Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “architecture optimization”

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 433 records · Page 24
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Transformer Neural Networks with Spatiotemporal Attention for Predictive Control and Optimization of Industrial Processes

In the context of real-time optimization and model predictive control of industrial systems, machine learning, and neural networks represent cutting-edge tools that hold promise for enhancing dynamic modeling. This work presents a novel transformer neural network architecture for real-time optimization and model predictive control. This network design includes a modified attention mechanism inspired by positional embedding attention from vision transformers and task-specific modifications to the input-output structure of the transformer’s decoder stack. Experiments were conducted using data from a 450 MW coal-fired power plant to evaluate this approach's effectiveness. The transformer neural network was compared with conventional recurrent models, including GRU and LSTM. The transformer exhibited a 6% increase in the R-squared (R2) value of predictions and an 83% reduction in mean squared error (MSE). Computation time was also reduced by 84% compared to conventional recurrent models.

Gallup, Ethan R.↗
NASA NTRS2017

Optimal Control Allocation with Load Sensor Feedback for Active Load Suppression, Experiment Development

The problem of control command and maneuver induced structural loads is an important aspect of any control system design. The aircraft structure and the control architecture must be designed to achieve desired piloted control responses while limiting the imparted structural loads. The classical approach is to utilize high structural margins, restrict control surface commands to a limited set of analyzed combinations, and train pilots to follow procedural maneuvering limitations. With recent advances in structural sensing and the continued desire to improve safety and vehicle fuel efficiency, it is both possible and desirable to develop control architectures that enable lighter vehicle weights while maintaining and improving protection against structural damage. An optimal control technique has been explored and shown to achieve desirable vehicle control performance while limiting sensed structural loads. The subject of this paper is the design of the optimal control architecture, and provides the reader with some techniques for tailoring the architecture, along with detailed simulation results.

controls↗
NASA NTRS1990

Multi-level Hierarchical Poly Tree computer architectures

Based on the concept of hierarchical substructuring, this paper develops an optimal multi-level Hierarchical Poly Tree (HPT) parallel computer architecture scheme which is applicable to the solution of finite element and difference simulations. Emphasis is given to minimizing computational effort, in-core/out-of-core memory requirements, and the data transfer between processors. In addition, a simplified communications network that reduces the number of I/O channels between processors is presented. HPT configurations that yield optimal superlinearities are also demonstrated. Moreover, to generalize the scope of applicability, special attention is given to developing: (1) multi-level reduction trees which provide an orderly/optimal procedure by which model densification/simplification can be achieved, as well as (2) methodologies enabling processor grading that yields architectures with varying types of multi-level granularity.

Padovan, Joe↗
DOE OSTI2022

Learning Optimal Aerodynamic Designs

This project created a framework for efficient, accurate, and scalable deep neural network representations of design optimization problem solutions. The inputs to these DNN representations are the vector of design requirement parameters, the outputs are the optimal design variables, and the goal is to learn the map from inputs to outputs (i.e., inverse design). The team addressed the problem of the optimal shape design of aerodynamic lifting surfaces—in particular aircraft wings—using a Reynolds-Average Navier Stokes model to govern the CFD-based aerodynamic shape optimization. The inverse design map for such problems is very complex and high-dimensional, involving inputs and outputs on the order of 1000s. To approximate this inverse design map, the team developed algorithms to construct parsimonious DNN architectures, which automatically identify low-dimensional manifolds in which design requirements affect optimal shape parameters, and trained these architectures with multifidelity optimization methods. The resulting methodology accurately and automatically designs optimal aerodynamic lifting surfaces with very high accuracy (99%) at interactive speeds, of the order of milliseconds, resulting in factors of one million or more speedup relative to CFD-based design optimization.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2015

Optimization of Selected Remote Sensing Algorithms for Embedded NVIDIA Kepler GPU Architecture

This paper evaluates the potential of embedded Graphic Processing Units in the Nvidias Tegra K1 for onboard processing. The performance is compared to a general purpose multi-core CPU and full fledge GPU accelerator. This study uses two algorithms: Wavelet Spectral Dimension Reduction of Hyperspectral Imagery and Automated Cloud-Cover Assessment (ACCA) Algorithm. Tegra K1 achieved 51 for ACCA algorithm and 20 for the dimension reduction algorithm, as compared to the performance of the high-end 8-core server Intel Xeon CPU with 13.5 times higher power consumption.

Riha, Lubomir↗
NASA NTRS2015

Optimization of Selected Remote Sensing Algorithms for Embedded NVIDIA Kepler GPU Architecture

This paper evaluates the potential of embedded Graphic Processing Units (GPUs) in Nvidia's Tegra K1 (based on Kepler (TM) hardware) for onboard processing. The performance is compared to a general purpose multi-core CPU (Central Processing Unit) and a fully-fledged GPU accelerator. This study uses two algorithms: Wavelet Spectral Dimension Reduction of Hyperspectral Imagery and Automated Cloud-Cover Assessment (ACCA) Algorithm. Tegra K1 achieved 51 for the ACCA algorithm and 20 for the dimension reduction algorithm, as compared to the performance of the high-end 8-core server Intel Xeon CPU with 13.5 times higher power consumption.

data reduction↗
DOE OSTI2023

Performance portable ice-sheet modeling with MALI

High-resolution simulations of polar ice sheets play a crucial role in the ongoing effort to develop more accurate and reliable Earth system models for probabilistic sea-level projections. These simulations often require a massive amount of memory and computation from large supercomputing clusters to provide sufficient accuracy and resolution; therefore, it has become essential to ensure performance on these platforms. Many of today’s supercomputers contain a diverse set of computing architectures and require specific programming interfaces in order to obtain optimal efficiency. In an effort to avoid architecture-specific programming and maintain productivity across platforms, the ice-sheet modeling code known as MPAS-Albany Land Ice (MALI) uses high-level abstractions to integrate Trilinos libraries and the Kokkos programming model for performance portable code across a variety of different architectures. In this article, we analyze the performance portable features of MALI via a performance analysis on current CPU-based and GPU-based supercomputers. The analysis highlights not only the performance portable improvements made in finite element assembly and multigrid preconditioning within MALI with speedups between 1.26 and 1.82x across CPU and GPU architectures but also identifies the need to further improve performance in software coupling and preconditioning on GPUs. We perform a weak scalability study and show that simulations on GPU-based machines perform 1.24–1.92x faster when utilizing the GPUs. The best performance is found in finite element assembly, which achieved a speedup of up to 8.65x and a weak scaling efficiency of 82.6% with GPUs. We additionally describe an automated performance testing framework developed for this code base using a changepoint detection method. The framework is used to make actionable decisions about performance within MALI. We provide several concrete examples of scenarios in which the framework has identified performance regressions, improvements, and algorithm differences over the course of 2 years of development.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRS2003

Aerodynamic Design of Complex Configurations Using Cartesian Methods and CAD Geometry

The objective for this paper is to present the development of an optimization capability for the Cartesian inviscid-flow analysis package of Aftosmis et al. We evaluate and characterize the following modules within the new optimization framework: (1) A component-based geometry parameterization approach using a CAD solid representation and the CAPRI interface. (2) The use of Cartesian methods in the development Optimization techniques using a genetic algorithm. The discussion and investigations focus on several real world problems of the optimization process. We examine the architectural issues associated with the deployment of a CAD-based design approach in a heterogeneous parallel computing environment that contains both CAD workstations and dedicated compute nodes. In addition, we study the influence of noise on the performance of optimization techniques, and the overall efficiency of the optimization process for aerodynamic design of complex three-dimensional configurations. of automated optimization tools. rithm and a gradient-based algorithm.

Nemec, Marian↗
DOE OSTI2017

Anomaly Detection Using Optimally-Placed μPMU Sensors in Distribution Grids

IEEE As the distribution grid moves toward a tightly-monitored network, it is important to automate the analysis of the enormous amount of data produced by the sensors to increase the operators situational awareness about the system. Here, focusing on Micro-Phasor Measurement Unit (μPMU) data, we propose a hierarchical architecture for monitoring the grid and establish a set of analytics and sensor fusion primitives for the detection of abnormal behavior in the control perimeter. And due to the key role of the μPMU devices in our architecture, a source-constrained optimal μPMU placement is also described that finds the best location of the devices with respect to our rules. The effectiveness of the proposed methods are tested through the synthetic and real μPMU data.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

HydraGNN_OPF_GFM_2026 - Ensemble of predictive graph foundation models for power grid applications

This dataset supports research on graph foundation models for optimal power flow (OPF) on electric grids using HydraGNN. It contains heterogeneous graph representations of PGLib-OPF cases spanning systems from 14 to 13,659 buses, together with packed HDF5 datasets for pretraining, feasibility classification, and N-1 contingency analysis. The release includes OPF solution data, downstream fine-tuning datasets, pretrained HeteroSAGE and HeteroHEAT model checkpoints, hyperparameter-optimization summaries across multiple heterogeneous GNN architectures, and aggregated fine-tuning results for sample-efficiency studies. The dataset is designed to enable scalable training, evaluation, and transfer-learning studies for OPF surrogate modeling, including node-level AC-OPF solution prediction, graph-level prediction, feasibility classification, operating-condition generalization, and contingency-response tasks.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Accelerated Constrained Sparse Tensor Factorization on Massively Parallel Architectures

This study presents the first constrained sparse tensor factorization (cSTF) framework that optimizes and fully offloads computation to massively parallel GPU architectures, and the first performance characterization of cSTF on GPU architectures. In contrast to prior work on tensor factorization, where the matricized tensor times Khatri-Rao product (MTTKRP) is the primary performance bottleneck, our systematic analysis of the cSTF algorithm on GPUs reveals that adding constraints creates an additional bottleneck in the update operation for many real-world sparse tensors. While executing the update operation on the GPU brings significant speedup over its CPU counterpart, it remains a significant bottleneck. To further accelerate the update operation, we propose cuADMM, a new update algorithm that leverages algorithmic and code optimization strategies to minimize both computation and data movement on GPUs. As a result, our framework delivers significantly improved performance compared to prior state-of-the-art. On 10 real-world sparse tensors, our framework achieves geometric mean speedup of 5.1 × (max 41.59 ×) and 7.01 × (max 58.05 ×) on the NIVIDA A100 and H100 GPUs, respectively, over the state-of-the-art SPLATT library running on a 26-core Intel Ice Lake Xeon CPU.

Soh, Yongseok↗
DOE OSTI2025

Physics-Informed Neural Networks for PDE-Constrained Optimization and Control

The goal of optimal control is to determine a sequence of inputs for maximizing or minimizing a given performance criterion subject to the dynamics and constraints of the system under observation. This work introduces Control Physics-Informed Neural Networks (PINNs), which simultaneously learn both the system states and the optimal control signal in a single-stage framework that leverages the system’s underlying physical laws. While prior approaches often follow a two-stage process-modeling, the system first and then devising its control—the presented novel framework embeds the necessary optimality conditions directly into the network architecture and loss function. We demonstrate the effectiveness of the novel methodology by solving various open-loop optimal control problems governed by analytical, one-dimensional, and two-dimensional partial differential equations (PDEs).

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2012

In-Space Propellant Production Using Water

A new era of space exploration is being planned. Manned exploration architectures under consideration require the long term storage of cryogenic propellants in space, and larger science mission directorate payloads can be delivered using cryogenic propulsion stages. Several architecture studies have shown that in-space cryogenic propulsion depots offer benefits including lower launch costs, smaller launch vehicles, and enhanced mission flexibility. NASA is currently planning a Cryogenic Propellant Storage and Transfer (CPST) technology demonstration mission that will use existing technology to demonstrate long duration storage, acquisition, mass gauging, and transfer of liquid hydrogen in low Earth orbit. This mission will demonstrate key technologies, but the CPST architecture is not designed for optimal mission operations for a true propellant depot. This paper will consider cryogenic propellant depots that are designed for operability. The operability principles considered are reusability, commonality, designing for the unique environment of space, and use of active control systems, both thermal and fluid. After considering these operability principles, a proposed depot architecture will be presented that uses water launch and on orbit electrolysis and liquefaction. This could serve as the first true space factory. Critical technologies needed for this depot architecture, including on orbit electrolysis, zero-g liquefaction and storage, rendezvous and docking, and propellant transfer, will be discussed and a developmental path forward will be presented. Finally, use of the depot to support the NASA Science Mission Directorate exploration goals will be presented.

Notardonato, William↗
DOE OSTI2017

Geometry Optimization with Machine Trained Topological Atoms

The geometry optimization of a water molecule with a novel type of energy function called FFLUX is presented, which bypasses the traditional bonded potentials. Instead, topologically-partitioned atomic energies are trained by the machine learning method kriging to predict their IQA atomic energies for a previously unseen molecular geometry. Proof-of-concept that FFLUX’s architecture is suitable for geometry optimization is rigorously demonstrated. It is found that accurate kriging models can optimize 2000 distorted geometries to within 0.28kJmol-1 of the corresponding ab initio energy, and 50% of those to within 0.05kJmol-1. Kriging models are robust enough to optimize the molecular geometry to sub-noise accuracy, when two thirds of the geometric inputs are outside the training range of that model. Finally, the individual components of the potential energy are analyzed, and chemical intuition is reflected in the independent behavior of the three energy terms Eintra A (intra-atomic),' Vcl AA (electrostatic) an' Vx AA (exchange), in contrast to standard force fields.

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

Effects of Photovoltaic Module Materials and Design on Module Deformation Under Load

Static structural finite element models of an aluminum-framed crystalline silicon (c-Si) photovoltaic (PV) module and a glass-glass thin film PV module were constructed and validated against experimental measurements of deflection under uniform pressure loading. Parametric analyses using Latin Hypercube Sampling (LHS) were performed to propagate simulation input uncertainties related to module material properties, dimensions, and manufacturing tolerances into expected uncertainties in simulated deflection predictions. This exercise verifies the applicability and validity of finite element modeling for predicting mechanical behavior of solar modules across architectures and enables computational models to be used with greater confidence in assessment of module mechanical stressors and design for reliability. Sensitivity analyses were also performed on the uncertainty quantification data sets using linear correlation coefficients to elucidate the key parameters influencing module deformation. This information has implications on which materials or parameters may be optimized to best increase module stiffness and reliability, whether the key optimization parameters change with module architecture or loading magnitudes, and whether parameters such as frame design and racking must be replicated in reduced-scale reliability studies to adequately capture full module mechanical behavior.

14 SOLAR ENERGY↗
DOE OSTI2024

Hybrid Parameter Search and Dynamic Model Selection for Mixed-Variable Bayesian Optimization

Herein this article presents a new type of hybrid model for Bayesian optimization (BO) adept at managing mixed variables, encompassing both quantitative (continuous and integer) and qualitative (categorical) types. Our proposed new hybrid models (named hybridM) merge the Monte Carlo Tree Search structure (MCTS) for categorical variables with Gaussian Processes (GP) for continuous ones. hybridM leverages the upper confidence bound tree search (UCTS) for MCTS strategy, showcasing the tree architecture’s integration into Bayesian optimization. Our innovations, including dynamic online kernel selection in the surrogate modeling phase and a unique UCTS search strategy, position our hybrid models as an advancement in mixed-variable surrogate models. Numerical experiments underscore the superiority of hybrid models, highlighting their potential in Bayesian optimization.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

A software‐defined networks ‐based measurement method of network traffic for 6G technologies

Abstract In software‐defined networks (SDN) for 6G technologies, the controller should accurately and efficiently measure the flow traffic in switches for traffic engineering. Fine‐grained flow measurement can more accurately describe the traffic in the network, but it also consumes much more resources. To reduce the overhead incurred in the measurement process and obtain the approximate fine‐grained measurements, we propose a novel lightweight measurement scheme that runs in the controller. The novel lightweight measurement architecture consists of two parts: coarse‐grained measurement and interpolation‐optimization. In the first part, based on the SDN architecture, we use the pull‐based random sampling method to quickly obtain the coarse‐grained measurement of flow traffic through OpenFlow protocol. In the second part, we insert some discrete values into the coarse‐grained measurement with the interpolation theory, then we optimize interpolation results until finding the optimal fine‐grained flow traffic measurement by utilizing the multiconstraint method. We verified the feasibility of the proposed measurement method, and simulation results show that the measurement error of the proposed method is under 25%, but the flow measurement overhead of this method occupies only 3.3% compared with that of the fine‐grained method.

Huo, Liuwei↗