Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “learning efficiency”

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 1,585 records · Page 88

Reconstruction of Large Radius Tracks with the Exa.TrkX pipeline

Particle tracking is a challenging pattern recognition task at the Large Hadron Collider (LHC) and the High Luminosity-LHC. Conventional algorithms, such as those based on the Kalman Filter, achieve excellent performance in reconstructing the prompt tracks from the collision points. However, they require dedicated configuration and additional computing time to efficiently reconstruct the large radius tracks created away from the collision points. We developed an end-to-end machine learning-based track finding algorithm for the HL-LHC, the Exa.TrkX pipeline. The pipeline is designed so as to be agnostic about global track positions. In this work, we study the performance of the Exa.TrkX pipeline for finding large radius tracks. Trained with all tracks in the event, the pipeline simultaneously reconstructs prompt tracks and large radius tracks with high efficiencies. This new capability offered by the Exa.TrkX pipeline may enable us to search for new physics in real time.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

A Novel Deep Reinforcement Learning Approach to Traffic Signal Control with Connected Vehicles

The advent of connected vehicle (CV) technology offers new possibilities for a revolution in future transportation systems. With the availability of real-time traffic data from CVs, it is possible to more effectively optimize traffic signals to reduce congestion, increase fuel efficiency, and enhance road safety. The success of CV-based signal control depends on an accurate and computationally efficient model that accounts for the stochastic and nonlinear nature of the traffic flow. Without the necessity of prior knowledge of the traffic system’s model architecture, reinforcement learning (RL) is a promising tool to acquire the control policy through observing the transition of the traffic states. In this paper, we propose a novel data-driven traffic signal control method that leverages the latest in deep learning and reinforcement learning techniques. By incorporating a compressed representation of the traffic states, the proposed method overcomes the limitations of the existing methods in defining the action space to include more practical and flexible signal phases. The simulation results demonstrate the convergence and robust performance of the proposed method against several existing benchmark methods in terms of average vehicle speeds, queue length, wait time, and traffic density.

42 ENGINEERING↗

FY22 Progress Report: SRNL Analysis of ICCWR LCM and WAMS Data for Corrosion and Cracking

Algorithms for machine learning and data analysis for the 3013 Surveillance Program are being developed in an ongoing collaborative effort by the Savannah River National Laboratory (SRNL) and the University of South Carolina (USC). To detect the presence of corrosion and cracking, data is collected from large binary files generated by a Laser Confocal Microscope (LCM) or Wide Area 3D Measurement System (WAMS). Software is being developed to use the physical attributes in the data files (e.g., height, color, and grayscale values; all as functions of a location in a plane projection) to detect the presence of surface corrosion and cracking. A user-friendly Matlab Graphical User Interface (GUI) that reads data from either LCM or WAMS files was developed to integrate input data with software developed for processing and evaluation. The GUI can selectively download binary data, interrogate data attributes, label data for training ML algorithms, flag significant features, execute Machine Learning (ML) algorithms, output parameters from trained ML algorithms, report ML model accuracy with respect to labeled data, and generate graphical representations for various analyses. Surface defects can be called out by setting user-specified thresholds, feature based analysis or machine learning algorithms. Enhancements to data labeling capability have been developed to address this essential precursor to application of ML routines. Efficient labeling is particularly important in view of the very large volume of data required to train ML algorithms.

3013 Corrosion↗

Reducing systematic bias in machine learning applications to J/ψ signal extraction in high-energy nuclear physics

Machine learning techniques are increasingly used in high-energy nuclear physics because they can exploit multivariate correlations more efficiently than conventional cut-based analyses. A central challenge is the construction of training samples that faithfully reproduce the detector response observed in data. Signal samples are usually derived from detector simulations; therefore, mismatches between simulation and data can degrade classifier performance and introduce systematic biases. This work presents two practical correction procedures, namely cumulative distribution function (CDF) mapping and a shift-and-scale transformation, to align simulated signal features with those measured in data. Their performance is demonstrated with $J$/$\psi$ yield measurements in $\sqrt{s_{nn}}$ = 200 GeV Ru+Ru and Zr+Zr collisions recorded by STAR. A set of self-consistency tests shows that these procedures substantially suppress the systematic bias associated with data-simulation discrepancies in machine-learning-based signal extraction.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

S AP F LOWER : an automated tool for sap flow data preprocessing, gap-filling, and analysis using deep learning

Sap flow, a critical process in plant water use and ecosystem water cycles, is often measured using thermal dissipation probes (TDP) due to their ease of installation and continuous data collection. However, sap flow data frequently include noise, outliers, and gaps, creating challenges for analysis and requiring substantial manual processing. We developed S AP F LOWER , a tool that automates data preprocessing, model training, gap-filling, sapwood area scaling and modeling, and water use analysis. It integrates autocleaning, machine learning and deep learning models (e.g. random forest, Gaussian process regression, long short-term memory (LSTM), bidirectional LSTM (BiLSTM)), and efficient workflows to process sap flow data. S AP F LOWER can remove over 90% of noisy data while preserving legitimate variations and achieve high accuracy in gap-filling based on user-determined parameters. Random forest, LSTM, and BiLSTM models reduced root mean square error to 10% or less for long-term gaps. Model training and prediction can be performed efficiently within seconds. S AP F LOWER significantly enhances the efficiency and accessibility of TDP data analysis by automating complex tasks, enabling researchers without programming expertise to employ advanced techniques. Future improvements will focus on species-specific corrections for TDP and support for additional measurement methods. S AP F LOWER is openly available on GitHub (https://github.com/JiaxinWang123/SapFlower) and Zenodo (doi: 10.5281/zenodo.13665919).

ecosystem water balance↗

Learning reference governor for cycle-to-cycle combustion control with misfire avoidance in spark-ignition engines at high exhaust gas recirculation–diluted conditions

Cycle-to-cycle feedback control is employed to achieve optimal combustion phasing while maintaining high levels of exhaust gas recirculation by adjusting the spark advance and the exhaust gas recirculation valve position. The control development is based on a control-oriented model that captures the effects of throttle position, exhaust gas recirculation valve position, and spark timing on the combustion phasing. Under the assumption that in-cylinder pressure information is available, an adaptive extended Kalman filter approach is used to estimate the exhaust gas recirculation rate into the intake manifold based on combustion phasing measurements. The estimation algorithm is adaptive since the cycle-to-cycle combustion variability (output covariance) is not known a priori and changes with operating conditions. A linear quadratic regulator controller is designed to maintain optimal combustion phasing while maximizing exhaust gas recirculation levels during load transients coming from throttle tip-in and tip-out commands from the driver. During throttle tip-outs, however, a combination of a high exhaust gas recirculation rate and an overly advanced spark, product of the dynamic response of the system, generates a sequence of misfire events. In this work, an explicit reference governor is used as an add-on scheme to the closed-loop system in order to avoid the violation of the misfire limit. The reference governor is enhanced with model-free learning which enables it to avoid misfires after a learning phase. Experimental results are reported which illustrate the potential of the proposed control strategy for achieving an optimal combustion process during highly diluted conditions for improving fuel efficiency.

42 ENGINEERING↗

A Perspective on the Future of High Efficiency Engines

New fuel economy standards and emissions regulations are accelerating the development of new engine technologies, sensors, and on-board computing. These developments will enable unprecedented engine control, which will in turn enable real-world implementations of low temperature combustion, high-speed controls, and other high efficiency engine technologies. With this expanded flexibility in engine design and control, the challenge will now be the exponential increase in the design and calibration space and the need for the development of new simulations, optimization methods, and self-learning control methodologies. This manuscript provides historical and future perspectives on the opportunities and challenges of this unparalleled technology growth on the next generation of high efficiency engines.

Wagner, Robert M↗

Bounds on the sample complexity for private learning and private data release

Learning is a task that generalizes many of the analyses that are applied to collections of data, and in particular, collections of sensitive individual information. Hence, it is natural to ask what can be learned while preserving individual privacy. [Kasiviswanathan, Lee, Nissim, Raskhodnikova, and Smith; FOCS 2008] initiated such a discussion. They formalized the notion of private learning, as a combination of PAC learning and differential privacy, and investigated what concept classes can be learned privately. Somewhat surprisingly, they showed that, ignoring time complexity, every PAC learning task could be performed privately with polynomially many samples, and in many natural cases this could even be done in polynomial time. While these results seem to equate non-private and private learning, there is still a significant gap: the sample complexity of (non-private) PAC learning is crisply characterized in terms of the VC-dimension of the concept class, whereas this relationship is lost in the constructions of private learners, which exhibit, generally, a higher sample complexity. Looking into this gap, we examine several private learning tasks and give tight bounds on their sample complexity. In particular, we show strong separations between sample complexities of proper and improper private learners (such separation does not exist for non-private learners), and between sample complexities of efficient and inefficient proper private learners. Our results show that VC-dimension is not the right measure for characterizing the sample complexity of proper private learning. We also examine the task of private data release (as initiated by [Blum, Ligett, and Roth; STOC 2008]), and give new lower bounds on the sample complexity. Our results show that the logarithmic dependence on size of the instance space is essential for private data release.

99 GENERAL AND MISCELLANEOUS↗

Understanding Growth Dynamics and Yield Prediction of Sorghum Using High Temporal Resolution UAV Imagery Time Series and Machine Learning

Unmanned aerial vehicles (UAV) carrying multispectral cameras are increasingly being used for high-throughput phenotyping (HTP) of above-ground traits of crops to study genetic diversity, resource use efficiency and responses to abiotic or biotic stresses. There is significant unexplored potential for repeated data collection through a field season to reveal information on the rates of growth and provide predictions of the final yield. Generating such information early in the season would create opportunities for more efficient in-depth phenotyping and germplasm selection. This study tested the use of high-resolution time-series imagery (5 or 10 sampling dates) to understand the relationships between growth dynamics, temporal resolution and end-of-season above-ground biomass (AGB) in 869 diverse accessions of highly productive (mean AGB = 23.4 Mg/Ha), photoperiod sensitive sorghum. Canopy surface height (CSM), ground cover (GC), and five common spectral indices were considered as features of the crop phenotype. Spline curve fitting was used to integrate data from single flights into continuous time courses. Random Forest was used to predict end-of-season AGB from aerial imagery, and to identify the most informative variables driving predictions. Improved prediction of end-of-season AGB (RMSE reduction of 0.24 Mg/Ha) was achieved earlier in the growing season (10 to 20 days) by leveraging early- and mid-season measurement of the rate of change of geometric and spectral features. Early in the season, dynamic traits describing the rates of change of CSM and GC predicted end-of-season AGB best. Late in the season, CSM on a given date was the most influential predictor of end-of-season AGB. The power to predict end-of-season AGB was greatest at 50 days after planting, accounting for 63% of variance across this very diverse germplasm collection with modest error (RMSE 1.8 Mg/ha). End-of-season AGB could be predicted equally well when spline fitting was performed on data collected from five flights versus 10 flights over the growing season. This demonstrates a more valuable and efficient approach to using UAVs for HTP, while also proposing strategies to add further value.

54 ENVIRONMENTAL SCIENCES↗

Analytical Cost Metrics : Days of Future Past

As we move towards the exascale era, the new architectures must be capable of running the massive computational problems efficiently. Scientists and researchers are continuously investing in tuning the performance of extreme-scale computational problems. These problems arise in almost all areas of computing, ranging from big data analytics, artificial intelligence, search, machine learning, virtual/augmented reality, computer vision, image/signal processing to computational science and bioinformatics. With Moore’s law driving the evolution of hardware platforms towards exascale, the dominant performance metric (time efficiency) has now expanded to also incorporate power/energy efficiency. Therefore the major challenge that we face in computing systems research is: “how to solve massive-scale computational problems in the most time/power/energy efficient manner?”

97 MATHEMATICS AND COMPUTING↗

Machine Learning-Guided Optimization of SABRE Hyperpolarization for α-Ketoglutarate in Acetone–Water

Signal amplification by reversible exchange (SABRE) is a hyperpolarization method that polarizes target nuclei of metabolites quickly and efficiently. Recent SABRE advances, including Ace-SABRE, yield biocompatible, aqueous solutions of hyperpolarized markers for metabolic monitoring. Building on recent advancements, expanding the substrate scope of Ace-SABRE is desirable. However, SABRE polarization is sensitive to many different parameters; therefore, traditional optimization approaches are experimentally time-consuming. In this proof-of-concept application of machine learning (ML), Bayesian optimization (BO) is used for four important input parameters to model the complex SABRE dynamics while saving experimental time. The presented ML model also provides chemical insights that enable predictions of sample compositions for increased polarization levels. In this paper, we transition from an original average free polarization of p = ∼0.90% to a maximum observed free polarization of p = ∼6.6% for 1- 13 C alpha-ketoglutarate (AKG) with 13 C at natural abundance, utilizing both direct outputs as well as chemical insights revealed by the ML model.

Catalysts↗

Nonparametric Prediction Intervals of Wind Power via Linear Programming

This letter proposes a machine learning-based linear programming model that quickly establishes the nonparametric prediction intervals of wind power by integrating extreme learning machine and quantile regression. The proportions of quantiles can be adaptively determined via sensitivity analysis. The proposed method has been proven to be significantly efficient and reliable, with a high application potential in power systems.

extreme learning machine↗

FatMan vs. LittleBoy: Scaling Up Linear Algebraic Operations in Scale-Out Data Platforms

Linear algebraic operations such as matrix manipulations form the kernel of many machine learning and other crucial algorithms. Scaling up as well as scaling out such algorithms are highly desirable to enable efficient processing over millions of data points. To this end, we present a matrix manipulation approach to effectively scale-up each node in a scale-out data parallel platform such as Apache Spark. Specifically, we enable hardware acceleration for matrix multiplications in a distributed Spark setup without user intervention. Our approach supports both dense and sparse distributed matrices, and provides flexible control of acceleration by matrix density. We demonstrate the benefit of our approach for generalized matrix multiplication operations over large matrices with up to four billion elements. To connect the effectiveness of our approach with machine learning applications, we performed Gramian matrix computation via generalized matrix multiplications. Our experiments show that our approach achieves more than 2× performance speed-up, and up to 96.1% computation improvement, compared to a state of the art Spark MLlib for dense matrices.

97 MATHEMATICS AND COMPUTING↗

FatMan vs. LittleBoy: Scaling up Linear Algebraic Operations in Scale-out Data Platforms

Linear algebraic operations such as matrix manipulations form the kernel of many machine learning and other crucial algorithms. Scaling up as well as scaling out such algorithms are highly desirable to enable efficient processing over millions of data points. To this end, we present a matrix manipulation approach to effectively scale-up each node in a scale-out data parallel platform such as Apache Spark. Specifically, we enable hardware acceleration for matrix multiplications in a distributed Spark setup without user intervention. Our approach supports both dense and sparse distributed matrices, and provides flexible control of acceleration by matrix density. We demonstrate the benefit of our approach for generalized matrix multiplication operations over large matrices with up to four billion elements. To connect the effectiveness of our approach with machine learning applications, we performed Gramian matrix computation via generalized matrix multiplications. Our experiments show that our approach achieves more than 2x performance speed-up, and up to 96.1% computation improvement, compared to a state of the art Spark MLlib for dense matrices.

Lim, Seung-Hwan↗

AI/ML-assisted Design of Phosphate Glass and Ceramic Nuclear Waste Forms

Borosilicate glass is the widely accepted waste form for immobilization of high and medium level nuclear wastes. Advances in nuclear energies and new reactor designs require the development of new waste forms. For example, wastes from molten salt reactors and reprocessing of nuclear fuels lead to salt-based wastes that are difficult to be immobilized by conventional borosilicate glasses due to limited solubility and waste loading. In designing new waste forms, machine learning (ML) and artificial intelligence (AI) based approaches are much needed and can be beneficial in enabling a more efficient design in large parameter spaces as compared to traditional Edisonian trial-and-error approaches. Here, we report in this paper the rationale and latest progress of our ML/AI-based design of phosphate-based waste forms.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Best Practices Guide for High-Performance Indian Office Buildings

This document provides best practice guidance and energy- efficiency recommendations for the design, construction, and operation of high-­performance office buildings in India. Through a discussion of learnings from exemplary projects and inputs from experts, it provides recommendations that can potentially help achieve (1) enhanced working environments, (2) economic construction/faster payback, (3) reduced operating costs, and (4) reduced greenhouse gas (GHG) emissions. It also provides ambitious (but achievable) energy performance benchmarks, both as adopted targets during building modeling (design phase) and during measurement and verification (operations phase). These benchmarks have been derived from a set of representative best-in-class office buildings in India. The best practices strategies presented in this guide would ideally help in delivering high-­performance in terms of a triad—of energy efficiency, cost efficiency, and occupant comfort and well-­being. These best practices strategies and metrics should be normalized—that is, corrected to account for building characteristics, diversity of operations, weather, and materials and construction methods.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Emerging materials intelligence ecosystems propelled by machine learning

We report that the age of cognitive computing and artificial intelligence (AI) is just dawning. Inspired by its successes and promises, several AI ecosystems are blossoming, many of them within the domain of materials science and engineering. These materials intelligence ecosystems are being shaped by several independent developments. Machine learning (ML) algorithms and extant materials data are utilized to create surrogate models of materials properties and performance predictions. Materials data repositories, which fuel such surrogate model development, are mushrooming. Automated data and knowledge capture from the literature (to populate data repositories) using natural language processing approaches is being explored. The design of materials that meet target property requirements and of synthesis steps to create target materials appear to be within reach, either by closed-loop active-learning strategies or by inverting the prediction pipeline using advanced generative algorithms. AI and ML concepts are also transforming the computational and physical laboratory infrastructural landscapes used to create materials data in the first place. Surrogate models that can outstrip physics-based simulations (on which they are trained) by several orders of magnitude in speed while preserving accuracy are being actively developed. Automation, autonomy and guided high-throughput techniques are imparting enormous efficiencies and eliminating redundancies in materials synthesis and characterization. The integration of the various parts of the burgeoning ML landscape may lead to materials-savvy digital assistants and to a human-machine partnership that could enable dramatic efficiencies, accelerated discoveries and increased productivity. Here, we review these emergent materials intelligence ecosystems and discuss the imminent challenges and opportunities. The materials research landscape is being transformed by the infusion of approaches based on machine learning. This Review discusses the emerging materials intelligence ecosystems and the potential of human-machine partnerships for fast and efficient virtual materials screening, development and discovery.

36 MATERIALS SCIENCE↗

Cluster expansion by transfer learning for phase stability predictions

Recent progress towards universal machine-learned interatomic potentials holds considerable promise for materials discovery. Yet the accuracy of these potentials for predicting phase stability may still be limited. In contrast, cluster expansions provide accurate phase stability predictions but are computationally demanding to parameterize from first principles, especially for structures of low dimension or with a large number of components, such as interfaces or multimetal catalysts. We overcome this trade-off via transfer learning. Using Bayesian inference, we incorporate prior statistical knowledge from machine-learned and physics-based potentials, enabling us to sample the most informative configurations and to efficiently fit first-principles cluster expansions. Furthermore, this algorithm is tested on Pt:Ni, showing robust convergence of the mixing energies as a function of sample size with reduced statistical fluctuations.

36 MATERIALS SCIENCE↗