Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “adaptive learning”

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 1,549 records · Page 86

Adaptive supervisory control of remote manipulation

The command language by which an operator exerts supervisory control over a general purpose remote manipulator should be designed to accommodate certain characteristics of human performance if there is to be effective communication between the operator and the machine. Some of the ways in which people formulate tasks, use language, learn and make errors are discussed and design implications are drawn. A general approach to command language design is suggested, based on the notion matching the operator's current task schema or context by appropriate program structures or 'frames' in the machine.

Ferrell, W. R.↗

Adaptive Fuzzy Systems in Computational Intelligence

In recent years, the interest in computational intelligence techniques, which currently includes neural networks, fuzzy systems, and evolutionary programming, has grown significantly and a number of their applications have been developed in the government and industry. In future, an essential element in these systems will be fuzzy systems that can learn from experience by using neural network in refining their performances. The GARIC architecture, introduced earlier, is an example of a fuzzy reinforcement learning system which has been applied in several control domains such as cart-pole balancing, simulation of to Space Shuttle orbital operations, and tether control. A number of examples from GARIC's applications in these domains will be demonstrated.

Berenji, Hamid R.↗

Grid-Interactive Multi-Zone Building Control Using Reinforcement Learning with Global-Local Policy Search: Preprint

In this paper, we develop a grid-interactive multi-zone building controller based on a deep reinforcement learning (RL) approach. The controller is designed to facilitate building operation during normal conditions and demand response events, while ensuring occupants comfort and energy efficiency. We leverage a continuous action space RL formulation, and devise a two-stage global-local RL training framework. In the first stage, a global fast policy search is performed using a gradient-free RL algorithm. In the second stage, a local fine-tuning is conducted using a policy gradient method. In contrast to the state-of-the-art model predictive control (MPC) approach, the proposed RL controller does not require complex computation during real-time operation and can adapt to non-linear building models. We illustrate the controller performance numerically using a five-zone commercial building.

30 DIRECT ENERGY CONVERSION↗

Scalability analysis of heavy-duty gas turbines using data-driven machine learning

With the increasing integration of variable renewable energy sources into power systems, the role of flexible power generation technologies like gas turbines (GT) in rapid grid balancing remains crucial. This sustained importance underscores the need for scaled and precise modeling of GT to ensure effective integration within evolving energy frameworks. While physics-driven GT models integrate thermodynamics, fluid dynamics, and combustion principles, they often rely on approximate mathematical representations to accommodate scaling that may not capture the actual complex dynamics for GTs and inertial effects associated to GTs with different ratings. In this study, a data-driven model is proposed using machine learning (ML) techniques to conduct GT scalability analysis and performance evaluation with high accuracy. The ML model, trained on data from various operating conditions and performance parameters, aims to uncover intricate relationships and patterns, resembling GT characteristics at different scales (ratings). The model is developed to capture complex system interaction and to adapt to changing operational scenarios at different capacities, providing valuable insights of power system dynamics. In this study, the real-time digital simulator platform was employed to generate training data for the ML model and assess its dynamic characteristics. The ultimate objective was to develop a detailed modeling framework based on governing equations and data-driven ML capable of predicting key performance indicators, in thermal systems such as GTs, including power output, speed, fuel consumption, and exhaust temperature under diverse operating conditions at different scales. The developed ML framework demonstrated high accuracy, with mean relative errors for GT power prediction, reference speed, exhaust temperature, and compressor pressure ratio (CPR) parameters consistently below 0.1% across typical load fluctuation scenarios. Maximum deviations were limited to approximately 0.5 K for exhaust temperature and 0.009 for CPR, underscoring the model’s ability to replicating dynamic GT behavior with high precision. The adaptability of the ML model enables its application across diverse operational conditions and its extension to other thermal systems. By leveraging advanced ML techniques, this study presents a robust and scalable modeling framework that enhances GT simulation precision, facilitating improved integration into evolving power systems.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Accelerating data acquisition with FPGA-based edge machine learning: a case study with LCLS-II

New scientific experiments and instruments generate vast amounts of data that need to be transferred for storage or further processing, often overwhelming traditional systems. Edge machine learning (EdgeML) addresses this challenge by integrating machine learning (ML) algorithms with edge computing, enabling real-time data processing directly at the point of data generation. EdgeML is particularly beneficial for environments where immediate decisions are required, or where bandwidth and storage are limited. In this paper, we demonstrate a high-speed configurable ML model in a fully customizable EdgeML system using a field programmable gate array (FPGA). Our demonstration focuses on an angular array of electron spectrometers, referred to as the ‘CookieBox,’ developed for the Linac Coherent Light Source II project. The EdgeML system captures 51.2 Gbps from a 6.4 GS s −1 analog to digital converter and is designed to integrate data pre-processing and ML inside an FPGA. Our implementation achieves an inference latency of 0.2 µs for the ML model, and a total latency of 0.4 µs for the complete EdgeML system, which includes pre-processing, data transmission, digitization, and ML inference. The modular design of the system allows it to be adapted for other instrumentation applications requiring low-latency data processing.

97 MATHEMATICS AND COMPUTING↗

Solving Seismic Wave Equations on Variable Velocity Models With Fourier Neural Operator

Here, in the study of subsurface seismic imaging, solving the acoustic wave equation is a pivotal component in existing models. The advancement of deep learning (DL) enables solving partial differential equations (PDEs), including wave equations, by applying neural networks to identify the mapping between the inputs and the solution. This approach can be faster than traditional numerical methods when numerous instances are to be solved. Previous works that concentrate on solving the wave equation by neural networks consider either a single velocity model or multiple simple velocity models, which is restricted in practice. Instead, inspired by the idea of operator learning, this work leverages the Fourier neural operator (FNO) to effectively learn the frequency domain seismic wavefields under the context of variable velocity models. We also propose a new framework paralleled FNO (PFNO) for efficiently training the FNO-based solver given multiple source locations and frequencies. Numerical experiments demonstrate the high accuracy of both FNO and PFNO with complicated velocity models in the OpenFWI datasets. Furthermore, the cross-dataset generalization test verifies that PFNO adapts to out-of-distribution velocity models. Finally, PFNO admits higher computational efficiency on large-scale testing datasets than the traditional finite-difference method. The aforementioned advantages endow the FNO-based solver with the potential to build powerful models for research on seismic waves.

58 GEOSCIENCES↗

Cookie-Jar: An Adaptive Re-configurable Framework for Wireless Network Infrastructures

5G advancements like Massive Multiple Input Multiple Output (MIMO) bring high capacity and low latency, but also intensify interference challenges. Static and dynamic coordination techniques address this, often at the cost of increased power draw. We introduce Cookie-Jar (CJ), an interference coordination (IC) framework using reinforcement learning for multi-goal optimization. By dynamically adjusting network, power, and topology parameters based on real-time conditions, CJ improves Signal to Noise and Interference Ratio (SINR) while minimizing power consumption. Simulated 5G experiments showcase CJ's potential, achieving a 15% SINR improvement with near-identical power draw compared to existing methods.

Network↗

Creating a Salt Batch: Challenges and Lessons Learned

CONCLUSION • The overall Salt Batch system has been honed through each iteration of the process • Increased communication across facilities and work groups has enabled the salt team to react swiftly to emergent items and identify improvement opportunities • Even the best plans require backup options – Emergent items can appear at any time during the process – Flexibility to adapt to the unexpected is a must-have team mindset • To date, every salt batch compiled has been qualified and approved as feed for SWPF – No feed break has occurred between the Tank Farm and SWPF

Goldblatt, Joshua B. [Savannah River National Labo↗

Visualization of hydraulic fracture using physics-informed clustering to process ultrasonic shear waves

Ultrasonic transmission is sensitive to the spatial variation in mechanical properties of materials due to the presence of cracks/fractures. Wave propagation through fractured media introduces changes in the frequency content, travel time and transmission coefficient of the wave. A workflow based on physics-informed unsupervised learning is developed to process the transmitted ultrasonic-shear waveforms to non-invasively visualize the geomechanical alterations due to hydraulic fracturing. Novelty of the work involves the assignment of both statistically consistent and physically consistent clusters to the measurements of shear waveforms acquired across the one axial and two frontal planes. Physically consistent/relevant information is incorporated by considering the travel time of the peak of spectral energy and transmission coefficient of the transmitted waveform. The proposed workflow generates maps of geomechanical alterations across the frontal and axial planes of the sample. The outputs of the workflow are in good agreement with independent techniques viz. acoustic emission and X-ray computed tomography. Finally, the proposed workflow can be adapted for improved fracture characterization in the subsurface when processing sonic-logging, cross-wellbore seismic or surface seismic waveform data.

42 ENGINEERING↗

A Multi-Objective Bayesian Optimized Human Assessed Multi-Target Generated Spectral Recommender System for Rapid Pareto Discoveries of Material Properties

Optimization for different tasks like material characterization, synthesis, and functional properties for desired applications over multi-dimensional control parameter and function spaces need a rapid strategic search through active learning. However, in all cases prior to optimization, the target material properties are assumed known and fixed, which mostly deviates from real-world scenarios in material synthesis. This can be critical for running expensive experiments on new materials, when the experimental results are fuzzy for any scientific outcomes due to improper target setting, ultimately wasting time and cost. The failure rate and cost are even higher over exploring on multi-target space, where we want to learn the pareto among multiple properties, to jointly optimize during material synthesis for desired applications. To address the challenge, here we introduce the human-operator attempt flexibility in the active learning based automated experiment framework, with generating multiple human assessed targets through a voting-based recommender system during real-time microscope measurements over the large material image space, sequentially learn/update multiple desired targets through a weighting system, and adaptively search in multiple material properties functional space for non-dominated pareto discoveries to maximize the custom structural similarity based acquisition function. We term this a multi-objective Bayesian optimized human assessed multi-target generated spectral recommender systems (MOBO-HAM-SRS). The approach has been demonstrated to peizoresponse force spectroscopy of a ferroelectric thin film, exploring with different kernels and acquisition functions. This work shows an advancement towards human-AI collaborated automated experiments, steering optimization trajectories through human overpowering AI at the early stage when uncertainty is high and AI overpowering human at the later stage with rapid exploration towards optimal goal, following human-assessed multiple targets properties.

Biswas, Arpan↗

Nuclear Theory from First Principles to Forefront Experiments (Final Report for DE-SC0018638)

The Lee research group is a part of the Nuclear Lattice Effective Field Theory Collaboration, which has developed and performed ab initio lattice simulations of nuclear structure, scattering, reactions, and many-body systems. The other senior members of the collaboration include Ulf-G. Meißner at Bonn/Julich, Evgeny Epelbaum and Hermann Krebs at Bochum, Timo Lahde and Thomas Luu at Julich, and Gautam Rupak at Mississippi State. Our letter “Ab initio alpha-alpha scattering” was featured in a Nature News and Views article. Another letter “Nuclear binding near a quantum phase transition” was highlighted in a Viewpoint article in the online APS journal Physics as well as a news article in the IOP publication Physics World (September 21, 2016). Our letter “Eigenvector continuation with subspace learning” was also highlighted a Synopsis article in Physics. There are many promising ab initio approaches being used to calculate the properties of few-and many-nucleon systems. This includes the no-core shell model, symmetry-adapted no-core shell model quantum Monte Carlo, auxiliary-field diffusion Monte Carlo, self-consistent Green’s functions, many-body perturbation theory, in-medium similarity renormalization group, and coupled cluster methods. Lattice effective field theory is another ab initio approach which combines the framework of effective field theory with lattice Monte Carlo methods to allow favorable scaling from few- to many-body systems. Perhaps the most important aspect of lattice effective field theory is that its strengths and weaknesses are orthogonal to that of other ab initio methods. For example, lattice effective field theory has little difficulty in probing cluster structures and collectivity, while such features are much more difficult using other methods. Furthermore it can be used to compute superfluid condensate fractions as well as the phase diagram of strongly matter and the density and temperature dependence of clustering. Lattice effective field theory was first used in simulations of infinite nuclear matter and infinite neutron matter with pions and without pions. In addition to the efforts by our collaboration, there have been recent efforts by other groups as well.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Environmentally Adaptive, Multiband Software-Defined-Radar for Monitoring of Item of Interest in a Dynamically Cluttered Room

High-resolution multi-frequency radars when networked together, form a robust and seamless monitoring system for high-valued items. The multi-look-direction radar network investigated by LLNL and DSI, operates at 77 GHz and 5.8GHz, and is capable of detection at centimeter resolution movement of objects of interest. This dual frequency radar (unlike optical methods) can operate under various environments with conditions such a smoke, dust, and other natural or manmade obscurations. In addition, the multiband network radar is based on low-cost FCC approved EM specifications and can be scaled with the dimensions of the room and objects under consideration by user-defined inputs. Furthermore, the underlying radar signal processing based on software-defined radar engine is adaptive to its operational environment, where operators can input the size of the facility and object of interest and the distance between the object and radar. Finally, this multi-frequency radar employs a host of change detection and machine learning algorithms to reach performance levels in terms of high probability of detection and low false alarm rates while the monitoring state of the object can be reported remotely.

42 ENGINEERING↗

Re-engineering the Multimission Command System at the Jet Propulsion Laboratory

The Operations Engineering Lab (OEL) at JPL has developed the multimission command system as part of JPL's Advanced Multimission Operations System. The command system provides an advanced multimission environment for secure, concurrent commanding of multiple spacecraft. The command functions include real-time command generation, command translation and radiation, status reporting, some remote control of Deep Space Network antenna functions, and command file management. The mission-independent architecture has allowed easy adaptation to new flight projects and the system currently supports all JPL planetary missions (Voyager, Galileo, Magellan, Ulysses, Mars Pathfinder, and CASSINI). This paper will discuss the design and implementation of the command software, especially trade-offs and lessons learned from practical operational use. The lessons learned have resulted in a re-engineering of the command system, especially in its user interface and new automation capabilities. The redesign has allowed streamlining of command operations with significant improvements in productivity and ease of use. In addition, the new system has provided a command capability that works equally well for real-time operations and within a spacecraft testbed. This paper will also discuss new development work including a multimission command database toolkit, a universal command translator for sequencing and real-time commands, and incorporation of telecommand capabilities for new missions.

Alexander, Scott↗

A Mixed Integer Efficient Global Optimization Algorithm with Multiple Infill Strategy - Applied to a Wing Topology Optimization Problem

With the advancement in high performance computing and numerical optimization techniques,engineering design optimization problems are becoming more complex, larger scale,higher fidelity, and computationally more demanding, requiring longer run times than ever before. There exists methodologies and techniques that can address some of these challenges but very few can address all, and most are limited in the extent that these concerns can be addressed. With the goal of addressing such challenging engineering problems, we developed anew optimization framework, named AMIEGO, that combines concepts from surrogate-based optimization approaches, gradient-based numerical methods, Partial Least Squares, evolutionary algorithms, and Branch-and-Bound, providing newer capabilities that were not previouslyperceived. However, the original version of this framework, in the process of adaptive samplingto explore and exploit the design space, finds only a single sample point per iteration. The efforthere builds upon this previously developed optimization framework to include multiple infillsampling capability that combines the concept of generalized expected improvement function,unsupervised learning, and multi-objective evolutionary technique. To demonstrate, AMIEGOwith the multiple infill capability (called AMIEGO-MIMOS) solves a series of increasingly difficultengineering design optimization problems. The results reveal the performance of the newapproach is problem dependent. When applied to a ten-bar truss problem, the newly proposedmultiple infill strategy consistently leads to a better design solutions when compared to theexisting CPTV method (implemented with the context of the AMIEGO framework). On theother hand, when applied to a mixed-integer high fidelity wing topology optimization problem- MIMOS, despite showing a steeper convergence at the start, eventually leads to an inferiorsolution as compared to CPTV approach. These results also reveal that a small number ofstarting points, in general, are sufficient to lead to a good overall solution.

Mixed-integer optimization↗

Adaptive Data Screening for Multi-Angle Polarimetric Aerosol and Ocean Color Remote Sensing Accelerated by Automatic Differentiation

Remote sensing measurements from multi-angle polarimeters (MAPs) contain rich aerosol microphysical property information, and these sensors have been used to perform retrievals in optically complex atmosphere and ocean systems. Previous studies have concluded that, generally, five moderately separated viewing angles in each spectral band provide sufficient accuracy for aerosol property retrievals, with performance gradually saturating as angles are added above that threshold. The Hyper-Angular Rainbow Polarimeter (HARP) instruments provide high angular sampling with a total of 90-120 unique angles across four bands, a capability developed mainly for liquid cloud retrievals. In practice, not all view angles are optimal for aerosol retrievals due to impacts of clouds, sun glint, and other impediments. The many viewing angles of HARP can provide resilience to these effects, if the impacted views are screened from the dataset, as the remaining views may be sufficient for successful analysis. In this study, we discuss how the number of available viewing angles impacts aerosol and ocean color retrieval uncertainties, as applied to two versions of the HARP instrument. AirHARP is an airborne prototype that was deployed in the ACEPOL field campaign, while HARP2 is an instrument in development for the upcoming NASA Plankton, Aerosol, Cloud, ocean Ecosystem (PACE) mission. Based on synthetic data, we find that a total of 20-30 angles across all bands (i.e. five to eight viewing angles per band) are sufficient to achieve good retrieval performance. Following from this result, we develop an adaptive multi-angle polarimetric data screening (MAPDS) approach to evaluate data quality by comparing measurements with their best-fitted forward model. The FastMAPOL retrieval algorithm is used to retrieve scene geophysical values, by matching an efficient, deep learning-based, radiative transfer emulator to observations. The data screening method effectively identifies and removes viewing angles affected by thin cirrus clouds and other anomalies, improving retrieval performance. This was tested with AirHARP data, and we found agreement with the High Spectral Resolution Lidar-2 (HSRL-2) aerosol data. The data screening approach can be applied to modern satellite remote sensing missions, such as PACE, where a large amount of multi-angle, hyperspectral, polarimetric measurements will be collected.

multi-angle polarimeter↗

2010 Plant Molecular Biology Gordon Research Conference

The Plant Molecular Biology Conference has traditionally covered a breadth of exciting topics and the 2010 conference will continue in that tradition. Emerging concerns about food security have inspired a program with three main themes: (1) genomics, natural variation and breeding to understand adaptation and crop improvement, (2) hormonal cross talk, and (3) plant/microbe interactions. There are also sessions on epigenetics and proteomics/metabolomics. Thus this conference will bring together a range of disciplines, will foster the exchange of ideas and enable participants to learn of the latest developments and ideas in diverse areas of plant biology. The conference provides an excellent opportunity for individuals to discuss their research because additional speakers in each session will be selected from submitted abstracts. There will also be a poster session each day for a two-hour period prior to dinner. In particular, this conference plays a key role in enabling students and postdocs (the next generation of research leaders) to mingle with pioneers in multiple areas of plant science.

59 BASIC BIOLOGICAL SCIENCES↗

Variable rate neural compression for sparse detector data

Particle colliders produce data at extraordinary rates, posing major challenges for transmission and storage. High-throughput compression algorithms are therefore essential. In the sPHENIX experiment taking data at the Relativistic Heavy Ion Collider, a time projection chamber records three-dimensional (3D) particle trajectories that are highly sparse, making conventional learning-free lossy compression ineffective. Convolutional neural networks have surpassed traditional methods in compression ratio and accuracy. However, they fail to exploit sparsity for efficiency. To address these gaps, we present BCAE-VS, a bicephalous convolutional autoencoder with variable compression ratio for sparse data, which adapts compression to input complexity through key-point identification and sparse convolution. BCAE-VS achieves higher accuracy and compression ratios than prior neural approaches while being orders of magnitude smaller. Moreover, its throughput increases with sparsity—a property not observed in other methods. Although it was developed for collider experiments, BCAE-VS readily extends to other sparse data domains, such as light detection and ranging (LiDAR) sensing and 3D microscopy.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Machine learning for nonintrusive model order reduction of the parametric inviscid transonic flow past an airfoil

Fluid flow in the transonic regime finds relevance in aerospace engineering, particularly in the design of commercial air transportation vehicles. Computational fluid dynamics models of transonic flow for aerospace applications are computationally expensive to solve because of the high degrees of freedom as well as the coupled nature of the conservation laws. While these issues pose a bottleneck for the use of such models in aerospace design, computational costs can be significantly minimized by constructing special, structure-preserving surrogate models called reduced-order models. In this work, we propose a machine learning method to construct reduced-order models via deep neural networks and we demonstrate its ability to preserve accuracy with a significantly lower computational cost. In addition, our machine learning methodology is physics-informed and constrained through the utilization of an interpretable encoding by way of proper orthogonal decomposition. Application to the inviscid transonic flow past the RAE2822 airfoil under varying freestream Mach numbers and angles of attack, as well as airfoil shape parameters with a deforming mesh, shows that the proposed approach adapts to high-dimensional parameter variation well. Notably, the proposed framework precludes the knowledge of numerical operators utilized in the data generation phase, thereby demonstrating its potential utility in the fast exploration of design space for diverse engineering applications. Comparison against a projection-based nonintrusive model order reduction method demonstrates that the proposed approach produces comparable accuracy and yet is orders of magnitude computationally cheap to evaluate, despite being agnostic to the physics of the problem.

97 MATHEMATICS AND COMPUTING↗