Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “TRAINS”

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 667 records · Page 37

Exchange bias training relaxation in spin glass/ferromagnet bilayers

A canonical spin glass (SG) FeAu layer is fabricated to couple to a soft ferromagnet (FM) FeNi layer. Below the SG freezing temperature, exchange bias (EB) and training are observed. Training in SG/FM bilayers is insensitive to cooling field and may suppress the EB or change the sign of the EB field from negative to positive at specific temperatures, violating from the simple power-law or the single exponential function derived from the antiferromagnet based systems. In view of the SG nature, we employ a double decay model to distinguish the contributions from the SG bulk and the SG/FM interface to training. Dynamical properties during training under different cooling fields and at different temperatures are discussed, and the nonzero shifting coefficient in the time index as a signature of slowing-down decay for SG based systems is interpreted by means of a modified Monte Carlo Metropolis algorithm.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

An Entropy-Maximization Approach to Automated Training Set Generation for Interatomic Potentials

Machine learning-based interatomic potentials are currently garnering a lot of attention as they strive to achieve the accuracy of electronic structure methods at the computational cost of empirical potentials. Given their generic functional forms, the transferability of these potentials is highly dependent on the quality of the training set, the generation of which can be highly labor-intensive. Good training sets should at once contain a very diverse set of configurations while avoiding redundancies that incur cost without providing benefits. We formalize these requirements in a local entropy-maximization framework and propose an automated sampling scheme to sample from this objective function. We show that this approach generates much more diverse training sets than unbiased sampling and is competitive with hand-crafted training sets.

74 ATOMIC AND MOLECULAR PHYSICS↗

Ti:sapphire/KrF hybrid laser system generating trains of subterawatt subpicosecond UV pulses

The GARPUN-MTW Ti:sapphire/KrF hybrid laser system is used to investigate different multipass schemes for amplifying trains of ultrashort pulses (USPs) of subpicosecond duration. It is shown that, for an USP repetition period of 3 – 5 ns, which exceeds the gain-medium recovery time (∼2 ns), trains are amplified in the same way as single USPs. Due to this, a train can efficiently extract pump energy from the amplifier and sum energies of individual USPs. The energy of a four-USP train, extracted during four passes through the preamplifier and two passes through the final KrF amplifier (4 + 2 scheme), is saturated at a level of 1.6 J and corresponds to maximum USP peak powers of about 0.6 TW. The energy of amplified spontaneous emission (ASE), on the contrary, rapidly increases at a large total gain length L{sub eff} ≈ 6 m and is approximately equal to the USP energy. In the (4 + 1) and (2 + 2) schemes the USP energy decreases only slightly, to E{sub out} = 1.3 and 1.2 J, and the ASE fraction is reduced to about 10% and 3%, respectively. USP self-focusing leads to multiple laser beam filamentation and a 200-fold local increase in the radiation intensity in filaments, to ∼2 × 10{sup 11} W cm{sup -2}, a level at which the nonlinear loss in the output CaF{sub 2} windows of the KrF amplifier, caused by three-photon absorption, nonlinear scattering, and broadening of the radiation spectrum to a value exceeding the gain band of the KrF laser transition, becomes the main factor determining the saturation of the USP output energy. (lasers)

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DIAGNOSING THE TIME DEPENDENCE OF ACTIVE REGION CORE HEATING FROM THE EMISSION MEASURE. II. NANOFLARE TRAINS

The time dependence of heating in solar active regions can be studied by analyzing the slope of the emission measure distribution coolward of the peak. In a previous study we showed that low-frequency heating can account for 0% to 77% of active region core emission measures. We now turn our attention to heating by a finite succession of impulsive events for which the timescale between events on a single magnetic strand is shorter than the cooling timescale. We refer to this scenario as a 'nanoflare train' and explore a parameter space of heating and coronal loop properties with a hydrodynamic model. Our conclusions are (1) nanoflare trains are consistent with 86% to 100% of observed active region cores when uncertainties in the atomic data are properly accounted for; (2) steeper slopes are found for larger values of the ratio of the train duration {Delta} {sub H} to the post-train cooling and draining timescale {Delta} {sub C}, where {Delta} {sub H} depends on the number of heating events, the event duration and the time interval between successive events ({tau} {sub C}); (3) {tau} {sub C} may be diagnosed from the width of the hot component of the emission measure provided that the temperature bins are much smaller than 0.1 dex; (4) the slope of the emission measure alone is not sufficient to provide information about any timescale associated with heating-the length and density of the heated structure must be measured for {Delta} {sub H} to be uniquely extracted from the ratio {Delta} {sub H}/{Delta} {sub C}.

79 ASTRONOMY AND ASTROPHYSICS↗

PROPAGATION AND DISPERSION OF SAUSAGE WAVE TRAINS IN MAGNETIC FLUX TUBES

A localized perturbation of a magnetic flux tube produces wave trains that disperse as they propagate along the tube, where the extent of dispersion depends on the physical properties of the magnetic structure, on the length of the initial excitation, and on its nature (e.g., transverse or axisymmetric). In Oliver et al. we considered a transverse initial perturbation, whereas the temporal evolution of an axisymmetric one is examined here. In both papers we use a method based on Fourier integrals to solve the initial value problem. We find that the propagating wave train undergoes stronger attenuation for longer axisymmetric (or shorter transverse) perturbations, while the internal to external density ratio has a smaller effect on the attenuation. Moreover, for parameter values typical of coronal loops axisymmetric (transverse) wave trains travel at a speed 0.75–1 (1.2) times the Alfvén speed of the magnetic tube. In both cases, the wave train passage at a fixed position of the magnetic tube gives rise to oscillations with periods of the order of seconds, with axisymmetric disturbances causing more oscillations than transverse ones. To test the detectability of propagating transverse or axisymmetric wave packets in magnetic tubes of the solar atmosphere (e.g., coronal loops, spicules, or prominence threads) a forward modeling of the perturbations must be carried out.

79 ASTRONOMY AND ASTROPHYSICS↗

Empirically-calibrated H100 node power models for accurate AI training energy estimation

Accurately quantifying the energy use of artificial intelligence (AI) training is critical for infrastructure planning, carbon accounting, and sustainable data center operation, but few studies have directly measured the power consumption of production workloads on contemporary hardware. By combining empirical measurements from Brookhaven National Laboratory during AI training on 8-graphics-processing-unit H100 systems with open-source benchmarking data, we develop statistical models relating computational intensity to node-level power consumption. We measure the gap between manufacturer-rated thermal design power (TDP) and actual power demand during AI training. Our analysis reveals that even computationally intensive workloads operate at only 76% of the 10.2 kW TDP rating. Our architecture-specific model, calibrated to floating-point operations, predicts energy consumption with 11.4% mean absolute percentage error, significantly outperforming TDP-based approaches (27%–37% error). We identified distinct power signatures between transformer and convolutional neural network architectures, with transformers showing characteristic fluctuations that may impact grid stability. These results provide a measurement-grounded basis for improving AI training energy estimates, enabling more reliable infrastructure sizing, cost projections, and environmental impact assessments.

Newkirk, Alex C↗

Optimizing a magnitude-limited spectroscopic training sample for photometric classification of supernovae

ABSTRACT In preparation for photometric classification of transients from the Legacy Survey of Space and Time (LSST) we run tests with different training data sets. Using estimates of the depth to which the 4-m Multi-Object Spectroscopic Telescope (4MOST) Time Domain Extragalactic Survey (TiDES) can classify transients, we simulate a magnitude-limited sample reaching rAB ≈ 22.5 mag. We run our simulations with the software snmachine, a photometric classification pipeline using machine learning. The machine-learning algorithms struggle to classify supernovae when the training sample is magnitude limited, in contrast to representative training samples. Classification performance noticeably improves when we combine the magnitude-limited training sample with a simulated realistic sample of faint high-redshift supernovae observed from larger spectroscopic facilities; the algorithms’ range of average area under receiver operator characteristic curve (AUC) scores over 10 runs increases from 0.547–0.628 to 0.946–0.969 and purity of the classified sample reaches 95 per cent in all runs for two of the four algorithms. By creating new, artificial light curves using the augmentation software avocado, we achieve a purity in our classified sample of 95 per cent in all 10 runs performed for all machine-learning algorithms considered. We also reach a highest average AUC score of 0.986 with the artificial neural network algorithm. Having ‘true’ faint supernovae to complement our magnitude-limited sample is a crucial requirement in optimization of a 4MOST spectroscopic sample. However, our results are a proof of concept that augmentation is also necessary to achieve the best classification results.

79 ASTRONOMY AND ASTROPHYSICS↗

Influence of propagation on the coherent accumulation of excitation induced by an ultrashort pulse train

We study the effects of propagation through an extended sample of two- and three-level atoms on the coherent accumulation of excitation by an ultrashort pulse train. In the two-level case, previous pulses in the train may prepare the medium such that a later pulse may experience amplification and absorption in different positions inside the sample. For a large number of pulses, the atomic medium may be saturated by the train, and some pulses propagate without experiencing either absorption or amplification. In general, absorption of the resonant pulse frequency during propagation compromises the accumulation efficiency. In the three-level case, the coherent accumulation of excitation leads to electromagnetically induced transparency of the pulse train, and the pulses exit the medium without any distortion in their temporal profile.

74 ATOMIC AND MOLECULAR PHYSICS↗

Generation of shock trains in free liquid jets with a nanosecond green laser

Shock wave trains in liquid jets were previously generated only by ablation with femtosecond x-ray lasers. Here we show that shock trains in water microjets can be also generated using nanosecond green laser pulses with 1- to 10-mJ energy. Furthermore, the ablation of 15-, 20-, 30-, and 70-μm water microjets opened a gap in the jets and launched an initial shock wave. Fully developed shock trains were observed in the 30- and 70-μm jets up to 250-ns delays, and these trains were also transmitted inside the nozzles. A few tens of nanoseconds after the pulse, the shock dynamics and its pressure became similar to the ones generated by x-ray lasers, with a more rapid pressure decay in thinner jets. At time delays exceeding 100 ns in the 30-μm jets, the leading shock pressure stabilized to an approximately constant pressure of 40 MPa. The energy density deposited in the jets was estimated at 30 MJ/cm 3 by comparing the jet gaps in the green and x-ray laser experiments, and matched previous estimates for optical ablation in water. Here, the pressure decay in the 30-μm jets was modeled based on the pressure decay observed in x-ray laser experiments.

74 ATOMIC AND MOLECULAR PHYSICS↗

Microstructural and rheological training and memory of nanocolloidal soft glasses under cyclic shear

An intrinsic feature of disordered and out-of-equilibrium materials, such as glasses, is the dependence of their properties on their history. An important example is rheological memory, in which disordered solids obtain properties based on their deformation history. Here, in this study, we employ x-ray photon correlation spectroscopy with in situ rheometry to characterize memory formation in a nanocolloidal soft glass due to cyclic shear. During a cycle, particles undergo irreversible displacements composed of a combination of shear-induced diffusion and heterogeneous, residual strain fields. At lower shear amplitudes, the displacements resemble a random walk in which the directions in each cycle are independent of those in preceding cycles, while at high amplitude, the irreversible displacements in consecutive cycles become correlated. The magnitudes of the displacements decrease with each cycle before reaching a steady state where the microstructure has been trained to achieve enhanced reversibility even at shear amplitudes well above yielding and despite the presence of thermal fluctuations. At amplitudes below and near yielding, these decreases are monotonic, while well above yielding, they are nonmonotonic, suggesting evidence of shear banding. Accompanying this microstructural training are corresponding decreases in the dissipation during each cycle and the magnitude of the residual stress toward steady-state values. Memory of the training is revealed by measurements in which the amplitude of the shear is changed after steady state is reached. The magnitude of the particle displacements, as well as the dissipation and the change in residual stress, vary nonmonotonically with the new shear amplitude, having minima near the training amplitude, thereby revealing correlated microscopic and macroscopic signatures of memory.

Chen, Yihao [Johns Hopkins Univ., Baltimore, MD (U↗

Single-Net Continual Learning with Progressive Segmented Training

There is an increasing need of continual learning in dynamic systems, such as the self-driving vehicle, the surveillance drone, and the robotic system. Such a system requires learning from the data stream, training the model to preserve previous information and adapt to a new task, and generating a single-headed vector for future inference. Different from previous approaches with dynamic structures, this work focuses on a single network and model segmentation to prevent catastrophic forgetting. Leveraging the redundant capacity of a single network, model parameters for each task are separated into two groups: one important group which is frozen to preserve current knowledge, and secondary group to be saved (not pruned) for a future learning. A fixed-size memory containing a small amount of previously seen data is further adopted to assist the training. Without additional regularization, the simple yet effective approach of Progressive Segmented Training (PST) successfully incorporates multiple tasks and achieves the state-of-the-art accuracy in the single-head evaluation on CIFAR-10 and CIFAR-100 datasets. Moreover, the segmented training significantly improves computation efficiency in continual learning at the edge.

Du, Xiaocong↗

Elastic distributed training with fast convergence and efficient resource utilization

Distributed learning is now routinely conducted on cloud as well as dedicated clusters. Training with elastic resources brings new challenges and design choices. Prior studies focus on runtime performance and assume a static algorithmic behavior. In this work, by analyzing the impact of of resource scaling on convergence, we introduce schedules for synchronous stochastic gradient descent that proactively adapt the number of learners to reduce training time and improve convergence. Our approach no longer assumes a constant number of processors throughout training. In our experiment, distributed stochastic gradient descent with dynamic schedules and reduction momentum achieves better convergence and significant speedups over prior static ones. Numerous distributed training jobs running on cloud may benefit from our approach.

Cong, Guojing↗

Accelerated Over-The-Air Neural Receiver Training Using Self-Contrastive Learning

Self-contrastive learning (SCL), a self-supervised learning method, has been shown to improve image and signal classifier accuracies and reduce the training time for neural communications receivers. In particular, prior work has shown that SCL applied as a pre-training step can improve simulated performance of OFDM in 3GPP TDL channel models by reducing the training time of the downstream classification task (demodulation and demapping). In this work a practical implementation demonstrating SCL pre-training using software defined radios (SDRs) is proposed.

Cooke, Corey [ORNL] (ORCID:0000000234263672)↗

Effect of CLIQ on Training of HL-LHC Quadrupole Magnets

The high-luminosity LHC upgrade requires stronger than LHC low-beta quadrupole magnets to reach the luminosity goals of the project. The project is well advanced and HL-LHC quadrupole magnets are currently being commissioned in US Labs (MQXFA magnets) and CERN (MQXFB magnets). Those are the first Nb 3 Sn magnets to be used in any large particle accelerator. At development stages, many Nb 3 Sn accelerator sub-scale models showed relatively slow training and MQXFA magnets were projected to have low tens of quenches before reaching operational field. Recently it was shown that dedicated capacitor-based de-vices can affect Nb 3 Sn magnet training, and it was suggested that CLIQ, a capacitor-based device intended for quench protection, can do too. Here, the present paper investigates effects on training likely induced by CLIQ, using the base fact that only half the coils in a quadrupole experience upward current modulation at quench because of capacitor discharge. The study encompasses all MQXFA production magnets trained at BNL to date. No other high-statistics data from identical magnets (series) with CLIQ protection exist so far. Implications and opportunities stemming from data analysis are discussed and conclusions drawn.

43 PARTICLE ACCELERATORS↗

SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks

Going deeper and wider in neural architectures improves their accuracy, while the limited GPU DRAM places an undesired restriction on the network design domain. Deep Learning (DL) practitioners either need to change to less de- sired network architectures, or nontrivially dissect a network across multiGPUs. These distract DL practitioners from concentrating on their original machine learning tasks. We present SuperNeurons: a dynamic GPU memory scheduling runtime to enable the network training far beyond the GPU DRAM capacity. SuperNeurons features 3 memory optimizations, Liveness Analysis, Unified Tensor Pool, and Cost-Aware Recomputation; together they effectively reduce the network-wide peak memory usage down to the maximal memory usage among layers. We also address the performance issues in these memory-saving techniques. Given the limited GPU DRAM, SuperNeurons not only provisions the necessary memory for the training, but also dynamically allocates the memory for convolution workspaces to achieve the high performance. Evaluations against Caffe, Torch, MXNet and TensorFlow have demonstrated that SuperNeurons trains at least 3.2432 deeper network than current ones with the leading performance. Particularly, SuperNeurons can train ResNet2500 that has 104 basic network layers on a 12GB K40c.

Wang, Linnan↗

Swap Path Network for Robust Person Search Pre-training

This code corresponds to the WACV25 conference paper, "Swap Path Network for Robust Person Search Pre-training". In that paper, we introduce a new model for the person search task called the Swap Path Net (SPNet). The person search task is a problem in computer vision, where we locate and rank matches to an image of a query person in a set of other images where we want to find them. We also introduce a novel pre-training algorithm specific to the Swap Path Net architecture. The code implements pre-training and fine-tuning of the Swap Path Net (SPNet). This includes ingesting image datasets and updating the weights of the SPNet neural network to train it for the person search task. The repository contains code, configs, and instructions to reproduce all results from the paper.

Jaffe, LucasW [Lawrence Livermore National Laborat↗

Skip-Connected Self-Recurrent Spiking Neural Networks with Joint Intrinsic Parameter and Synaptic Weight Training

As an important class of spiking neural networks (SNNs), recurrent spiking neural networks (RSNNs) possess great computational power and have been widely used for processing sequential data like audio and text. However, most RSNNs suffer from two problems. 1. Due to the lack of architectural guidance, random recurrent connectivity is often adopted, which does not guarantee good performance. 2. Training of RSNNs is in general challenging, bottlenecking achievable model accuracy. To address these problems, we propose a new type of RSNNs called Skip-Connected Self-Recurrent SNNs (ScSr-SNNs). Recurrence in ScSr-SNNs is introduced in a stereotyped manner by adding self-recurrent connections to spiking neurons. The SNNs with self-recurrent connections can realize recurrent behaviors similar to those of more complex RSNNs while the error gradients can be more straightforwardly calculated due to the mostly feedforward nature of the network. The network dynamics is enriched by skip connections between nonadjacent layers. Moreover, we propose a new backpropagation (BP) method called backpropagated intrinsic plasticity (BIP) to further boost the performance of ScSr-SNNs by training intrinsic model parameters. Unlike standard intrinsic plasticity rules that adjust the neuron's intrinsic parameters according to neuronal activity, the proposed BIP method optimizes intrinsic parameters based on the backpropagated error gradient of a well-defined global loss function in addition to synaptic weight training. Here, based on challenging speech, neuromorphic speech, and neuromorphic image datasets, the proposed ScSr-SNNs can boost performance by up to 2.85% compared with other types of RSNNs trained by state-of-the-art BP methods.

97 MATHEMATICS AND COMPUTING↗

A train-the-trainer education and promotion program: chronic fatigue syndrome – a diagnostic and management challenge

Background: Chronic fatigue syndrome (CFS) is a complicated illness for providers and patients. Fewer than 20% of persons with CFS have been diagnosed and treated. For providers, compounding the issue are the challenges in making a diagnosis due to the lack of a biomedical marker. Methods: The objective of the CFS diagnosis and management curriculum was to instruct core trainers as to the evaluation, diagnosis, and management of CFS. Over a two year period, 79 primary care physicians, physician assistants, and nurse practitioners from diverse regions in the U.S. participated as core trainers in a two day Train-the-Trainer (TTT) workshop. As core trainers, the workshop participants were expected to show increases in knowledge, self-efficacy, and management skills with the primary goal of conducting secondary presentations. Results: The optimal goal for each core trainer to present secondary training to 50 persons in the health care field was not reached. However, the combined core trainer group successfully reached 2064 primary care providers. Eighty-two percent of core trainers responded "Very good" or "Excellent" in a post-tessurvey of self-efficacy expectation and CFS diagnosis. Data from the Chicago workshops showed significant improvement on the Primary Care Opinion Survey (p < 0.01) and on the Relevance and Responsibility Factors of the CAT survey (p = 0.03 and p = 0.04, respectively). Dallas workshop data show a significant change from pre- to post-test scores on the CFS Knowledge test (p = 0.001). Qualitative and process evaluation data revealed that target audience and administrative barriers impacted secondary training feasibility. Conclusion: Data show the workshop was successful in meeting the objectives of increasing CFS knowledge and raising perceived self-efficacy towards making a diagnosis. The CFS TTT program informed an educational provider project by shifting the format for physicians to grand rounds and continuing medical education design while retaining TTT aspects for nurse practitioners and physicians assistants. Evaluations also indicate that secondary trainings may be more readily employed and accepted if administrative barriers are addressed early in the planning phases.

59 BASIC BIOLOGICAL SCIENCES↗