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 811 records · Page 45

Helmet-Mounted Display Technology for Eva Training in NASA's Neutral Buoyancy Lab

Currently, during extravehicular activity (EVA) on the International Space Station (ISS), astronauts are in constant communication with mission control; however, this paradigm will significantly change during future NASA exploration missions due to limited and time-delayed communications. As exploration missions will thereby require an increase in crew autonomy, it is hypothesized that heads-up display (HUD) technology can supplement communications with mission control. Before introducing novel display technology to EVA operations, it must first be demonstrated and evaluated in an EVA training environment. The UC Davis Center for Spaceflight Research, in collaboration with NASA Johnson Space Center’s Human Physiology, Performance, Protection, and Operations (H-3PO) Lab has developed a low-cost and rapid development helmet-mounted display (HMD) for EVA training at NASA’s Neutral Buoyancy Lab (NBL). The first two phases of HMD testing (Phase I and II) at the NBL focused on technology and capability development and demonstration. Crew member feedback was obtained that evaluated aspects of HMD including its user satisfaction, visibility, readability, and usefulness. Overall, feedback indicated HMD was readable, un-obtrusive, and the available display modes had potential to be useful and enhance EVA training. HMD display modes currently available include: real-time biofeedback (metabolic rate), phase elapsed time (PET), ability to set timers, task procedural aids (e.g. Pistol Grip Tool settings) and custom messages. The goal for Phase III, which is currently underway, is to evaluate the effects that access to bioinformatics through HMD has on astronaut training and performance at the NBL. For this phase of testing, crewmembers will be asked to perform a go/no-go task while wearing HMD throughout the NBL run to characterize crew member state of situational awareness with respect to HMD. This information could be used to inform how best to display relatively important or supplemental, but not critical, data in the future.

Heads up display↗

Development of the Suited Injury Modes and Effects Analysis for Identification of Top Injury Risks in Lunar Missions and Training

A new Exploration Extravehicular Activity Suit (xEVAS) is being designed to replace the current Extravehicular Mobility Unit (EMU) for the National Aeronautics and Space Administration’s (NASA’s) Artemis program to return astronauts to the lunar surface. This new suit will allow for increased range of motion compared the current EMU and Apollo era suits and will have additional features that will enhance the health and safety of exploration. With the design of lunar missions and the xEVAS progressing, it is important to consider possible injuries and injury mechanisms that could occur in the suit. To address these concerns, the suited Injury Modes and Effects Analysis (IMEA) was developed to outline suited injury scenarios and rank them based on risk score. The IMEA documents possible scenarios and underlying mechanisms of injury while wearing an extravehicular activity (EVA) suit. Tasks during lunar surface EVA as well as training events to prepare for lunar missions were considered as history has shown that more suit injuries occur during training than in flight. Each scenario is ranked with a consequence and likelihood scoring based on our current understanding of the suit and Artemis design reference missions to identify high-risk cases that will drive further work in suited injury. Injuries, mechanisms of injury, and mitigation strategies are evaluated within each scenario. The Suited Injury Summit was held on January 5, 2022, to vet the IMEA with external experts. This was an all-day virtual meeting with the suited injury team, ergonomists, suit engineers, safety engineers, the flight operations directorate, flight doctors, astronauts, astronaut strength, conditioning, and rehabilitation specialists (ASCRS), and external subject matter experts (SMEs). External SMEs consisted of surgeons with varying specialties. The intent of this meeting was to walk through the top injury risks identified in the analysis, identify any gaps that were not captured, and discuss mitigations. With participation from all groups, countless lessons-learned came from the Summit meeting. Using the lessons-learned and discussion from the Summit, the top 10 risks have been identified: neutral buoyancy laboratory training, hand/glove injuries, poor suit fit, field training, specific EVA tasks/design of task, boots/ankle injuries, falls from heights, background radiation, repetitive contact, and ambulation/long-distance ambulation. Mitigation steps have also been determined for each of the top risks. The IMEA and documentation of top risks is a living document. Yearly meetings are planned to update the analysis and reevaluate top risks and mitigations. The IMEA is being used to drive work in suited injury, and this work will continue to evolve with IMEA and lunar mission updates.

Teresa Reiber↗

Feasibility Study of a Multi Tilt-rotor Aircraft as the Artemis Lunar Training Vehicle

The Lunar Landing Research Vehicles (LLRVs) and the Lunar Landing Training Vehicles (LLTVs) provided astronaut candidates for the Apollo program with essential experience and confidence required to complete the missions, and contributed to six successful manned landings on the moon. The primary challenge in terrestrial training was being able to replicate the ratio of bank angle to linear acceleration that a pilot would experience in lunar gravity. Presently, as the Artemis program seeks to return humans to the Moon by 2025, engineers are evaluating suitable platforms to serve as an In-Flight Trainer (IFT) or Artemis Lunar Training Vehicle (ALTV) for astronauts training in the task of manual landing. The program is investigating the viability of current technology in the field of electric vertical takeoff and landing (eVTOL) vehicles and is evaluating using a multi tilt-rotor aircraft platform as a candidate platform for a preliminary ALTV. The tilt-rotor capability enables the vehicle attitude to be decoupled from its flight path, which is a crucial requirement in realistically simulating lunar gravity on Earth. Other key considerations include compensating for a lack of aerodynamic forces while flying through the atmosphere of Earth, as well as the ability to simulate the dynamics of multiple different lander designs for the Human Landing System (HLS) program. This paper details the feasibility study and presents a preliminary flight control architecture for an IFT based on a notional multi tilt-rotor platform. The modeling-following control law, based on nonlinear dynamic inversion (NDI), removes the need for gain scheduling because the vehicle operates across a wide range of flight conditions. The inner-loop dynamic control allocation strategy consists of a static portion that is optimized offline for trim while compensating for the difference in gravity and a dynamic portion that is computed in real time. The reference model consists of the full closed-loop dynamics of a generic HLS design. The modularity of the flight control architecture enables evaluation of multiple HLS concepts with minimal modifications to the control law. Simulation results of the multi tilt-rotor configuration following the final portion of the Apollo 11 descent trajectory are shown.

Jing Pei↗

Feasibility Study of a Multi-Tilt-Rotor Aircraft as the Artemis Lunar Training Vehicle

The Lunar Landing Research Vehicles (LLRVs) and the Lunar Landing Training Vehicles (LLTVs) provided astronauts of the Apollo program with essential experience and confidence required to complete the missions, and contributed to six successful manned landings on the moon. The primary challenge in terrestrial training was being able to replicate the ratio of tilt angle to linear acceleration that a pilot would experience in lunar gravity. Presently, as the Artemis program seeks to return humans to the Moon by 2025, engineers are evaluating suitable platforms to serve as an In-Flight Trainer (IFT) or Artemis Lunar Training Vehicle (ALTV) for astronauts training in the task of manual landing. The program is investigating the viability of current technology in the field of electric vertical takeoff and landing (eVTOL) vehicles and is evaluating using a multi-tilt-rotor aircraft platform as a candidate for a preliminary ALTV. The tilt-rotor capability enables the vehicle attitude to be decoupled from its flight path, which is a crucial requirement in realistically simulating lunar gravity on Earth. Other key considerations include compensating for a lack of aerodynamic forces while flying through the atmosphere of Earth, as well as the ability to simulate the dynamics of multiple different lander designs for the Human Landing System (HLS) program. This paper details the feasibility study and presents a preliminary flight control architecture for an IFT based on a notional multi-tilt-rotor platform. The model-following control law, based on nonlinear dynamic inversion (NDI), removes the need for gain scheduling. The inner-loop dynamic control allocation strategy consists of a static portion that is optimized offline for trim while compensating for the difference in gravity and a dynamic portion that is computed in real time. The reference model consists of the full closed-loop dynamics of a generic HLS design. The modularity of the flight control architecture enables evaluation of multiple HLS concepts with minimal modifications to the control law. Simulation results of the multi-tilt-rotor configuration following the final portion of the Apollo 11 descent trajectory are shown.

Jing Pei↗

Development of the Suited Injury Modes and Effects Analysis for Identification of Top Injury Risks in Lunar Missions and Training

A new Exploration Extravehicular Activity Suit (xEVAS) is being designed to replace the current Extravehicular Mobility Unit (EMU) for the National Aeronautics and Space Administration’s (NASA’s) Artemis program to return astronauts to the lunar surface. This new suit will allow for increased range of motion compared the current EMU and Apollo era suits and will have additional features that will enhance the health and safety of exploration. With the design of lunar missions and the xEVAS progressing, it is important to consider possible injuries and injury mechanisms that could occur in the suit. To address these concerns, the suited Injury Modes and Effects Analysis (IMEA) was developed to outline suited injury scenarios and rank them based on risk score. The IMEA documents possible scenarios and underlying mechanisms of injury while wearing an extravehicular activity (EVA) suit. Tasks during lunar surface EVA as well as training events to prepare for lunar missions were considered as history has shown that more suit injuries occur during training than in flight. Each scenario is ranked with a consequence and likelihood scoring based on our current understanding of the suit and Artemis design reference missions to identify high-risk cases that will drive further work in suited injury. Injuries, mechanisms of injury, and mitigation strategies are evaluated within each scenario. The Suited Injury Summit was held on January 5, 2022, to vet the IMEA with external experts. This was an all-day virtual meeting with the suited injury team, ergonomists, suit engineers, safety engineers, the flight operations directorate, flight doctors, astronauts, astronaut strength, conditioning, and rehabilitation specialists (ASCRS), and external subject matter experts (SMEs). External SMEs consisted of surgeons with varying specialties. The intent of this meeting was to walk through the top injury risks identified in the analysis, identify any gaps that were not captured, and discuss mitigations. With participation from all groups, countless lessons-learned came from the Summit meeting. Using the lessons-learned and discussion from the Summit, the top 10 risks have been identified: neutral buoyancy laboratory training, hand/glove injuries, poor suit fit, field training, specific EVA tasks/design of task, boots/ankle injuries, falls from heights, background radiation, repetitive contact, and ambulation/long-distance ambulation. Mitigation steps have also been determined for each of the top risks. The IMEA and documentation of top risks is a living document. Yearly meetings are planned to update the analysis and reevaluate top risks and mitigations. The IMEA is being used to drive work in suited injury, and this work will continue to evolve with IMEA and lunar mission updates.

Tessa Reiber↗

Artificial Neural Network (ANN) Surface Longwave and Shortwave Fluxes Trained on CERES Observations

The Clouds and Earth’s Radiant Energy System (CERES) project provides satellite-based observations of the radiative fluxes and clouds systems. CERES climate quality data products typically take several months of calibration and validation before release to the public. The Fast Longwave and Shortwave Radiative Flux (FLASHFlux) data product was developed to provide key data for the applied sciences and educational users within a week of observation. FLASHFlux achieves this by using simplified calibration, an operational meteorological product from Global Modeling and Assimilation Office (GMAO), and its own surface parameterizations model. The CERES FLASHFlux provides two data products: 1) an hourly Level 2 Single Scanner Footprint (SSF) data separately for Terra and NOAA-20 observations, and 2) a daily Level 3 Time Interpolated and Spatially Averaged (TISA) 1o x 1o gridded data that combines Terra and NOAA-20 observations. Currently, FLASHFlux uses the Langley Parameterized Shortwave Algorithm (LPSA) and Langley Parameterized Longwave Algorithm (LPLA) to derive its surface fluxes (Kratz et al., 2010; Gupta et al, 2001). A new Machine Learning (ML) based approach using Artificial Neural Networks to derive Surface Longwave (LW) & Shortwave (SW) fluxes based on training data from the CERES Clouds Radiative Swath (CRS) product is being investigated to replace LPSA and LPLA in the SSF surface flux products. One of the biggest hurdles in training ML model is model fitting. To overcome the problem of overfitting we use feature engineering that helps in finding the important feature and remove features that are irrelevant to the model. In our training we employed the Leave-One-Feature-Out Importance (LOFO) to evaluate the significance of each feature in our training. We intercompare ANN fluxes against surface fluxes produced from the Fu-Liou model in CRS and the LPSA/LPLA in FLASHFlux SSF. Furthermore, we validated ANN derived fluxes to the Baseline Surface Radiation Network (BSRN).

P C Sawaengphokhai↗

An experimental comparison of triggered and random pulse train uncertainties

In this paper we present an experimental comparison of signal-triggered and randomly triggered based analysis algorithms of neutron multiplicity data. Traditional shift register type signal-triggered multiplicity analysis of singles, doubles and triples rates is compared with analysis using randomly triggered gates. Two methods of random gate generation are explored - non-overlapping gates (Feyrunan approach) and periodic overlapping gates (fast accidentals). Using californium sources with low, medium and high rate in combination with AmLi sources (as a surrogate for plutonium) we investigate relative standard deviation (RSD) of data in order to determine if there are parameter spaces in which one of the measurement methods should be preferred. Neutron correlation analysis is a commonly used NDA technique to assay plutonium mass. The data can be collected in two distinct ways: using signal-triggered or randomly triggered counting gates. Analysis algorithms were developed for both approaches to determine singles (S), doubles (D) and triples (7) rates from the measured sample. Currently the most commonly implemented technique to collect neutron coincidence data utilizes shift register based electronics. Shift register uses signal-triggered counting gates to generate foreground multiplicity distribution of correlated+accidental events and a random gate (opened after a predefined long delay following the signal trigger) to generate background multiplicity distribution of accidental events. Modern shift registers include fast accidental option to sample data with a fixed clock frequency. This way a set of overlapping gates is used to generate background multiplicity distributions in order to improve the measurement precision. In parallel to shift register approach the Feynman variance technique is frequently used, which utilizes set of consecutive non-overlapping gates. In general, different user communities (e.g. safeguards, nuclear material accountancy, emergency response) have used only one of the two analysis methods for the nuclear material assay. The aim of this study is to provide a systematic comparison of the precision of the measured S, D, T rates and {sup 240}Pu effective mass obtained using the above mentioned pulse train sampling techniques. In order to perform this task, a LANL developed list mode based data acquisition system is used, where the entire pulse train is recorded and subsequently analyzed. The list mode acquisition brings an essential advantage for this type of comparison, since the very same pulse train can be analyzed using signal-triggered as well as randomly triggered counting gates. The aim of this study is not only to compare the precision of signal-triggered versus random triggered sampling techniques, but also to investigate the influence of fast accidental sampling on the precision of signal-triggered results. In addition the different random sampling techniques used in safeguards are investigated. For this purpose we implement two types of random sampling - non-overlapping gates (Feynrnan approach) and periodic overlapping gates (fast accidentals). In the following sections the equations utilized in the pulse train analysis are described, experimental setup and measurement techniques are discussed and finally the results are summarized and discussed.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

Using an operator training simulator in the undergraduate chemical engineering curriculim

An operator training simulator (OTS) is to the chemical engineer what a flight simulator is to the aerospace engineer. The basis of an OTS is a high-fidelity dynamic model of a chemical process that allows an engineer to simulate start-up, shut-down, and normal operation. It can also be used to test the skill and ability of an engineer or operator to respond and control some unforeseen situation(s) through the use of programmed malfunctions. West Virginia University (WVU) is a member of the National Energy Technology Laboratory’s Regional University Alliance (NETL-RUA). Working through the NETL-RUA, the authors have spent the last four years collaborating on the development of a high-fidelity OTS for an Integrated Gasification Combined Cycle (IGCC) power plant with CO{sub 2} capture that is the cornerstone of the AVESTARTM (Advanced Virtual Energy Simulation Training And Research) Center with sister facilities at NETL and WVU in Morgantown, WV. This OTS is capable of real-time dynamic simulation of IGCC plant operation, including start-up, shut-down, and power demand load following. The dynamic simulator and its human machine interfaces (HMIs) are based on the DYNSIM and InTouch software, respectively, from Invensys Operations Management. The purpose of this presentation is to discuss the authors’ experiences in using this sophisticated dynamic simulation-based OTS as a hands-on teaching tool in the undergraduate chemical engineering curriculum. At present, the OTS has been used in two separate courses: a new process simulation course and a traditional process control course. In the process simulation course, concepts of steady-state and dynamic simulations were covered prior to exposing the students to the OTS. Moreover, digital logic and the concept of equipment requiring one or more permissive states to be enabled prior to successful operation were also covered. Students were briefed about start-up procedures and the importance of following a predetermined sequence of actions in order to start-up the plant successfully. Student experience with the dynamic simulator consisted of a six-hour training session in which the Claus sulfur capture unit of the IGCC plant was started up. The students were able to operate the simulator through the InTouch-based HMI displays and study and understand the underlying dynamic modeling approach used in the DYNSIM-based simulator. The concepts learned during the training sessions were further reinforced when students developed their own DYNSIM models for a chemical process and wrote a detailed start-up procedure. In the process control course, students learned how the plant responds dynamically to changes in the manipulated inputs, as well as how the control system impacts plant performance, stability, robustness and disturbance rejection characteristics. The OTS provided the opportunity to study the dynamics of complicated, “real-life” process plants consisting of hundreds of pieces of equipment. Students implemented ideal forcing functions, tracked the time-delay through the entire plant, studied the response of open-loop unstable systems, and learned “good practices” in control system design by taking into account the real-world events where significant deviations from the “ideal” or “expected” response can occur. The theory of closed-loop stability was reinforced by implementing limiting proportional gain for stability limits of real plants. Finally, students were divided into several groups where each group was tasked to control a section of the plant within a set of operating limits in the face of disturbances and simulated process faults. At the end of this test, they suggested ways to improve the control system performance based on the theory they learned in class and the hands-on experience they earned while working on the OTS.

97 MATHEMATICS AND COMPUTING↗

Method for training honeybees to respond to olfactory stimuli and enhancement of memory retention therein

A specialized conditioning protocol for honeybees that is designed for use within a complex agricultural ecosystem. This method ensures that the conditioned bees will be less likely to exhibit a conditioned response to uninfected plants, a false positive response that would render such a biological sensor unreliable for agricultural decision support. Also described is a superboosting training regime that allows training without the aid of expensive equipment and protocols for training in out in the field. Also described is a memory enhancing cocktail that aids in long term memory retention of a vapor signature. This allows the bees to be used in the field for longer durations and with fewer bees trained overall.

59 BASIC BIOLOGICAL SCIENCES↗

Industrial Energy Training and Certification

Compressed air systems, ammonia refrigeration systems, chilled water systems, steam systems, process heating systems, combined heat and power systems, pump systems and fan systems are major industrial energy systems commonly found in manufacturing facilities. Efficiency of these systems contributes significantly to whole facilities' energy performance. On the national, even international level, well-structured training and highly recognized certification programs help develop a highly-skilled and qualified workforce to maintain and improve facilities' energy performance, particularly as technologies within these systems become more advanced. The purpose of this paper is to review currently available training and certification programs focusing on these systems and to identify the gap between market's needs and currently available programs. Three major conclusions are: first, most training programs focus on operations, maintenance, safety and design although some briefly touch the energy performance aspect; second, except CRES by RETA and PSA Certificate and PSAP Master Certification by HI, no other certifications had been found emphasizing on knowledge and skills for improving and maintaining these systems' energy performance; third, developing energy efficiency focused training and ANSI accredited certification programs on these energy systems will fill the gap between market's needs and currently available programs.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Industrial Energy Training and Certification

We present compressed air systems, ammonia refrigeration systems, chilled water systems, steam systems, process heating systems, combined heat and power systems, pump systems and fan systems are major industrial energy systems commonly found in manufacturing facilities. Efficiency of these systems contributes significantly to whole facilities' energy performance. On the national, even international level, well-structured training and highly recognized certification programs help develop a highly-skilled and qualified workforce to maintain and improve facilities' energy performance, particularly as technologies within these systems become more advanced. The purpose of this paper is to review currently available training and certification programs focusing on these systems and to identify the gap between market's needs and currently available programs. Three major conclusions are: first, most training programs focus on operations, maintenance, safety and design although some briefly touch the energy performance aspect; second, except CRES by RETA and PSA Certificate and PSAP Master Certification by HI, no other certifications had been found emphasizing on knowledge and skills for improving and maintaining these systems' energy performance; third, developing energy efficiency focused training and ANSI accredited certification programs on these energy systems will fill the gap between market's needs and currently available programs.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

US DOE In-Plant Trainings to Develop Expertise and Replicate Success

In-Plant Trainings (INPLTs) offered by the US Department of Energy Better Buildings, Better Plants (Better Plants) program are multi-day workshops performed by industry-recognized experts. INPLTs include both classroom- and field-based sessions that train attendees to identify energy conservation opportunities, quantify savings from these opportunities, and implement projects to realize the savings. These training workshops enhance the attendees’ understanding of working principles, knowledge of best practices, and capability to analyze the energy performance of industrial energy systems. INPLTs are competitively awarded and focus on a wide range of topics, including traditional industrial systems such as steam, process heating and motor-driven systems, and processes such as energy treasure hunts and municipal water and wastewater treatment. Partners that are awarded INPLTs can invite external stakeholders, such as employees of other manufacturers, utility representatives, and vendors. The Better Plants program had delivered 123 INPLTs as of spring 2019, trained more than 2,000 participants, and identified more than $37 million in energy cost savings. This paper provides an overview of INPLTs, some key statistics, the top identified energy savings opportunities, and success stories from INPLTs delivered from 2011 to 2018. Finally, the vision for future INPLTs is discussed based on participants’ feedback and the long-term and strategic goals of the Better Plants program.

Guo, Wei↗

Accelerating Collective Communication in Data Parallel Training across Deep Learning Frameworks

This work develops new techniques within Horovod, a generic communication library supporting data parallel training across deep learning frameworks. In particular, we improve the Horovod control plane by implementing a new coordination scheme that takes advantage of the characteristics of the typical data parallel training paradigm, namely the repeated execution of collectives on the gradients of a fixed set of tensors. Using a caching strategy, we execute Horovod’s existing coordinator-worker logic only once during a typical training run, replacing it with a more efficient decentralized orchestration strategy using the cached data and a global intersection of a bitvector for the remaining training duration. Next, we introduce a feature for end users to explicitly group collective operations, enabling finer grained control over the communication buffer sizes. To evaluate our proposed strategies, we conduct experiments on a world-class supercomputer — Summit. We compare our proposals to Horovod’s original design and observe 2x performance improvement at a scale of 6000 GPUs; we also compare them against tf.distribute and torch.DDP and achieve 12% better and comparable performance, respectively, using up to 1536 GPUs; we compare our solution against BytePS in typical HPC settings and achieve about 20% better performance on a scale of 768 GPUs. Finally, we test our strategies on a scientific application (STEMDL) using up to 27,600 GPUs (the entire Summit) and show that we achieve a near-linear scaling of 0.93 with a sustained performance of 1.54 exaflops (with standard error +- 0.02) in FP16 precision.

Romero, Joshua↗

Stable Parallel Training of Wasserstein Conditional Generative Adversarial Neural Networks : *Full/Regular Research Paper submission for the symposium CSCI-ISAI: Artificial Intelligence

We use a stable parallel approach to train Wasserstein Conditional Generative Adversarial Neural Networks (W-CGANs). The parallel training reduces the risk of mode collapse and enhances scalability by using multiple generators that are concurrently trained, each one of them focusing on a single data label. The use of the Wasserstein metric reduces the risk of cycling by stabilizing the training of each generator. We apply the approach on the CIFAR10 and the CIFAR100 datasets, two standard benchmark datasets with images of the same resolution, but different number of classes. Performance is assessed using the inception score, the Fréchet inception distance, and image quality. An improvement in inception score and Fréchet inception distance is shown in comparison to previous results obtained by performing the parallel approach on deep convolutional conditional generative adversarial neural networks (DC-CGANs). Weak scaling is attained on both datasets using up to 100 NVIDIA V100 GPUs on the OLCF supercomputer Summit.

Lupo Pasini, Massimiliano↗

Geometry-aware training of factorized layers in tensor Tucker format

Reducing parameter redundancies in neural network architectures is crucial for achieving feasible computational and memory requirements during train and inference of large networks. Given its easy implementation and flexibility, one promising approach is layer factorization, which reshapes weight tensors into a matrix format and parameterizes it as the product of two rank-r matrices. However, this family of approaches often requires an initial full-model warm-up phase, prior knowledge of a feasible rank, and it is sensitive to parameter initialization.In this work, we introduce a novel approach to train the factors of a Tucker decomposition of the weight tensors. Our training proposal proves to be optimal in locally approximating the original unfactorized dynamics and stable for the initialization. Furthermore, the rank of each mode is dynamically updated during training.We provide a theoretical analysis of the algorithm, showing convergence, approximation and local descent guarantees. The method's performance is further illustrated through a variety of experiments, showing remarkable training compression rates and comparable or even better performance than the full baseline and alternative layer factorization strategies.

Zangrando, Emanuele [Gran Sasso Science Institute ↗

Teaching And Training Tools For The Undergraduate: Experience With A Rebuilt AN-400 Accelerator

There is an increasingly recognized need for people trained in a broad range of applied nuclear science techniques, indicated by reports from the American Physical Society and elsewhere. Anecdotal evidence suggests that opportunities for hands-on training with small particle accelerators have diminished in the US, as development programs established in the 1960's and 1970's have been decommissioned over recent decades. Despite the reduced interest in the use of low energy accelerators in fundamental research, these machines can offer a powerful platform for bringing unique training opportunities to the undergraduate curriculum in nuclear physics, engineering and technology. We report here on the new MSU Applied Nuclear Science Lab, centered around the rebuild of an AN400 electrostatic accelerator. This machine is run entirely by undergraduate students under faculty supervision, allowing a great deal of freedom in its use without restrictions from graduate or external project demands.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Developing Subgrantee Administrative Training for the Weatherization Assistance Program

During Fiscal Years (FY) 2019 and 2020, the National Renewable Energy Laboratory (NREL) developed a series of online trainings for the U.S. Department of Energy (DOE) Weatherization Assistance Program (WAP) to support Subgrantee administrative professionals. NREL and its subcontractor developed a series of online administrative trainings for WAP Subgrantees. In total, 29 administrative training courses were developed for WAP Subgrantees, focused on the following job roles: Weatherization Director, Fiscal Manage, Quality Assurance Manager. As of September 8, 2020, 2,840 users in nearly all WAP Grantee jurisdictions had registered with the learning management system and completed over 23,000 courses. This report provides a summary of the development process, rollout, and outreach to the WAP network, user response, and lessons learned.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Multilevel-in-width training for deep neural network regression

A common challenge in regression is that for many problems, the degrees of freedom required for a high-quality solution also allows for overfitting. Regularization is a class of strategies that seek to restrict the range of possible solutions so as to discourage overfitting while still enabling good solutions, and different regularization strategies impose different types of restrictions. In this paper, we present a multilevel regularization strategy that constructs and trains a hierarchy of neural networks, each of which has layers that are wider versions of the previous network's layers. Here, we draw intuition and techniques from the field of Algebraic Multigrid (AMG), traditionally used for solving linear and nonlinear systems of equations, and specifically adapt the Full Approximation Scheme (FAS) for nonlinear systems of equations to the problem of deep learning. Training through V-cycles then encourage the neural networks to build a hierarchical understanding of the problem. We refer to this approach as multilevel-in-width to distinguish from prior multilevel works which hierarchically alter the depth of neural networks. The resulting approach is a highly flexible framework that can be applied to a variety of layer types, which we demonstrate with both fully connected and convolutional layers. We experimentally show with PDE regression problems that our multilevel training approach is an effective regularizer, improving the generalize performance of the neural networks studied.

97 MATHEMATICS AND COMPUTING↗