Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Parallel 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 1,153 records · Page 64
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

IDAES-PSE 2.7.0 Release

The Institute for the Design of Advanced Energy Systems (IDAES) Integrated Platform is a versatile computational environment offering extensive process systems engineering (PSE) capabilities for optimizing the design and operation of complex, interacting technologies and systems. IDAES enables users to efficiently search vast, complex design spaces to discover the lowest cost solutions while supporting the full process modeling lifecycle, from conceptual design to dynamic optimization and control. The extensible, open platform empowers users to create models of novel processes and rapidly develop custom analyses, workflows, and end-user applications. IDAES-PSE 2.7.0 Release Highlights New features: AutoScaler and CustomScalerBase classes: Such tools are the core of the new scaling framework being implemented in IDAES. Wider adoption of scaling tools among users will result in quicker and more robust model solutions. Scaler for equilibrium reactor and saponification properties: These scaler models are examples to follow for how to use the new scaling tools. ONNX Surrogate support from Optimization & Machine Learning Toolkit (OMLT): ONNX is an open standard format to save and load ML/AI models that is widely supported by all major frameworks. This capability makes it easier for IDAES users to create surrogate models and use them without having to support each framework individually. 1D Membrane Model for CO2 Capture and Utilization: Supports ongoing efforts for modeling and optimizing polymer membrane processes for CO2 capture and conversion into formic acid. StreamScaler unit model: Unrelated to the CustomScalerBase, this unit model allows a stream’s extensive variables to be scaled by a fixed factor. This allows streams being processed by multiple units in parallel to be scaled down to unit scale and scaled back up to process scale. Bug fixes or improvements: Scaling, EoS, Diagnostics tool, Modular Properties, tests & documentation Deprecations: Old Cubic EoS

AS↗
NASA NTRS1984

Acoustooptic linear algebra processors - Architectures, algorithms, and applications

Architectures, algorithms, and applications for systolic processors are described with attention to the realization of parallel algorithms on various optical systolic array processors. Systolic processors for matrices with special structure and matrices of general structure, and the realization of matrix-vector, matrix-matrix, and triple-matrix products and such architectures are described. Parallel algorithms for direct and indirect solutions to systems of linear algebraic equations and their implementation on optical systolic processors are detailed with attention to the pipelining and flow of data and operations. Parallel algorithms and their optical realization for LU and QR matrix decomposition are specifically detailed. These represent the fundamental operations necessary in the implementation of least squares, eigenvalue, and SVD solutions. Specific applications (e.g., the solution of partial differential equations, adaptive noise cancellation, and optimal control) are described to typify the use of matrix processors in modern advanced signal processing.

Casasent, D.↗
NASA NTRS1988

An improved simulated annealing algorithm for standard cell placement

Simulated annealing is a general purpose Monte Carlo optimization technique that was applied to the problem of placing standard logic cells in a VLSI ship so that the total interconnection wire length is minimized. An improved standard cell placement algorithm that takes advantage of the performance enhancements that appear to come from parallelizing the uniprocessor simulated annealing algorithm is presented. An outline of this algorithm is given.

Jones, Mark↗
NASA NTRS1993

Analog Processor To Solve Optimization Problems

Proposed analog processor solves "traveling-salesman" problem, considered paradigm of global-optimization problems involving routing or allocation of resources. Includes electronic neural network and auxiliary circuitry based partly on concepts described in "Neural-Network Processor Would Allocate Resources" (NPO-17781) and "Neural Network Solves 'Traveling-Salesman' Problem" (NPO-17807). Processor based on highly parallel computing solves problem in significantly less time.

Duong, Tuan A.↗
NASA NTRS1993

Controls-structures-interaction dynamics during RCS control of the Orbiter/SRMS/SSF configuration

During the assembly flights of the Space Station Freedom (SSF), the Orbiter will either dock with the SSF and retract to the final berthed position, or will grapple the SSF using the Shuttle Remote Manipulator System (SRMS) and maneuver the SRMS coupled vehicles to their final berthed position. The SRMS method is expected to take approximately one to one and a half hours to complete and require periodic attitude corrections by either the Orbiter or the SSF reaction control system (RCS) or continuous control by a control moment gyro (CMG) system with RCS desaturation as required. Free drift of the attached vehicles is not currently thought to be acceptable because the desired system attitude will quickly deteriorate due to unbalanced gravity gradient and aerodynamic torques resulting in power generation problems, thermodynamic control problems, and communications problems. This paper deals with the simulation and control of the SRMS during trunnion/latch interaction dynamics and during RCS maneuvers. The SRMS servo drive joints have highly non-linear elastic characteristics which tend to degrade sensitive control strategies. In addition the system natural frequencies are extremely low and depend on the drive joint deflections and SRMS geometric position. The lowest mean period of oscillation for the Orbiter/SRMS/SSF(MB6) system in brakes hold mode positioned near the final berthed position is approximately 120 seconds. A detailed finite element model of the SRMS has been developed and used in a newly developed SRMS systems dynamics simulation to investigate the non-linear transient response dynamics of the Orbiter/SRMS/SSF systems. The present SRMS control strategy of brakes only recommended by the Charles Draper Labs is contrasted with a robust controller developed by the authors. The robust controller uses an optimal inear quadratic regulator (LQR) to optimally place the closed-loop poles of a multivariable continuous-time system within the common region of an open sector with the sector angle plus or minus 45 degrees from the negative real axis, and the left-hand side of a parallel to the imaginary axis in the complex s-plane. This guarantees that the critical damping ratio for the desired control modes is equal to or in excess of 0.707. The matrix sign function is used for solving the Riccati equations which appear in the controller design procedure. Fast and stable algorithms have recently been developed for the computation of the matrix sign function. Simulation results are given which demonstrate the potential CSI involvement for the current SRMS control system and the proposed control system.

Schliesing, J. A.↗
NASA NTRS1993

Computational mechanics analysis tools for parallel-vector supercomputers

Computational algorithms for structural analysis on parallel-vector supercomputers are reviewed. These parallel algorithms, developed by the authors, are for the assembly of structural equations, 'out-of-core' strategies for linear equation solution, massively distributed-memory equation solution, unsymmetric equation solution, general eigensolution, geometrically nonlinear finite element analysis, design sensitivity analysis for structural dynamics, optimization search analysis and domain decomposition. The source code for many of these algorithms is available.

Storaasli, Olaf O.↗
NASA NTRS1993

Extended ecosystem signatures with application to Eos synergism requirements

The primary objective is to define the advantages of synergistically combining optical and microwave remote sensing measurements for the determination of biophysical properties important in ecosystem modeling. This objective was approached in a stepwise fashion starting with ground-based observations of controlled agricultural and orchard canopies and progressing to airborne observations of more natural forest ecosystems. This observational program is complemented by a parallel effort to model the visible reflectance and microwave scattering properties of composite vegetation canopies. The goals of the modeling studies are to verify our basic understanding of the sensor-scene interaction physics and to provide the basis for development of inverse models optimized for retrieval of key biophysical properties. These retrieval algorithms can then be used to simulate the expected performance of various aspects of Eos including the need for simultaneous SAR and HIRIS observations or justification for other (non-synchronous) relative timing constraints and the frequency, polarization, and angle of incidence requirements for accurate biophysical parameter extractions. This program completed a very successful series of truck-mounted experiments, made remarkable progress in development and validation of optical reflectance and microwave scattering models for vegetation, extended the scattering models to accommodate discontinuous and periodic canopies, developed inversion approaches for surface and canopy properties, and disseminated these results widely through symposia and journal publications. In addition, the third generation of the computer code for the microwave scattering models was provided to a number of other US, Canadian, Australian, and European investigators who are currently presenting and publishing results using the MIMICS research code.

Ulaby, Fawwaz T.↗
NASA NTRS2008

Varying the Divergence of Multiple Parallel Laser Beams

A provision for controlled variation of the divergence of a laser beam or of multiple parallel laser beams has been incorporated into the design of a conceptual free-space optical-communication station from which the transmitted laser beam(s) would be launched via a telescope. The original purpose to be served by this provision was to enable optimization, under various atmospheric optical conditions, of the divergence of a laser beam or beams transmitted from a ground station to a spacecraft.

Kovalik, Joseph M.↗
NASA NTRSDate not supplied

X-Ray Imagery as the Record of All Data of Interest in Hypervelocity Impact Fragment Studies

Laboratory study of hypervelocity spacecraft fragmentation has traditionally involved the collection and analysis of fragments that were caught in deceleration material surrounding the impact. This process has typically involved the disintegration of the catchment material either through chemical dissolution, or through physical excavation to recover the fragments. Due to the scale of the three impact tests—the Satellite Orbital Debris Characterization Impact Test (SOCIT), the DebriSat satellite impact test, and the DebrisLV launch vehicle impact test—the latter two using more than 12 cubic meters of polyurethane foam to capture the fragments, hese projects have used x-ray imagery to precisely locate and thus, to more efficiently extract fragments in the soft-catch material. Three years into the DebriSat fragment extraction process, a side study was initiated to explore what additional information could be discerned from the x-rays, with significant results. This study was instrumental to a rapid replacement and retooling as the project was forced to replace the x-ray system around which the extraction process had been based. The revised process continues to map the debris for extraction. The project has, in parallel, systematically addressed the limits/tolerances of what x-rays can reveal about size, shape, density, mass, velocity, energy, and deformation/damage of the fragment during the deceleration in the catchment material while replicating the original extraction mapping function. All of these features have been optimized or have sufficient understanding to characterize the basic factors that will define a complete data set extracted solely from x-ray imagery. It is an ideal time to develop such a process, with extracted fragments providing “ground truth” against image-only data, and abundant available imagery of the same fragments under both the prior and replacement x-ray technologies, which have several fundamentally different characteristics. This paper addresses the types and quality of hypervelocity fragmentation data that can be and has been extracted from x-rays. It further addresses the question of whether and under what circumstances future hypervelocity experiments can use x-ray methods to largely—or to completely—avoid the extraction process in recording all appropriate results. Lastly, this paper addresses lessons learned and how future efforts can be further optimized.

John B. Bacon↗
NASA NTRS2023

Multiphysics Modeling of Electrode Dissolution under Hydrodynamic Conditions in Low Conductivity Water

Efficient plug-flow electrochemical reactors are characterized by their ability to effectively convert species with significant ionic strength and/or with the assistance of a well-behaved electrolyte. Because of the classic electroconductivity requirement, electrochemical reactors are not particularly attractive options for applications with low-conductivity conditions, especially for low-pressure feeds. However, these reactors can still find application in dedicated processes such as ultra-clean water conditioning and biological-coupled separation systems. Consequently, a multi-physics model was developed using COMSOL Multiphysics to characterize different reactor-design conditions based on the Tertiary Current Distribution which accounts for the effects of expected variations in electrolyte composition and ionic strength on the electrochemical process, as well as solution resistance and electrode kinetics. The modelling framework presented here employs single-phase laminar fluid flow, the Nernst-Planck equation, the water-based electroneutrality condition, and concentration-dependent overpotentials. This investigation particularly explores the electrolysis process of “anodic dissolution,” in which elemental species dissociate from the solid matrix of the electrode and enter the liquid phase of the electrolyte as soluble ions. The reactor configuration of interest has a rectangular parallel-electrode design and is operated galvanostatically. A series of parametric studies are carried out to inspect the response of the system when hydrodynamic, kinetic, and geometric conditions are changed. The parametric sweep resulted in variable effluent concentrations and system voltage, which reveal underlaying optimization patterns for electrode dissolution in low conductivity water.

Multiphysics↗
DOE OSTI2025

Robustness of Deep Learning Classification to Adversarial Input on GPUs: Asynchronous Parallel Accumulation Is a Source of Vulnerability

The ability of machine learning (ML) classification models to resist small, targeted input perturbations—known as adversarial attacks—is a key measure of their safety and reliability. We show that floating-point non associativity (FPNA) coupled with asynchronous parallel programming on GPUs is sufficient to result in misclassification, without any perturbation to the input. Additionally, we show that this misclassification is particularly significant for inputs close to the decision boundary and that standard adversarial robustness results may be overestimated up to 4.6 when not considering machine-level details. We first study a linear classifier, before focusing on standard Graph Neural Network (GNN) architectures and datasets used in robustness assessments. We develop a novel black-box attack using Bayesian optimization to discover external workloads that can change the instruction scheduling which bias the output of reductions on GPUs and reliably lead to misclassification. Motivated by these results, we present a new learnable permutation (LP) gradient-based approach to learning floating-point operation orderings that lead to misclassifications. The LP approach provides a worst-case estimate in a computationally efficient manner, avoiding the need to run identical experiments tens of thousands of times over a potentially large set of possible GPU states or architectures. Finally, using instrumentation-based testing, we investigate parallel reduction ordering across different GPU architectures under external background workloads, when utilizing multi-GPU virtualization, and when applying power capping. Our results demonstrate that parallel reduction ordering varies significantly across architectures under the first two conditions, substantially increasing the search space required to fully test the effects of this parallel scheduler-based vulnerability. These results and the methods developed here can help to include machine-level considerations into adversarial robustness assessments, which can make a difference in safety and mission critical applications.

Shanmugavelu, Sanjif [Maxeler Technologies, a Groq↗
DOE OSTI2022

Transience of the Retinal Output Is Determined by a Great Variety of Circuit Elements

Retinal ganglion cells (RGCs) encrypt stimulus features of the visual scene in action potentials and convey them toward higher visual centers in the brain. Although there are many visual features to encode, our recent understanding is that the ~46 different functional subtypes of RGCs in the retina share this task. In this scheme, each RGC subtype establishes a separate, parallel signaling route for a specific visual feature (e.g., contrast, the direction of motion, luminosity), through which information is conveyed. The efficiency of encoding depends on several factors, including signal strength, adaptational levels, and the actual efficacy of the underlying retinal microcircuits. Upon collecting inputs across their respective receptive field, RGCs perform further analysis (e.g., summation, subtraction, weighting) before they generate the final output spike train, which itself is characterized by multiple different features, such as the number of spikes, the inter-spike intervals, response delay, and the rundown time (transience) of the response. These specific kinetic features are essential for target postsynaptic neurons in the brain in order to effectively decode and interpret signals, thereby forming visual perception. We review recent knowledge regarding circuit elements of the mammalian retina that participate in shaping RGC response transience for optimal visual signaling.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

A GPU-Accelerated Population Generation, Sorting, and Mutation Kernel for an Optimization-Based Causal Inference Model

We develop a GPU-accelerated machine learning generative adversarial network model that can be used with observational data for the purpose of constructing causal inferences. The theoretical basis of our machine learning model is novel and is conceptualized to be operable and scalable for high performance computing platforms. Our GPU-accelerated code enables large-scale parallelization of the computation within a common and accessible computing environment. This will expand the reach of our model and empower research in new substantive domains while maintaining the underlying theoretical properties.

Cho, Wendy K. Tam↗
DOE OSTI2020

A Two-Stage Decomposition Approach for AC Optimal Power Flow

The alternating current optimal power flow (AC-OPF) problem is critical to power system operations and planning, but it is generally hard to solve due to its nonconvex and large-scale nature. Furthermore, this paper proposes a scalable decomposition approach in which the power network is decomposed into a master network and a number of subnetworks, where each network has its own AC-OPF subproblem. This formulates a two-stage optimization problem and requires only a small amount of communication between the master and subnetworks. The key contribution is a smoothing technique that renders the response of a subnetwork differentiable with respect to the input from the master problem, utilizing properties of the barrier problem formulation that naturally arises when subproblems are solved by a primal-dual interior-point algorithm. Consequently, existing efficient nonlinear programming solvers can be used for both the master problem and the subproblems. The advantage of this framework is that speedup can be obtained by processing the subnetworks in parallel, and it has convergence guarantees under reasonable assumptions. The formulation is readily extended to instances with stochastic subnetwork loads. Numerical results show favorable performance and illustrate the scalability of the algorithm which is able to solve instances with more than 11 million buses.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS2023

Modeling and Simulation of a Parallel Hybrid Electric Regional Aircraft for the Electrified Powertrain Flight Demonstration (EPFD) Program

This paper presents a parametric modeling and integrated aircraft sizing and synthesis approach for a charge depleting parallel hybrid electric architecture. The developed models are integrated within the baseline thin-haul and regional aircraft. In addition to the physical architecture, different modes of operation enabled by propulsion system electrification are also modeled parametrically. The modes of operation presented in this paper are the peak power shaving, climb power electric boost, in-flight battery recharging, and electric taxi. The sizing of the powertrain and the aircraft are performed within the multidisciplinary analysis and optimization environment, E-PASS. The consideration of the physical system and its operation together provides a holistic approach where the propulsion system and the airframe are designed under an optimized power and energy management strategy. The parametric nature of the work enables the design space exploration for electrification and lays the groundwork for future technology projection and uncertainty quantification studies. The developed capability is generic and can be applied on other aircraft classes. The work is done as part of the Electrified Powertrain Flight Demonstration program.

electrified powertrain flight demonstration↗
DOE OSTI2024

A high efficiency rooftop air conditioning system using multi-speed compressors

This study delineates a meticulous exploration of technologies to enhance the energy efficiency of rooftop air conditioning units, employing the DOE/ORNL heat pump design model for comprehensive engineering design and optimization. A baseline rooftop air conditioning unit, featuring a 13 ton (45.7 kW) cooling capacity and a 17.9 integrated energy efficiency ratio, served as the point of departure for substantive efficiency enhancements. Key modifications included the consolidation of two refrigerant circuits into one, integrating three parallel 2-stage (dual-speed) compressors, fan replacements with high-efficiency substitutes. Notably, a lower global warming potential refrigerant, R452B, was evaluated as a substitute for R-410A, demonstrating better performance in the lab prototype. Further, the achieved measured integrated energy efficiency ratio of 21.4 in the lab prototype surpassed the baseline integrated energy efficiency ratio. Comparative evaluations between R410A and R452B indicated heightened efficiency with the latter, showcasing a lab-demonstrated integrated energy efficiency ratio of 22.4 at the rated capacity of 13.8 ton (48.5 kW) and 23.9 integrated energy efficiency ratio at the rated capacity of 10 ton (35.2 kW). This research underscores the successful development of a rigorous, energy efficient rooftop air conditioning unit prototype with noteworthy environmental and economic implications.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2022

Crystal structure of diclazuril, C 17 H 9 Cl 3 N 4 O 2

The crystal structure of diclazuril has been solved and refined using synchrotron X-ray powder diffraction data, and optimized using density functional theory techniques. Diclazuril crystallizes in space group P2 1 /a (#14) with a = 27.02080(18), b = 11.42308(8), c = 5.36978(5) Å, β = 91.7912(7)°, V = 1656.629(15) Å 3 , and Z = 4. The crystal structure consists of layers of molecules parallel to the ac-plane. A strong N–H∙∙∙O hydrogen bond links the molecules into dimers along the a-axis with a graph set R2,2(8). The powder pattern has been submitted to ICDD for inclusion in the Powder Diffraction File™ (PDF®).

36 MATERIALS SCIENCE↗
DOE OSTI2021

Evaluating CUDA Portability with HIPCL and DPCT

HIPCL is expanding the scope of the CUDA portability route from an AMD platform to an OpenCL platform. In the meantime, the Intel DPC++ Compatibility Tool (DPCT) is migrating a CUDA program to a data parallel C++ (DPC++) program. Towards the goal of portability enhancement, we evaluate the performance of the CUDA applications from Rodinia, SHOC, and proxy applications ported using HIPCL and DPCT on Intel GPUs. After profiling the ported programs, we aim to understand their performance gaps, and optimize codes converted by DPCT to improve their performance. The open-source repository for the CUDA, HIP, and DPCT programs will be useful for the development of a translator.

Jin, Zheming↗