use cases for massive scientific data analysis (PRD #4), machine learning-enhanced modeling and simulation (PRD #5), and intelligent automation and decision-support for complex systems (PRD #6). The Priority Research Directions provide a sound basis for a coherent, long-term research and development strategy in SciML and AI. Over the last decade, DOE investments in applied mathematics have laid the groundwork for the type of basic research that will underpin key advances in the six PRDs. Such advances will build on the work from leading researchers in optimization, linear algebra, high-performance solvers and algorithms, multiscale modeling and simulation, complex systems research, uncertainty quantification, and the new basic research areas that will emerge from the pursuit of transformative technologies.

97 MATHEMATICS AND COMPUTING↗

Brochure on Basic Research Needs for Scientific Machine Learning: Core Technologies for Artificial Intelligence [Slides]

Scientific Machine Learning (SciML) and Artificial Intelligence (AI) will have broad use and transformative effects across the Department of Energy. Accordingly, the January 2018 Basic Research Needs workshop identified six Priority Research Directions (PRDs). The first three PRDs describe foundational research themes that correspond to the need for domain-awareness (PRD #1), interpretability (PRD #2), and robustness (PRD #3). The other three PRDs describe capability research themes and correspond to the three major use cases for massive scientific data analysis (PRD #4), machine learning-enhanced modeling and simulation (PRD #5), and intelligent automation and decision-support for complex systems (PRD #6). The Priority Research Directions provide a sound basis for a coherent, long-term research and development strategy in SciML and AI. Over the last decade, DOE investments in applied mathematics have laid the groundwork for the type of basic research that will underpin key advances in the six PRDs. Such advances will build on the work from leading researchers in optimization, linear algebra, high-performance solvers and algorithms, multiscale modeling and simulation, complex systems research, uncertainty quantification, and the new basic research areas that will emerge from the pursuit of transformative technologies.

97 MATHEMATICS AND COMPUTING↗

Integrated Multi Scale Data Analytics and Machine Learning for the Grid; Benchmarking Algorithms and Data Quality Analysis

Machine Learning and Data Analytics are terms which are utilized now ubiquitously throughout grid analytics forums, as a potential solution to the growing big data challenges for the distribution grid. As sensors become inexpensive and common, and communication networks grow, the analytics themselves must adapt and enable consumers and providers to visualize and utilize the data provided effectively. Machine learning is one of the techniques proposed in order to manage this data deluge. This report is a subset of the work in this activity, funded through the DOE Grid Modernization Initiative, to summarize the benchmarking and review of data quality impact on the algorithm sets being developed within each use case area.

42 ENGINEERING↗

Electrochemical Machining Technology for Surface Improvements of Ni-base Superalloy Additively Manufactured Components

Additive Manufacturing’s (AM) promise and potential is of growing interest to US industries such as the energy sector. However, to move AM from prototyping to full-scale production a number of key risk areas must still be overcome, particularly the enhancing the surface finish of AM parts. Due to the industry’s desire for components fabricated from difficult to machine alloys and highly complex geometries, advanced finishing technologies are needed. This project focused on the ability to enhance the surface finish of material from the crack prone Ni-base superalloy Inconel 738 fabricated using the Arcam electron beam melting (EBM) process using the Pulsed Electrochemical Machining (PECM) process for surface enhancements. To evaluate the suitability of the PECM process, several artifacts were experimented with, each of which had increasing levels of complexity and relevancy to the industrial gas turbine sector. Ultimately, it was shown that the finish of as-built relevant EBM gas turbine airfoil surfaces could be enhanced by an average of 4x to approach an average roughness of a surface (Ra) equivalent of 1 um.

36 MATERIALS SCIENCE↗

Online Simulation Tools for Orbit Correction in the CBETA Machine (CBETA Note 029)

Control of beam trajectory is essential in particle accelerators. The trajectory of a beam is sensitive to various types of imperfections that cause it to deviate from its desired path along the accelerator. Orbit correction is hence fundamental for the control of beam trajectory. In this work we aim demonstrate orbit correction using singular value decomposition techniques applied to distorted orbits generated in the CBETA-V Virtual Machine. In particular we present two concrete examples of such correction in different sections of the CBETA Fractional Arc Test layout. Our goal is to construct the backbone of an orbit correction software toolkit to be tested in the CBETA-V Virtual Machine and eventually implemented in the completed CBETA control system.

43 PARTICLE ACCELERATORS↗

Using Machine Learning in Adversarial Environments

Cyber defense is an asymmetric battle today. We need to understand better what options are available for providing defenders with possible advantages. Our project combines machine learning, optimization, and game theory to obscure our defensive posture from the information the adversaries are able to observe. The main conceptual contribution of this research is to separate the problem of prediction, for which machine learning is used, and the problem of computing optimal operational decisions based on such predictions, coupled with a model of adversarial response. This research includes modeling of the attacker and defender, formulation of useful optimization models for studying adversarial interactions, and user studies to measure the impact of the modeling approaches in realistic settings.

97 MATHEMATICS AND COMPUTING↗

FPGAs as a Service to Accelerate Machine Learning Inference [PowerPoint]

Large-scale particle physics experiments face challenging demands for high-throughput computing resources both now and in the future. New heterogeneous computing paradigms on dedicated hardware with increased parallelization, such as Field Programmable Gate Arrays (FPGAs), offer exciting solutions with large potential gains. The growing applications of machine learning algorithms in particle physics for simulation, reconstruction, and analysis are naturally deployed on such platforms. We demonstrate that the acceleration of machine learning inference as a web service represents a heterogeneous computing solution for particle physics experiments that requires minimal modification to the current computing model. As examples, we retrain the ResNet-50 convolutional neural network to demonstrate state-of-the-art performance for top quark jet tagging at the LHC, and apply a ResNet-50 model with transfer learning for neutrino event classification. Using Project Brainwave b y Microsoft to accelerate the ResNet-50 image classification model, we achieve average inference times of 60 (10) milliseconds with our experimental physics software framework using Brainwave as a cloud (edge or on-premises) service, representing an improvement by a factor of approximately 30 (175) in model inference latency over traditional CPU inference in current experimental hardware. A single FPGA service accessed by many CPUs achieves a throughput of 600--700 inferences per second using an image batch of one, comparable to large batch-size GPU throughput and significantly better than small batch-size GPU throughput. Deployed as an edge or cloud service for the particle physics computing model, coprocessor accelerators can have a higher duty cycle and are potentially much more cost-effective.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

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↗

Accelerated Machine Learning as a Service for Particle Physics Computing

Accelerated Machine Learning as a Service for Particle Physics Computing: • Amount and complexity of high-energy physics data increases dramatically from 2025 onward • Traditional algorithms will require too much CPU time • Machine learning can solve combinatorially-scaling problems in constant time, but must be fast enough

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Predicting Solar Plant Generation with Machine Learning Techniques

Accurately predicting power generation for PV sites is critical for prioritizing relevant operations & maintenance activities, thereby extending the lifetime of a system and improving profit margins. A number of factors influence power generation at PV sites, including local weather, shading and soiling losses, design of modules, DC mismatches, and degradation over time. Other external factors such as curtailment and grid outages can also have a notable impact on power generation. Machine learning techniques can be used to provide more accurate predictions of PV power production by accounting for important weather and climate information neglected by current industry methods. This article will cover the deficiencies of those methods and will show how machine learning can dramatically improve power generation predictions.

14 SOLAR ENERGY↗

Real-Time Adaptive Machine Learning Platform

As part of the Cyclotron Road program, Dauntless.io, Inc. extended its existing ultrafast (0.00001 – 0.001 second) real-time, adaptive machine learning platform for modeling & control of complex, high-value physical systems. Objectives included ability to scale ubiquitously & remain differentiated on a 5+ year horizon in the highly competitive, AI / machine learning market — a rapidly growing market that (overall) is estimated to be worth $191 B by 2024 at a CAGR of 37%.

97 MATHEMATICS AND COMPUTING↗