Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “optimal input design”

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 379 records · Page 21
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Control And Optimization Modular Modeling Application For Nuclear Deployment

The purpose of the COMMAND code is to provide a flexible, scalable tool for use in developing, integrating, and testing the technologies necessary for achieving autonomous operations of advanced nuclear reactors. The code enables users to efficiently implement custom simulations and experiments by combining key methods from different software modules. These modules are focused on: modeling and simulation tools, such as nuclear simulation tools used for high-fidelity modeling (e.g., Reactor Excursion and Leak Analysis Program [RELAP5-3D] and Monte Carlo N-Particle [MCNP]); machine learning and optimization tools (e.g., anomaly detection and data-driven modeling techniques); advanced control in its digital, high-performance, and supervisory control forms (e.g., proportional integral derivative (PID) control and model predictive control (MPC); and integration with hardware through industrial communication protocols. To ensure flexibility and scalability, COMMAND was designed to be both modular—the software “pieces” all inherit from generic building blocks and can be combined and connected to create complicated simulations—and high performing—designed for parallel processing, enabling simulations and experiments to take advantage of multi-core computers, servers, and nodes. The code is written in the Python programming language due to the language's popularity, active community, and open-source and cross-platform nature. Maintaining consistency with other simulation tools used within the nuclear energy community, users implement simulations and experiments through text input files, which define components, parameters, connections, etc., through lines of text. Given that COMMAND is written in Python, these input files are native Python scripts, and so use the standard Python structure and formatting. This also enables users to take advantage of Python's extensive package library to develop custom capabilities for their specific use cases.

Faber, Jacob [Idaho National Laboratory (INL), Ida↗
DOE OSTI2023

Development of a Heavy-Duty Electric Vehicle Integration and Implementation (HEVII) Tool

As demand for consumer electric vehicles (EVs) has drastically increased in recent years, manufacturers have been working to bring heavy-duty EVs to market to compete with Class 6-8 diesel-powered trucks. Many high-profile companies have committed to begin electrifying their fleet operations, but have yet to implement EVs at scale due to their limited range, long charging times, sparse charging infrastructure, and lack of data from in-use operation. Thus far, EVs have been disproportionately implemented by larger fleets with more resources. To aid fleet operators, it is imperative to develop tools to evaluate the electrification potential of heavy-duty fleets. However, commercially available tools, designed mostly for light-duty vehicles, are inadequate for making electrification recommendations tailored to a fleet of heavy-duty vehicles. The main challenge is that light-duty tools do not estimate real-time vehicle mass, a factor that has a disproportionate impact on the energy consumption of large commercial vehicles. The Heavy-Duty Electric Vehicle Integration and Implementation (HEVII) tool advances the state of the art in evaluating electrification potential and infrastructure requirements for fleets of commercial vehicles. In this work, the HEVII tool is demonstrated with non-uniformly sampled telematics data from an existing fleet to assess the suitability for electrification of each individual vehicle, determine optimal locations for charging infrastructure to support a fleet of EVs and analyze associated costs. Payload mass is predicted using sparse ground-truth data for all input drive cycles and an initial data analysis is conducted to assess the characteristics driving behaviors and energy consumption of the fleet using an adaptable vehicle model. Battery size requirements are determined by applying a novel charger placement algorithm to maximize routes that are viable for EVs and balance time delays with infrastructure development costs. This work details and demonstrates the different aspects of the HEVII tool, presenting preliminary results from an example use case.

ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2025

Conditional guide RNA deactivation by mRNA and small molecule triggers in Saccharomyces cerevisiae

CRISPR interference (CRISPRi) technologies have revolutionized bioengineering by providing precise tools for gene expression modulation, enabling targeted gene perturbation and metabolic pathway optimization. Despite these advances, achieving dynamic control over gene expression by CRISPR-based regulation remains a challenge due to its inherently static nature. Utilizing toehold-mediated strand displacement and ligand-responsive ribozymes (aptazymes), this study introduces switchable guide RNAs (gRNAs) that facilitate tunable gene expression mediated by mRNA or small molecule signals. We demonstrate complete silencing of gRNA via strategically designed 5’ or 3’ extensions that impede the gRNA spacer or the dCas9 handle, with subsequent restoration of function through sequestration or cleavage of the obstructive sequence. The resulting toehold-embedded or aptazyme-embedded gRNAs can be deactivated by specific signals, including two full-length translatable mRNAs and two small molecule triggers, thereby lifting CRISPRi repression on targeted genes. This modular approach allows for gRNA-based biocomputing through multi-layer or multi-input genetic logic gates in Saccharomyces cerevisiae . Offering a versatile strategy for post-CRISPR regulation in response to environmental signals or cellular states, this methodology expands the toolkit in eukaryotic systems for reversible control of gene expression.

Aptazyme↗
DOE OSTI2024

Modeling Approach for the Aluminum-clad Dry Storage Pilot using HFIR Fuel

To confirm that the dry storage of aluminum-clad research reactor spent nuclear fuel (ASNF) will remain within the safety envelope after applied drying schemes and that the resulting evolution of the gas space composition, temperature, and pressure conditions are understood, a dry storage pilot project is being established. The pilot will incorporate an instrumented lid for discrete interval or for on-demand gas composition and temperature monitoring of two DOE Standard Canisters (DSCs) loaded with three High Flux Isotope Reactor (HFIR) inner cores per DSC. Each DSC would be subjected to a separate alternative candidate drying scheme. Canisters will undergo 1 to 5 years of monitoring, including internal temperature and gas sampling to track pressure and composition changes. This report outlines the approach for modeling the ASNF-in-canister behavior in terms of evolving gas space conditions for the ASNF dry storage pilot using HFIR fuel. The ASNF has an adherent surface oxyhydroxide layer comprised of boehmite/bayerite that generates hydrogen when subjected to irradiation. Three-dimensional multi-physics computational fluid dynamics simulations will be executed to compute the thermal field within the DSC and provide inputs to a chemical model employed to compute pressure buildup as hydrogen is generated in the system. Implemented in Cantera, the chemical model solves gas phase and aluminum oxyhydroxide surface-mediated radiolysis reactions. Gas phase reactions are sourced from Wittman and Hanson (2015), whereas surface-mediated reactions are incorporated by fitting experimental data using an optimization algorithm (Abboud, 2023). Water radiolysis reactions from Wren and Ball (2001) are adopted with modifications as described in Abboud (2023c). Understanding the effect of the hydrogen buildup over time is important for long-term storage safety considerations. Modeling results will include the canister pressure, temperature, and composition evolution from the initial helium backfill with the addition of radiolytically-evolved chemical species (e.g., hydrogen and oxygen). The specific HFIR cores for the pilot program have not yet been selected, and the overall design is still in development. The CFD-chemical model used for this work will be based on prior models with necessary updates to allow for improved accuracy and efficiency. The experimental data obtained from the HFIR demonstration will be used to improve and validate the computational models to predict the ASNF-in-canister behavior.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2024

Self‐Consistent Convolutional Density Functional Approximations: Application to Adsorption at Metal Surfaces

The exchange-correlation (XC) functional in density functional theory is used to approximate multi-electron interactions. A plethora of different functionals are available, but nearly all are based on the hierarchy of inputs commonly referred to as “Jacob's ladder.” This paper introduces an approach to construct XC functionals with inputs from convolutions of arbitrary kernels with the electron density, providing a route to move beyond Jacob's ladder. We derive the variational derivative of these functionals, showing consistency with the generalized gradient approximation (GGA), and provide equations for variational derivatives based on multipole features from convolutional kernels. A proof-of-concept functional, PBEq, which generalizes the PBEα framework with mathematical equation being a spatially-resolved function of the monopole of the electron density, is presented and implemented. It allows a single functional to use different GGAs at different spatial points in a system, while obeying PBE constraints. Analysis of the results underlines the importance of error cancellation and the XC potential in data-driven functional design. After testing on small molecules, bulk metals, and surface catalysts, the results indicate that this approach is a promising route to simultaneously optimize multiple properties of interest.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

Automating Bayesian inference and design to quantify acoustic particle levitation

Self-propulsion of micro- and nanoparticles powered by ultrasound provides an attractive strategy for the remote manipulation of colloidal matter using biocompatible energy inputs. Quantitative understanding of particle motion and its dependence on size, shape, and composition requires accurate characterization of the acoustic field, which depends sensitively on the experimental setup. Here, we show how automated experiments based on Bayesian inference and design can accurately and efficiently characterize the acoustic field within resonant chambers used to propel acoustic nanomotors. Repeated cycles of observation, inference, and design (OID) are guided by a physical model that describes the rate at which levitating particles approach the nodal plane. Using video microscopy, we observe the relaxation of tracer particles to this plane following the application of the acoustic field. We use sequential Monte Carlo methods to infer model parameters such as the amplitude and frequency of the resonant chamber while accounting for particle-level measurement noise and population-level heterogeneity in the field. Guided by simulated outcomes, we select the optimal design for the next experiment as to maximize the information gain in the relevant parameters. We show how this iterative process serves to discriminate between competing hypotheses and efficiently converges to accurate parameter estimates using only few automated experiments. We discuss the need for model criticism to ensure the validity of the guiding model throughout automated cycles of observation, inference, and design. Furthermore, this work demonstrates how Bayesian methods can learn the parameters of nonlinear, hierarchical models used to describe video microscopy data of active colloids.

42 ENGINEERING↗
DOE OSTI2026

Pre-training Vision Models for the Classification of Alerts from Wide-field Time-domain Surveys

Modern wide-field time-domain surveys facilitate the study of transient, variable and moving phenomena by conducting image differencing and relaying alerts to their communities. Machine learning tools have been used on data from these surveys and their precursors for more than a decade, and convolutional neural networks (CNNs), which make predictions directly from input images, saw particularly broad adoption through the 2010s. Since then, continually rapid advances in computer vision have transformed the standard practices around using such models. It is now commonplace to use standardized architectures pre-trained on large corpora of everyday images (e.g., ImageNet). In contrast, time-domain astronomy studies still typically design custom CNN architectures and train them from scratch. Here, we explore the effects of adopting various pre-training regimens and standardized model architectures on the performance of alert classification. We find that the resulting models match or outperform a custom, specialized CNN like what is typically used for filtering alerts. Moreover, our results show that pre-training on galaxy images from Galaxy Zoo tends to yield better performance than pre-training on ImageNet or training from scratch. We observe that the design of standardized architectures are much better optimized than the custom CNN baseline, requiring significantly less time and memory for inference despite having more trainable parameters. On the eve of the Legacy Survey of Space and Time and other image-differencing surveys, these findings advocate for a paradigm shift in the creation of vision models for alerts, demonstrating that greater performance and efficiency, in time and in data, can be achieved by adopting the latest practices from the computer vision field.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Hypothesis testing via AI: Generating physically interpretable models of scientific data with machine learning (Full Technical Report)

Deep learning has demonstrated an exceptional ability to solve complex tasks (an engineering success); however, it has done so at the expense of the ability to generate new knowledge (a scientific failure). We propose an alternative framework—entitled Deep Symbolic Regression (DSR)—in which artificial neural networks (NNs) rapidly generate hypotheses about physical relationships among inputs. This framework bypasses the need to interpret an NN altogether, while still leveraging the representational power of deep learning. The resulting models are tractable mathematical expressions, which are inherently and readily human interpretable and can provide insights into underlying physical phenomena. Further, we fold this methodology into the scientific process by allowing the scientist to directly integrate a priori knowledge and beliefs to accelerate learning. We demonstrate this methodology on symbolic regression—the problem of rediscovering underlying expressions describing a dataset—and achieve state-of-the-art performance across a wide variety of symbolic regression problems. Further, we generalize our DSR framework to apply to the more general class of symbolic optimization problems, in which one seeks to optimize a sequence of symbols or “tokens” under a black-box reward function. Examples of other symbolic optimization problems include neural architecture search and computational antibody design. Our generalized tool, Deep Symbolic Optimization (DSO), has been demonstrated on the task of learning symbolic control policies for reinforcement learning environments, and has been adopted as an enabling capability for computational antibody design.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Integration and Optimization of a Waste Heat Driven Organic Rankine Cycle for Power Generation in Wastewater Treatment Plants

The study focuses on achieving energy self-sufficiency in Wastewater Treatment Plants by proposing a comprehensive model for integrating, sizing, and optimizing an Organic Rankine Cycle system. The Organic Rankine Cycle system is designed to utilize waste heat from the gensets at As Samra Wastewater Treatment Plant in Jordan, where it will contribute to the overall electrical energy supply of the plant. Real data from As Samra Wastewater Treatment Plant is used to model and calculate the available waste heat using TRNSYS® software. The Organic Rankine Cycle model is then developed using ASPEN PLUS® software to explore the impact of operational parameters and determine their optimal values for maximizing the plant's energy profile. An economic analysis is conducted to assess the feasibility of the proposed model, considering system components, installation, operation, and maintenance costs. To optimize the Organic Rankine Cycle system, the study employs the Multi-Output Support Vector Regression technique to capture nonlinear relationships between independent variables (fluid type, turbine inlet pressure, turbine inlet temperature, turbine outlet pressure, and mass flow rate) and dependent variables (pump power input, waste heat input, and turbine specific work). The Osprey optimization algorithm is used to address the multi-objective optimization problem, with the proposed Pareto-based Osprey Optimization Algorithm and the Multi-Objective Particle Swarm Optimization technique being employed to evaluate critical performance and economic parameters such as system thermal efficiency, net power output, and the levelized cost of electricity. The results of the optimization strategies indicate that the M-SVR model's prediction accuracy is significantly improved after parameter optimization, with the model returning high R 2 and low Mean Square Error values of 0.991 and 0.00216, respectively. The Pareto-Based Osprey Optimization Algorithm optimizer identifies the best working fluid as Isobutane/Isopentane in a ratio of 66:34, with optimal turbine inlet pressure and temperature of 15 bars and 218 °C, respectively. In conclusion, the Organic Rankine Cycle model at these optimal conditions achieves a cycle efficiency of 19.93% and an Levelized Cost of Electricity value of 0.0353 USD/kWh.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2025

Uncertainty-Based Design: Finite Element and Explainable Machine Learning Modeling of Carbon–Carbon Composites for Ultra-High Temperature Solar Receivers

Design under uncertainty has significantly grown in research developments during the past decade. Additionally, machine learning (ML) and explainable ML (XML) have offered various opportunities to provide reliable predictable models. The current article investigates the use of finite element modeling (FEM), ML and XML predictions, and uncertain-based design of carbon-carbon (C-C) composites for use in ultra-high temperatures. A C-C composite concentrating solar power (CSP) as a microvascular receiver is considered as a case study. These C-C composites are fiber composites with directly integrated carbonized microchannels to form a lightweight, high-absorptivity material that includes an embedded microvascular network of channels. The topology of these microchannels is engineered to optimize heat transfer to a supercritical carbon dioxide (sCO2) heat transfer fluid. The mechanical characterization of C-C composites is highly challenging. Thus, designing every component made of C-C composites for ultra-high temperature applications needs an uncertainty-based analysis. As a part of a comprehensive project on the development of a novel carbonized microvascular C-C composite, this paper explores C-C composite sensitivity analysis, FEM, ML prediction, and XML analysis. The resulting composite can then be carbonized and coated with an oxidation-resistant coating to form a thermally efficient and mechanically robust C-C composite. An ANSYS 3-D-FE model was used to analyze the CSP’s stress/strain. To consider the variability in the mechanical and thermal properties of C-C composites, various mechanical properties are considered as the ANSYS FEM’s input. A synthetic dataset from 730 ANSYS runs was produced to feed into the ML and XML algorithms for uncertainty analysis and prediction. The ML and XML algorithms could accurately predict the CSP stresses/strains.

Daghigh, Vahid (ORCID:0000000298941620)↗
DOE OSTI2022

iNovo479: Metabolic Modeling Provides a Roadmap to Optimize Bioproduct Yield from Deconstructed Lignin Aromatics by Novosphingobium aromaticivorans

Lignin is an abundant renewable source of aromatics and precursors for the production of other organic chemicals. However, lignin is a heterogeneous polymer, so the mixture of aromatics released during its depolymerization can make its conversion to chemicals challenging. Microbes are a potential solution to this challenge, as some can catabolize multiple aromatic substrates into one product. Novosphingobium aromaticivorans has this ability, and its use as a bacterial chassis for lignin valorization could be improved by the ability to predict product yields based on thermodynamic and metabolic inputs. In this work, we built a genome-scale metabolic model of N. aromaticivorans, iNovo479, to guide the engineering of strains for aromatic conversion into products. iNovo479 predicted product yields from single or multiple aromatics, and the impact of combinations of aromatic and non-aromatic substrates on product yields. We show that enzyme reactions from other organisms can be added to iNovo479 to predict the feasibility and profitability of producing additional products by engineered strains. Thus, we conclude that iNovo479 can help guide the design of bacteria to convert lignin aromatics into valuable chemicals.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

A New Design Consideration for Bidirectional Resonant Converters

This paper introduces innovative design considerations for a bidirectional resonant converter, optimized for Electric Vehicle (EV) charging and vehicle-togrid (V2G) applications. By eliminating the need for complex voltage or current gain functions, the proposed design greatly simplifies the development process, making it more accessible for manufacturers and system integrators. This approach not only reduces engineering time and resource investment but also accelerates time-to-market, giving stakeholders a competitive edge in rapidly expanding EV infrastructure markets. In addition, the streamlined design ensures soft switching at maximum output power, leading to higher efficiency and improved durability, which translates to lower operating costs and a longer service life for EV charging equipment. These benefits provide a clear pathway to more cost-effective, scalable, and sustainable EV charging and V2G solutions, enhancing value for stakeholders by facilitating smoother integration into the grid and supporting energy resilience. To validate the benefits, a 60 kW bidirectional charger with a flexible input range of 700−900VDC and an output range of 400−1250VDC was developed, underscoring the design's adaptability and potential for large-scale implementation.

Asa, Erdem [ORNL] (ORCID:0000000190884812)↗
DOE OSTI2020

Printing polymer blends through in situ active mixing during fused filament fabrication

Fused filament fabrication (FFF) enables production of 3D objects over a range of material compositions at low-cost relative to traditional manufacturing approaches. To date, a limited but growing number of materials are able to be used with FFF, however many applications exist where specific mechanical, thermal, or chemical properties are needed that cannot currently be met with the available feedstock selection. Therefore, a need exists to tune these materials for specific chemical or mechanical properties. One common formulation strategy to address these demanding design parameters is to develop composites or polymer blend filaments. Typically, this is a time-consuming and costly optimization process. Here, we have developed hardware for reproducibly mixing two filaments of similar or dissimilar compositions at the time of printing within individual printed layers. This mixing occurs via software-controlled rotating hardware in the chamber of an extruder’s hot-end. The efficiency of mixing within the printed layers has been characterized in detail as a function of the rotational speed and geometry of the blending hardware. These parameters were exploited to program the ratio and distribution of thermoplastic-based filaments blended within printed extrudate. Example printed specimens were produced with thermoplastic polyurethane (TPU) elastomer blended with rigid polylactic acid (PLA) and Nylon blended with PLA. In addition, a conductive carbon nanotube (CNT)-PLA composite was blended as a function of mixer geometry and input feed ratios with non-conductive PLA and resistance values were measured across the resulting printed specimens.

36 MATERIALS SCIENCE↗
DOE OSTI2026

Technoeconomic and Life Cycle Analysis of an Integrated Fermentation and Microbial Electrochemical Process for Volatile Fatty Acid Production from Food Waste

Techno-economic analysis (TEA) and life cycle assessment (LCA) were conducted for an integrated system designed for the production of volatile fatty acid (VFA) from food waste. The TEA estimated a production cost of $\$$3.12/kg VFA, and the LCA predicted negative greenhouse gas (GHG) emissions of -0.4 kg CO 2 e/kg VFA, driven primarily by diverting organic waste from landfills and avoiding methane emissions while producing valuable chemical products. Hotspot analysis showed arrested methanogenesis (AM) fermentation as the largest contributor to costs (37%) and environmental burden (47%), driven by high sodium hydroxide (NaOH) consumption. Distillation and microbial electrosynthesis (MES) units were the next-largest environmental contributors (28% and 18%). Major cost drivers also included residuals management (biosolids and wastewater) and the equipment and operating costs for AM, MES, and sonication pretreatment units. Although the new integrated system is environmentally benign, its costs and environmental impacts can be further reduced by integrating alternative energy sources, minimizing chemical and energy inputs through process optimization, and improving efficiency. In conclusion, this work highlighted the viability of waste-derived VFA production and provided a clear, data-driven strategy to accelerate the commercialization of waste valorization technology.

Carboxylic Acid Production↗
DOE OSTI2021

Cognitive simulation models for inertial confinement fusion: Combining simulation and experimental data

The design space for inertial confinement fusion (ICF) experiments is vast, and experiments are extremely expensive. Researchers rely heavily on computer simulations to explore the design space in search of high-performing implosions. However, ICF multiphysics codes must make simplifying assumptions, and thus deviate from experimental measurements for complex implosions. For more effective design and investigation, simulations require input from past experimental data to better predict future performance. In this work, we describe a cognitive simulation method for combining simulation and experimental data into a common, predictive model. This method leverages a machine learning technique called “transfer learning,” the process of taking a model trained to solve one task, and partially retraining it on a sparse dataset to solve a different, but related task. In the context of ICF design, neural network models are trained on large simulation databases and partially retrained on experimental data, producing models that are far more accurate than simulations alone. Here, we demonstrate improved model performance for a range of ICF experiments at the National Ignition Facility and predict the outcome of recent experiments with less than 10% error for several key observables. We discuss how the methods might be used to carry out a data-driven experimental campaign to optimize performance, illustrating the key product—models that become increasingly accurate as data are acquired.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

Comparison of Machine Learning Approaches for Prediction of the Equivalent Alkane Carbon Number for Microemulsions Based on Molecular Properties

The chemical properties of oils are vital in the design of microemulsion systems. The hydrophilic–lipophilic difference equation used to predict microemulsions’ phase behavior expresses the oils’ physiochemical properties as the equivalent alkane carbon number (EACN). The experimental determination of EACN requires knowledge of the temperature dependence of the microemulsion system and the effects of different surfactant concentrations. Thus, the experimental determination is time-intensive and tedious, requiring days to months for proper separations. Furthermore, the experiments require high purity of chemicals because microemulsions are sensitive to impurities. Our work focuses on the quick and reliable predictions of the EACN with machine learning (ML) models. Due to the immaturity of ML chemical predictions, we compare three graph neural networks (GNNs) and a gradient-boosted tree algorithm, known as XGBoost. The GNNs use the molecular structures represented as simplified molecular-input line-entry system (SMILES) codes for the initial input, which allows us to assess whether geometry optimization is necessary for reliable results. The XGBoost model also begins with the SMILES representations of the molecules but uses molecular descriptors instead of geometry optimizations. As a result, the best model tested (crystal graph convolutional neural network with Merck molecular force field-94) has an error of 1.15 EACN units of the true EACN for unknown data with the errors skewed toward zero and an R² score of 0.9

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

A Length Adaptive Algorithm-Hardware Co-design of Transformer on FPGA Through Sparse Attention and Dynamic Pipelining

Transformers are considered one of the most important deep learning models since 2018, in part because it establishes state-of-the-art (SOTA) records and could potentially replace existing Deep Neural Networks (DNNs). Despite the remarkable triumphs, the prolonged turnaround time of Transformer models is a widely recognized roadblock. The variety of sequence lengths imposes additional computing overhead where inputs need to be zero-padded to the maximum sentence length in the batch to accommodate the parallel computing platforms. This paper targets the field-programmable gate array (FPGA) and proposes a coherent sequence length adaptive algorithm–hardware co-design for Transformer acceleration. Particularly, we develop a hardware-friendly sparse attention operator and a length-aware hardware resource scheduling algorithm. The proposed sparse attention operator brings the complexity of attention-based models down to linear complexity and alleviates the off-chip memory traffic. The proposed length-aware resource hardware scheduling algorithm dynamically allocates the hardware resources to fill up the pipeline slots and eliminates bubbles for NLP tasks. Experiments show that our design has very small accuracy loss and has 80.2 × and 2.6 × speedup compared to CPU and GPU implementation, and 4 × higher energy efficiency than state-of-the-art GPU accelerator optimized via CUBLAS GEMM.

Peng, Hongwu↗
DOE OSTI2024

ITER ECH Transmission Line System Design and Status

The electron cyclotron (EC) heating & current drive (H&CD) system on ITER provides plasma heating by generating, transmitting, and launching high-intensity, high-frequency (170 GHz) electromagnetic wave energy steerable across the plasma cross-section. The transmission line (TL) subsystem connects the Matching Optics Unit (MOU) on each of the 24 gyrotrons to the 32 feed points in the four upper launchers and the 24 feed points in the equatorial launcher. Each TL must be able to operate at up to 1.2 MW of input power for up to 1 hour pulse lengths. The TL system contains 50 mm water-cooled corrugated waveguide, 90o miter bends, 140o miter bends, polarizer miter bend pairs, switches, expansion units, pumpouts, DC breaks, MOU-TL adapters, Radio Frequency (RF) loads, and isolation shutter valves. A detailed finite element analysis has been used to verify the thermo-mechanical performance of each component. The microwave performance has been analyzed using a 2-D electromagnetic code combined with a Monte Carlo code. This approach allows the impact of manufacturing and installation tolerances to be assessed and optimized to provide a high probability of achieving the system performance requirements. Prototypes of the waveguide and TL components have been fabricated and tested at high-power. Production contracts are now being issued for fabrication and delivery of the waveguide and components to ITER.

Hanson, Gregory↗