Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “train”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2022

Current Status of the DOE/NNSA Nuclear Criticality Safety Program Hands-on Criticality Safety Training Courses

In 2011, the US Department of Energy/National Nuclear Security Administration (DOE/NNSA) Nuclear Criticality Safety Program (NCSP) developed and piloted a 2-week nuclear criticality safety (NCS) practitioner course to support training and qualification of new NCS staff. The course was developed in accordance with the American National Standard Institute/American Nuclear Society (ANSI/ANS) standard for NCS training and qualifications (ANSI/ANS-8.26-2007). In 2013, an NCS manager’s course was developed for process supervisors, managers, regulators, and other professionals with NCS-related responsibilities. These courses consist of classroom education, facility training, and hands-on subcritical and critical experiments training. Each course is currently offered twice per year. The 2-week practitioner course offers a week of classroom training, with practical workshops and exercises focused on teaching students how to perform an NCS evaluation. The second week of training involves hands-on critical and subcritical experiments and measurements. The first week is offered in Las Vegas, Nevada, at the DOE Nevada Field Office or the National Atomic Testing Museum. Depending on the student’s clearance level, the second week is offered at Sandia National Laboratory (SNL) (uncleared and L-cleared students) or at the National Criticality Experiments Research Center (NCERC) (Q-cleared students). The 1-week manager’s course is offered at SNL or NCERC, depending on clearance or interest, and includes classroom and hands-on critical and subcritical experiments and measurements. This paper provides an overview and status report for the DOE/NNSA NCSP training courses in NCS and provides information about future course offerings.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2024

Implications of stop-and-go traffic on training learning-based car-following control

Learning-based car-following control (LCC) of connected and autonomous vehicles (CAVs) is gaining significant attention with the advancement of computing power and data accessibility. While the flexibility and large model capacity of model-free architecture enable LCC to potentially outperform the model-based car-following (CF) model in improving traffic efficiency and mitigating congestion, the generalizability of LCC for traffic conditions different from the training environment/dataset is not well-understood. Herein, this study seeks to explore the impact of stop-and-go traffic in the training dataset on the generalizability of LCC. It uses the characteristics of lead vehicle trajectories to describe stop-and-go traffic, and links the theory of identifiability (i.e., obtaining a unique parameter estimation result using sensor measurements) to the generalizability of behavior cloning (BC) and policy-based deep reinforcement learning (DRL). Correspondingly, the study shows theoretically that: (i) stop-and-go traffic can enable the property of identifiability and enhance the control performance of BC-based LCC in different traffic conditions; (ii) stop-and-go traffic is not necessary for DRL-based LCC to generalize to different traffic conditions; (iii) DRL-based LCC trained with only constant-speed lead vehicle trajectories (not sufficient to ensure identifiability) can be generalized to different traffic conditions; and (iv) stop-and-go traffic increases variance in the training dataset, which improves the convergence of parameter estimation while negatively impacting the convergence of DRL to the optimal control policy. Numerical experiments validate the above findings, illustrating that BC-based LCC entails comprehensive training datasets for generalizing to different traffic conditions, while DRL-based LCC can achieve generalization with simple free-flow traffic training environments. This further suggests DRL as a more promising and cost-effective LCC approach to reduce operational costs, mitigate traffic congestion, and enhance safety and mobility, which can accelerate the deployment and acceptance of CAVs.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2023

Utilizing multimodal high-intensity interval training for a firefighter training academy during the COVID-19 pandemic

Firefighters typically undergo a 16–24-week training academy during which they perform a variety of traditional exercise programs such as cardiovascular, resistance, and concurrent training. Because of limited facility access, some fire departments seek alternative exercise programs, such as multimodal high-intensity interval training (MM-HIIT), which essentially combines resistance and interval training. Here, the primary purpose of this study was to assess the effect of MM-HIIT on body composition and physical fitness in firefighter recruits who completed a training academy during the coronavirus (COVID-19) pandemic. A secondary purpose was to compare the effects of MM-HIIT to previous training academies that implemented traditional exercise programs. Healthy and recreationally-trained recruits (n=12) participated in 2-3 days/week of MM-HIIT for 12 weeks and had several components of body composition and physical fitness measured before and after the program. Because of COVID-19-related gym closures, all MM-HIIT sessions were performed outdoors at a fire station with minimal equipment. These data were retroactively compared to a control group (CG) that previously completed training academies with traditional exercise programs. Subjects in the MM-HIIT group significantly improved several components of body composition and fitness, including fat mass, fat-free mass, body fat percentage, aerobic capacity, and muscular endurance (p < 0.005). Moreover, there were no significant differences for any dependent variable when MM-HIIT was compared to the CG (p≥0.005). These results suggest that MM-HIIT may serve as an effective substitute for traditional concurrent training paradigms that are typically used for firefighter academies.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Reducing Communication in Graph Neural Network Training

Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse connectivity information of the data. GNNs represent this connectivity as sparse matrices, which have lower arithmetic intensity and thus higher communication costs compared to dense matrices, making GNNs harder to scale to high concurrencies than convolutional or fully-connected neural networks. Here, we introduce a family of parallel algorithms for training GNNs and show that they can asymptotically reduce communication compared to previous parallel GNN training methods. We implement these algorithms, which are based on 1D, 1. 5D, 2D, and 3D sparse-dense matrix multiplication, using torch.distributed on GPU-equipped clusters. Our algorithms optimize communication across the full GNN training pipeline. We train GNNs on over a hundred GPUs on multiple datasets, including a protein network with over a billion edges.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

A pre-training and self-training approach for biomedical named entity recognition

Named entity recognition (NER) is a key component of many scientific literature mining tasks, such as information retrieval, information extraction, and question answering; however, many modern approaches require large amounts of labeled training data in order to be effective. This severely limits the effectiveness of NER models in applications where expert annotations are difficult and expensive to obtain. In this work, we explore the effectiveness of transfer learning and semi-supervised self-training to improve the performance of NER models in biomedical settings with very limited labeled data (250-2000 labeled samples). We first pre-train a BiLSTM-CRF and a BERT model on a very large general biomedical NER corpus such as MedMentions or Semantic Medline, and then we fine-tune the model on a more specific target NER task that has very limited training data; finally, we apply semi-supervised self-training using unlabeled data to further boost model performance. We show that in NER tasks that focus on common biomedical entity types such as those in the Unified Medical Language System (UMLS), combining transfer learning with self-training enables a NER model such as a BiLSTM-CRF or BERT to obtain similar performance with the same model trained on 3x-8x the amount of labeled data. We further show that our approach can also boost performance in a low-resource application where entities types are more rare and not specifically covered in UMLS.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2021

Controllable X-ray Pulse Trains from Enhanced Self-Amplified Spontaneous Emission

We report the demonstration of optical compression of an electron beam and the production of controllable trains of femtosecond, soft x-ray pulses with the Linac Coherent Light Source (LCLS) freeelectron laser (FEL). This is achieved by enhanced self-amplified spontaneous emission with a 2 μm laser and a dechirper device. Optical compression was achieved by modulating the energy of an electron beam with the laser and then compressing with a chicane, resulting in high current spikes on the beam which we observe to lase. A dechirper was then used to selectively control the lasing region of the electron beam. Field autocorrelation measurements indicate a train of pulses, and we find that the number of pulses within the train can be controlled (from 1 to 5 pulses) by varying the dechirper position and undulator taper. These results are a step toward attosecond spectroscopy with x-ray FELs as well as future FEL schemes relying on optical compression of an electron beam.

Duris, Joseph P↗
DOE OSTI2023

Simple Diesel Train Fuel Consumption Model for Real-Time Train Applications

This paper introduces a simple diesel train energy consumption model that calculates the instantaneous energy consumption using vehicle operational input variables, including the instantaneous speed, acceleration, and roadway grade, which can be easily obtained from global positioning system (GPS) loggers. The model was tested against real-world data and produced an error of -1.33% for all data and errors ranging from -12.4% to +8.0% for energy consumption of four train datasets amounting to a total of 5854 km trips. The study also validated the proposed model with separate data that were collected between Valencia and Cuenca, Spain, which had a total length of 198 km and found that the model was accurate, yielding a relative error of -1.55% for the total energy consumption. These results show that the proposed model can be used by train operators, transportation planners, policy makers, and environmental engineers to evaluate the energy consumption effects of train operational projects and train simulation within intermodal transportation planning tools.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

Improved Architectures and Training Algorithms for Deep Operator Networks

Operator learning techniques have recently emerged as a powerful tool for learning maps between infinite-dimensional Banach spaces. Trained under appropriate constraints, they can also be effective in learning the solution operator of partial differential equations (PDEs) in an entirely self-supervised manner. In this work we analyze the training dynamics of deep operator networks (DeepONets) through the lens of Neural Tangent Kernel theory, and reveal a bias that favors the approximation of functions with larger magnitudes. To correct this bias we propose to adaptively re-weight the importance of each training example, and demonstrate how this procedure can effectively balance the magnitude of back-propagated gradients during training via gradient descent. We also propose a novel network architecture that is more resilient to vanishing gradient pathologies. Taken together, our developments provide new insights into the training of DeepONets and consistently improve their predictive accuracy by a factor of 10-50x, demonstrated in the challenging setting of learning PDE solution operators in the absence of paired input-output observations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

A nearsighted force-training approach to systematically generate training data for the machine learning of large atomic structures

A challenge of atomistic machine-learning (ML) methods is ensuring that the training data are suitable for the system being simulated, which is particularly challenging for systems with large numbers of atoms. Most atomistic ML approaches rely on the nearsightedness principle (“all chemistry is local”), using information about the position of an atom’s neighbors to predict a per-atom energy. Here, in this work, we develop a framework that exploits the nearsighted nature of ML models to systematically produce an appropriate training set for large structures. We use a per-atom uncertainty estimate to identify the most uncertain atoms and extract chunks centered around these atoms. It is crucial that these small chunks are both large enough to satisfy the ML’s nearsighted principle (that is, filling the cutoff radius) and are large enough to be converged with respect to the electronic structure calculation. We present data indicating when the electronic structure calculations are converged with respect to the structure size, which fundamentally limits the accuracy of any nearsighted ML calculator. These new atomic chunks are calculated in electronic structures, and crucially, only a single force—that of the central atom—is added to the growing training set, preventing the noisy and irrelevant information from the piece’s boundary from interfering with ML training. The resulting ML potentials are robust, despite requiring single-point calculations on only small reference structures and never seeing large training structures. We demonstrated our approach via structure optimization of a 260-atom structure and extended the approach to clusters with up to 1415 atoms.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Coherent high-power RF wakefield generation by electron bunch trains in a metamaterial structure

In this paper, we present an experimental study of coherent high-power wakefield generation in a metamaterial (MTM) structure at 11.7 GHz by 65 MeV electron bunch trains at the Argonne Wakefield Accelerator (AWA), following a previous experiment, the Stage-I experiment, at the AWA. Both the Stage-II experiment, reported in this paper, and the Stage-I experiment were conducted using MTM structures, which are all-metal periodic structures with the period being much smaller than the wavelength. Differences between the two experiments include (1) structure length (Stage-I 8 cm and Stage-II 20 cm); (2) number of bunches used to excite the structure (Stage-I with two bunches, up to 85 nC of total charge; Stage-II with eight bunches, up to 224 nC of total charge); and (3) highest peak power measured (Stage-I 80 MW in a 2 ns pulse and Stage-II 380 MW in a 10 ns pulse). High-power radio frequency pulses were generated by reversed Cherenkov radiation of the electron beam due to the negative group velocity in the MTM structures. Because the radiation is coherent, a train of bunches with a proper spacing can build up to achieve a high peak power. The observed output power levels are very promising for future applications in direct collinear wakefield acceleration or in transfer to a second accelerator for two-beam acceleration.

36 MATERIALS SCIENCE↗
DOE OSTI2019

Fine-Grained Exploitation of Mixed Precision for Faster CNN Training

As deep convolutional neural networks (CNNs) have become increasingly popular and successful at an ever-widening number of machine learning tasks specialized hardware has become increasingly available for training and deploying them. NVIDIA's recent Volta architecture includes tensor cores which perform a fused operation reduced and mixed precision (16-bit multiply, 32-bit accumulate). Recent research indicates that, typically, very little is lost (in terms of training accuracy) when half precision is used in place of single precision, and performance gains can be made by doing arithmetic in reduced precision. In this work we demonstrate that making layer-by-layer choices as to the arithmetic/data precision can lead to further performance improvement. In our study of 25,200 CNNs we demonstrate an average speedup (over purely half precision) of 1.27x and speedups as high as 3.64x by appropriately combining single and half precision arithmetic and data types on a layer-by-layer basis.

Johnston, Travis↗
DOE OSTI2021

Delivering Effective Virtual Energy-Focused Trainings: Successful Strategies and Lessons Learned from the Virtual Cohort In-Plant Training Pilot

While there are always barriers to energy efficiency efforts, few challenges have been as severe as the global COVID-19 pandemic. Many manufacturers throughout the United States and the world have been trying to determine how to safely open and operate their plants. To minimize the number of people working within facilities and maximize the physical distance between workers, only essential facility engineers are allowed into plants to ensure proper operations. The Department of Energy’s Better Plants Program created In-Plant Trainings (INPLTs) to help partners develop in-house expertise in energy efficiency. Delivering INPLTs in the traditional in-person fashion is infeasible under these circumstances. To continue providing INPLTs during this difficult time, the Better Plants Program piloted Virtual Cohort In-Plant Trainings (VINPLTs) on wastewater treatment and ammonia industrial refrigeration systems from October 27 to November 19, 2020. This paper provides an overview of the pilot, then discusses successful strategies and lessons learned from this pilot for delivering effective virtual energy-focused trainings.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2019

The Second ARM Training and Science Application Event: Training the Next Generation of Atmospheric Scientists

The Atmospheric Radiation Measurement (ARM) user facility (Turner and Ellingson 2016) collects valuable observations of atmospheric variables affecting the Earth’s radiation budget. These include properties of aerosol, cloud, precipitation, dynamic, and thermodynamic fields. The ARM user facility also supports routine high-resolution modeling efforts at its Southern Great Plains (SGP) site, and over the years it has had significant impacts on cloud-resolving and Earth system model development (Krueger et al. 2016; Randall et al. 2016). In an effort to promote use of the ARM data by the next generation of atmospheric scientists, the second ARM Summer Training and Science Applications Event on observations and modeling of clouds and precipitation took place from 14 to 21 July 2018. The event was sponsored by the ARM User Facility and was catered toward graduate students and early career scientists interested in observations and modeling of aerosol, cloud, and precipitation processes. Theoretical and practical instructions on the application of ground- and aircraft-based observations from a wide array of active and passive sensors, and finescale-resolution model simulations were provided during the training. This informed the participants about innovative methods for using the ARM data and numerical models to address complex scientific questions. The event was locally organized by the Cooperative Institute for Mesoscale Meteorological Studies (CIMMS) and was held at the National Weather Center in Norman, Oklahoma. The training was attended by 12 instructors and 24 participants.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

Strategic Training in Transdisciplinary Radiation Science for the 21st Century (STARS21): 15-Year Evaluation of an Innovative Research Training Program

To evaluate the 15-year impact of a transdisciplinary research training program for graduate students, postdoctoral fellows, and clinical trainees focused on radiation science, entitled Strategic Training in Transdisciplinary Radiation Science for the 21st Century (STARS21) with a primary objective to build capacity in radiation research.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2022

America’s Cutting Edge CNC machining and metrology training

This paper describes the workforce development activities supported by America’s Cutting Edge (ACE), a national initiative for machine tool technology development and advancement. ACE is supported by the Department of Defense Industrial Base Analysis and Sustainment (IBAS) program from the Office of Industrial Policy. Both the online and in-person components of the computer numerically controlled (CNC) machining and metrology training programs are summarized and participation information is provided.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2019

Decomposing the Train-Scheduling Problem into Integer-Optimal Polytopes

This paper presents conditions for which the linear relaxation for the train-scheduling problem is integer optimal. These conditions are then used to identify how to partition a general problem’s feasible region into integer-optimal polytopes. Such an approach yields an extended formulation that contains far fewer binary variables. Our computational experiments show that this approach results in significant computational savings. Moreover, this approach scales well when the train-scheduling problem is modeled using smaller time increments, allowing for higher fidelity models to be solved without significantly increasing the required computational time.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Co-training of multiple neural networks for simultaneous optimization and training of physics-informed neural networks for composite curing

This paper introduces a Physics-Informed Neural Network (PINN) technique that co-trains neural networks (NNs) that represent each function in a system of equations to simultaneously solve equations representing an out-of-autoclave (OOA) cure process while conducting optimization in adherence to process requirements. Specifically, this co-training approach benefits from using NNs to represent OOA inputs (air temperature profile) and outputs (part and tool temperature profiles and degree of cure). Production requirements can then be levied on the inputs, such as maximum air temperature and minimum cure cycle, and simultaneously on the outputs, such as degree of cure, maximum part temperature, and part temperature rate limits. The technique is validated with finite element (FE) simulations and physical experiments for curing a Toray T830H-6 K/3900-2D composite panel. Furthermore, this novel approach efficiently models and optimizes the OOA cure process.

Composite curing↗
DOE OSTI2020

FPDeep: Scalable Acceleration of CNN Training on Deeply-Pipelined FPGA Clusters

In this paper, we propose a framework called FPDeep, which uses a hybrid of model and layer paral- lelism to configure distributed reconfigurable clusters to train DNNs. This approach has numerous benefits. First, the design does not suffer from batch size growth. Second, novel workload and weight partitioning leads to balanced loads of both among nodes. And third, the entire system is fine-grained pipeline. This leads to high parallelism and utilization and also minimizes the time features need to be cached while waiting for back-propagation.

Wang, Tianqi↗