Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Machine Learning Algorithms”

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 1,747 records · Page 97
All sourcesNASA NTRSDOE OSTI
DOE OSTI2021

Stiff neural ordinary differential equations

Neural Ordinary Differential Equations (ODEs) are a promising approach to learn dynamical models from time-series data in science and engineering applications. This work aims at learning neural ODEs for stiff systems, which are usually raised from chemical kinetic modeling in chemical and biological systems. We first show the challenges of learning neural ODEs in the classical stiff ODE systems of Robertson’s problem and propose techniques to mitigate the challenges associated with scale separations in stiff systems. We then present successful demonstrations in stiff systems of Robertson’s problem and an air pollution problem. The demonstrations show that the usage of deep networks with rectified activations, proper scaling of the network outputs as well as loss functions, and stabilized gradient calculations are the key techniques enabling the learning of stiff neural ODEs. The success of learning stiff neural ODEs opens up possibilities of using neural ODEs in applications with widely varying time-scales, such as chemical dynamics in energy conversion, environmental engineering, and life sciences.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

The SODA Approach: Leveraging High-Level Synthesis for Hardware/Software Co-design and Hardware Specialization: Invited

Novel "converged" applications combine phases of scientific simulation with data analysis and machine learning. Each computational phase can benefit from specialized accelerators. However, algorithms evolve so quickly that mapping them on existing accelerators is suboptimal or even impossible. This paper presents the SODA (Software Defined Accelerators) framework, a modular, multi-level, open-source, no-human-in-the-loop, hardware synthesizer that enables end-to-end generation of specialized accelerators. SODA is composed of SODA-Opt, a high-level frontend developed in MLIR that interfaces with domain-specific programming frameworks and allows performing system level design, and Bambu, a state-of-the-art high-level synthesis engine that can target different device technologies. The framework implements design space exploration as compiler optimization passes. We show how the modular, yet tight, integration of the high-level optimizer and lower-level HLS tools enables the generation of accelerators optimized for the computational patterns of converged applications. We then discuss some of the research opportunities that such a framework allows, including system-level design, profile driven optimization, and supporting new optimization metrics.

Bohm Agostini, Nicolas↗
DOE OSTI2021

Analytics-at-scale of Sensor Data for Digital Monitoring in Nuclear Plants: 2nd Annual Report

For economic reasons, the nuclear industry is witnessing premature closure of nuclear power plants, despite excellent safety records. Operations and Maintenance (O&M) activities are some of the largest costs in operating legacy light-water plants. By reducing O&M costs, nuclear energy can become more economically competitive with other energy sources. This can be achieved by leveraging machine-learning and artificial intelligence technologies to develop data-driven algorithms to better diagnose potential faults within the system. Improved accuracy of the models can lead to a reduction in unnecessary maintenance, thus reducing costs associated with parts, labor, and unnecessary planned, forced, or extended outages. To address these challenges, the goal of this project is to perform research and development in the area of digital monitoring, i.e., the application of advanced sensor technologies (particularly wireless sensor technologies) and data science based analytic capabilities, to advance online monitoring and predictive maintenance in nuclear plants and improve plant performance (efficiency gain and economic competitiveness). This report summarizes the fiscal year 2020 research progress encompassing (1) different wireless vibration sensor and data indicators used to assess the health of a plant asset; (2) development of diagnostic models for fault detection; and (3) development of prognostic models for estimating the health of the system up to 7 days ahead.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Artificial Intelligence in Nuclear Physics

Artificial Intelligence (AI) and Machine Learning (ML) are rapidly developing fields providing data-driven algorithms to predict, classify, and make decisions based on data. Nuclear Physics Research is data-driven and AI/ML techniques have been implemented for experiment and accelerator control, in theoretical applications, and in data processing and analysis. These algorithms open possibilities for automation, thereby augmenting human capabilities. Additionally, Open Science is enabled by simultaneous analyses of multiple data sources, leading to scientific knowledge. This talk will summarize current applications of AI/ML in nuclear physics, as well as accelerator applications, and will cover upcoming initiatives and research in AI/ML.

Jeske, Torri↗
DOE OSTI2022

Analytics-at-scale of Sensor Data for Digital Monitoring in Nuclear Plants (4th Annual Report)

Nuclear plant sites collect and store large volumes of data collected from various equipment and systems. These datasets typically include plant process parameters, maintenance records, technical logs, online monitoring data, and equipment failure data. The collection of such data affords an opportunity to leverage data-driven machine learning and artificial intelligence technologies to provide diagnostic and prognostic capabilities within the nuclear power industry to reduce operating and maintenance costs. In this way, nuclear energy can become more economically competitive with other energy sources, and premature closures can be avoided. From a maintenance standpoint, savings can be achieved by leveraging machine learning and artificial intelligence technologies to develop data-driven algorithms to better diagnose and predict potential faults within the system. Improved model accuracy can lead to reductions in unnecessary maintenance and more efficient planning of future maintenance, thus lowering the costs associated with parts, labor, and unnecessary planned, forced, or extended outages. From an operations perspective, cost savings can be generated by shifting from route-based monitoring to wireless technologies for online monitoring, and by transitioning from onsite- to cloud-based computing and storage services. Wireless monitoring would reduce the operator manhours required for taking routine measurements, while cloud computing services would generate cost savings by reducing the amount of hardware needing to be purchased and maintained—all while scaling to both computational and storage demands. This report summarizes this project’s effort to shift from costly, labor-intensive preventative maintenance to cheaper predictive maintenance.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
NASA NTRS2023

A Hyperspectral Inversion Framework for Estimating Absorbing Inherent Optical Properties and Biogeochemical Parameters in Inland and Coastal Waters

The simultaneous remote estimation of biogeochemical parameters (BPs) and inherent optical properties (IOPs) from hyperspectral satellite imagery of globally distributed optically distinct inland and coastal waters is a complex, unsolved, non-unique inverse problem. To tackle this problem, we leverage a machine-learning model termed Mixture Density Networks (MDNs). MDNs outperform operational algorithms by calculating the covariance between the simultaneously estimated products. We train the MDNs on a large ( N = 8237) dataset of co-aligned, in situ measured, hyperspectral remote sensing reflectance (R rs ), BPs, and absorbing IOPs from globally representative optically distinct inland and coastal waters. The estimated IOPs include absorption due to phytoplankton (a ph ), chromophoric dissolved organic matter (a cdom ), and non-algal particles (a nap ). The estimated BPs include chlorophyll-a, total suspended solids, and phycocyanin (PC). MDNs dramatically reduce uncertainty in the retrievals, relative to operational algorithms, when using a 50/50 dataset split, where the MDNs are trained on a randomly selected half of the in situ dataset and validated on the other half. Our model is shown to have higher, or equivalent, generalization performance than the calculated operational algorithms available for all BPs and IOPs (except PC) via a leave-one-out cross-validation assessment. The MDNs are sensitive to uncertainties in the hyperspectral satellite R rs , resulting from instrument noise and atmospheric correction; there is a difference of ~37.4–62.8% (using median symmetric accuracy) between the MDNs’ estimates derived from co-located satellite-derived R rs and in situ R rs . Of the IOPs, a cdom and a nap are less sensitive to uncertainties in hyperspectral satellite imagery relative to a ph , with remote estimates of a ph exhibiting incorrect spectral shape and magnitude relative to in situ measured IOPs. Despite the uncertainties in satellite derived R rs , the spatial distributions of BPs and IOPs in MDN-derived product maps of Lake Erie and the Curonian Lagoon, based on imagery taken with the Hyperspectral Imager for the Coastal Ocean (HICO) and PRecursore Iper-Spettrale della Missione Applicativa (PRISMA), are confirmed via co-aligned in situ measurements and agree with the literature’s understanding of these well-studied regions. The consistency and accuracy of the model on HICO and PRISMA imagery, despite radiometric uncertainties, demonstrate its applicability to future hyperspectral missions, such as the Plankton, Aerosol, Cloud, ocean Ecosystem (PACE) mission, where the simultaneous estimation model will serve as a key part of phytoplankton community composition analysis.

Ryan E. O'Shea↗
DOE OSTI2026

Machine Learning on Heterogeneous, Edge, and Quantum Hardware for Particle Physics (ML-HEQUPP)

The next generation of particle physics experiments will face a new era of challenges in data acquisition, due to unprecedented data rates and volumes along with extreme environments and operational constraints. Harnessing this data for scientific discovery demands real-time inference and decision-making, intelligent data reduction, and efficient processing architectures beyond current capabilities. Crucial to the success of this experimental paradigm are several emerging technologies, such as artificial intelligence and machine learning (AI/ML) and silicon microelectronics, and the advent of quantum algorithms and processing. Their intersection includes areas of research such as low-power and low-latency devices for edge computing, heterogeneous accelerator systems, reconfigurable hardware, novel codesign and synthesis strategies, readout for cryogenic or high-radiation environments, and analog computing. This white paper presents a community-driven vision to identify and prioritize research and development opportunities in hardware-based ML systems and corresponding physics applications, contributing towards a successful transition to the new data frontier of fundamental science.

Gonski, Julia [SLAC]↗
DOE OSTI2020

Quantum Machine Learning in High Energy Physics

Machine learning has been used in high energy physics for a long time, primarily at the analysis level with supervised classification. Quantum computing was postulated in the early 1980s as way to perform computations that would not be tractable with a classical computer. With the advent of noisy intermediate-scale quantum computing devices, more quantum algorithms are being developed with the aim at exploiting the capacity of the hardware for machine learning applications. An interesting question is whether there are ways to apply quantum machine learning to High Energy Physics. This paper reviews the first generation of ideas that use quantum machine learning on problems in high energy physics and provide an outlook on future applications.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
NASA NTRS2024

EdgeCortix SAKURA-I Machine-Learning, PCIe Accelerator SEE Heavy Ion Test Report

To enable autonomy in space, machine-learning and computer vision applications become invaluable for sensor processing. However, these algorithms are computationally complex and unfeasible for many embedded central processing units (CPUs) and usually require external coprocessors, such as graphics processing units (GPUs) or accelerators specific to the application, including application specific integrated circuits (ASICs). In power-constrained systems, GPUs tend to consume more power than is acceptable (>40W), so lower-power accelerators have shown promise to provide the performance needed under spacecraft constraints. For radiation engineers, developing methodologies that can properly test CPUs, GPUs, and accelerators, and enable comparisons between them remains a necessary complication to solve as the devices become more complex. The methodology in this test aims to be a start in developing a baseline single-event effect (SEE) test for client-device machine learning accelerators. This category of devices do not host their own operating system. This testing campaign is a continuation of a previous 200 MeV proton test performed in January 2024. This report covers two heavy ion tests of the SAKURA-I card: one in April 2024, and one in June 2024. Additional data was needed after the April test due to ion-range issues experienced at higher linear-energy transfers (LETs). These range issues are described in more detail in Section 8. This experiment characterizes SEEs and data error susceptibility of the EdgeCortix SAKURA-I machine-learning accelerator under heavy ions. The device was monitored for single event upsets (SEUs) and single event functional interrupts (SEFIs) at the Lawrence Berkeley National Laboratory’s 88-inch cyclotron. The SAKURA-I board accelerates machine-learning inference applications on a host computer through a PCIex16 connection. For the purposes of devising an end to end automated analysis workflow for this experiment, the YOLO-V5 and SSD300 objection-detection models, and the ResNet-50, EfficientNet, and MobileNetV2 image classification models were used as a representative suite of analytical machine-learning models.

Seth S Roffe↗
NASA NTRS2014

Vision Based Autonomous Robotic Control for Advanced Inspection and Repair

The advanced inspection system is an autonomous control and analysis system that improves the inspection and remediation operations for ground and surface systems. It uses optical imaging technology with intelligent computer vision algorithms to analyze physical features of the real-world environment to make decisions and learn from experience. The advanced inspection system plans to control a robotic manipulator arm, an unmanned ground vehicle and cameras remotely, automatically and autonomously. There are many computer vision, image processing and machine learning techniques available as open source for using vision as a sensory feedback in decision-making and autonomous robotic movement. My responsibilities for the advanced inspection system are to create a software architecture that integrates and provides a framework for all the different subsystem components; identify open-source algorithms and techniques; and integrate robot hardware.

sensory feedback↗
DOE OSTI2023

Selecting representative geological realizations to model subsurface CO 2 storage under uncertainty

Carbon capture and storage (CCS) is one of the quickest and most effective solutions for reducing carbon emissions. The majority of subsurface storage occurs in saline aquifers, for which geological information is lacking which in turn results in geological uncertainty. To evaluate uncertainty in CO 2 injection projections, the use of multiple geological realizations (GRs) has been practiced very commonly. In this approach, hundreds or thousands of high-resolution GRs is used that quickly becomes computationally expensive. This issue can be addressed with representative geological realizations (RGRs) that preserve the uncertainty domain of the ensemble GRs. Here, in this study, we propose the use of unsupervised machine learning (UML) frameworks, including dissimilarity measurement, dimensionality reduction, clustering and sampling algorithms ta select a predetermined number of RGRs. We compare the simulation outputs of the RGR sets and the ensemble using the Kolmogorov–Smirnov (KS) test to select the best UML. The UML frameworks and their associated selection processes are evaluated using a saline aquifer with a single CO 2 injection well and 200 GRs with varying uncertain petrophysical characteristics. The best UML framework is selected to use only 5% of the GRs while maintaining the uncertainty domain of the ensemble GRs. In addition, the best UML framework is tested using a saline aquifer with three CO 2 injection wells and varied GRs. The results show that our proposed UML framework can be used to choose RGRs, capturing the whole uncertainty domain. Our approach leads to a significant reduction in the computational cost associated with scenario testing, decision-making, and development planning for CO 2 storage sites under geological uncertainty.

58 GEOSCIENCES↗
NASA NTRS2019

Ask-The-Expert: Minimizing Human Review for Big Data Analytics Through Active Learning

In this CIF project, we worked toward semi-automating knowledge discovery from anomaly detection algorithms through the use of active learning. Active learning is an area of research within machine learning that uses an "expert in the loop" to learn from large data sets that have very few annotations or labels available, and where providing such labels is expensive. In our case, the task can be defined as the identification of safety events from flight operational data. Since traditional anomaly detection algorithms cannot differentiate between operationally relevant and irrelevant statistical anomalies, Subject Matter Experts (SMEs) have a lengthy and expensive burden of investigating every example identified by the detection algorithm, classifying and labeling them as relevant or irrelevant. Active learningidentifies the unlabeled example for which a label would most improve the classifier, asks the domain expert for a label, and repeats this process until there are no more resources (time, budget) available for labeling or a minimum required performance is reached. A positive label indicates an operationally significant safety event whereas a negative label indicates otherwise. Based on these few labels we propose to build an active learning system that utilizes the SME's time in the most effective manner by iteratively asking for labels for as few informative instances as possible. Our work was proposed to be a stepping stone toward implementation and deployment of the system with user interface to be pursued by the Aviation Operations and Safety Program (AOSP) given its interest in safety monitoring and discovery of safety incidents.

aviation safety↗
DOE OSTI2014

SU-E-I-97: Smart Auto-Planning Framework in An EMR Environment (SAFEE)

Purpose: Our Radiation Oncology Department uses clinical practice guidelines for patient treatment, including normal tissue sparing and other dosimetric constraints. These practice guidelines were adapted from national guidelines, clinical trials, literature reviews, and practitioner's own experience. Modern treatment planning systems (TPS) have the capability of incorporating these practice guidelines to automatically create radiation therapy treatment plans with little human intervention. We are developing a software infrastructure to integrate clinical practice guidelines and radiation oncology electronic medical record (EMR) system into radiation therapy treatment planning system (TPS) for auto planning. Methods: Our Smart Auto-Planning Framework in an EMR environment (SAFEE) uses a software pipeline framework to integrate practice guidelines,EMR, and TPS together. The SAFEE system starts with retrieving diagnosis information and physician's prescription from the EMR system. After approval of contouring, SAFEE will automatically create plans according to our guidelines. Based on clinical objectives, SAFEE will automatically select treatment delivery techniques (such as, 3DRT/IMRT/VMAT) and optimize plans. When necessary, SAFEE will create multiple treatment plans with different combinations of parameters. SAFEE's pipeline structure makes it very flexible to integrate various techniques, such as, Model-Base Segmentation (MBS) and plan optimization algorithms, e.g., Multi-Criteria Optimization (MCO). In addition, SAFEE uses machine learning, data mining techniques, and an integrated database to create clinical knowledgebase and then answer clinical questions, such as, how to score plan quality or how volume overlap affects physicians' decision in beam and treatment technique selection. Results: In our institution, we use Varian Aria EMR system and RayStation TPS from RaySearch, whose ScriptService API allows control by external programs. These applications are the building blocks of our SAFEE system. Conclusion: SAFEE is a feasible method of integrating clinical information to develop an auto-planning paradigm to improve clinical workflow in cancer patient care.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2019

Microstructure optimization with constrained design objectives using machine learning-based feedback-aware data-generation

Microstructure sensitive design has a critical impact on the performance of engineering materials. The safety and performance requirements of critical components, as well as the cost of material and machining of Titanium components, make dovetailing of the microstructure imperative. This paper addresses the optimization of several microstructure design problems for Titanium components under specific design constraints using a feedback-aware data-driven solution methodology. In this study, the microstructure is modeled with an orientation distribution function (ODF) that measures the volumes of different crystallographic orientations. Two algorithms are used to sample the entire microstructure space followed by machine learning-aided identification of a minimal subset of ODF dimensions which is subsequently explored by targeted sampling. Conventional optimization methods lead to a unique microstructure rather than yielding a comprehensive space of optimal or near-optimal microstructures. Multiple solutions are crucial for the deployment of materials design for manufacturing as traditional manufacturing processes can only generate a limited set of microstructures. Our data sampling-based methodology not only outperforms or is on par with other optimization techniques in terms of the optimal property value, but also provides numerous near-optimal solutions, 3–4 orders of magnitude more than previous methods. Consequently, the proposed framework delivers a spectrum of optimal solutions in the microstructure space which can accelerate materials development and reduce manufacturing costs.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Incorporation of Physics Phenomenology into an Adaptive Algorithm Framework (Final Report)

We attempt to incorporate prior physics knowledge into a machine learning architecture at an applied application level (empirical) as opposed to the level of fundamental physics (first principles). The purpose of this work is to allow for the application of methods of physics-informed machine learning to a broad range of national security problems, while enhancing the trust in machine-learned models by decreasing the “black box” nature of such methods.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

Resilient Observer Design for Cyber-Physical Systems with Data-Driven Measurement Pruning

Resilient observer design for Cyber-Physical Systems (CPS) in the presence of adversarial false data injection attacks (FDIA) is an active area of research. The existing state-of-the-art algorithms tend to break down as more and more knowledge of the system is built into the attack model; also as the percentage of attacked nodes increases. From the view of optimization theory, the problem is often cast as a classical error correction problem for which a theoretical limit of has been established as the maximum percentage attacked nodes for which state recovery is guaranteed. Beyond this limit, the performance of -minimization based schemes, for instance, deteriorates rapidly. Similar performance degradation occurs for other types of resilient observers beyond certain percentages of attacked nodes. In order to increase the corresponding percentage of attacked nodes for which state recoveries can be guaranteed, researchers have begun to incorporate prior information into the underlying resilient observer design framework. For the most pragmatic cases, this prior information is often obtained through a data-driven machine learning process. Existing results have shown a strong positive correlation between the maximum attacked percentages that can be tolerated and the accuracy of the data-driven model. Motivated by these results, this chapter examines the case for pruning algorithms designed to improve the Positive Prediction Value (PPV) of the resulting prior information, given stochastic uncertainty characteristics of the underlying machine learning model. Theoretical quantification of the achievable improvement is given. Simulation results show that the pruning algorithm significantly increases the maximum correctable percentage of attacked nodes, even for machine learning model whose prediction power is comparable to the random flip of a coin.

Resilient Observer, Cyber-physical Systems, Data-D↗
DOE OSTI2016

Machine- z : Rapid machine-learned redshift indicator for Swift gamma-ray bursts

Studies of high-redshift gamma-ray bursts (GRBs) provide important information about the early Universe such as the rates of stellar collapsars and mergers, the metallicity content, constraints on the re-ionization period, and probes of the Hubble expansion. Rapid selection of high-z candidates from GRB samples reported in real time by dedicated space missions such as Swift is the key to identifying the most distant bursts before the optical afterglow becomes too dim to warrant a good spectrum. Here, we introduce ‘machine-z’, a redshift prediction algorithm and a ‘high-z’ classifier for Swift GRBs based on machine learning. Our method relies exclusively on canonical data commonly available within the first few hours after the GRB trigger. Using a sample of 284 bursts with measured redshifts, we trained a randomized ensemble of decision trees (random forest) to perform both regression and classification. Cross-validated performance studies show that the correlation coefficient between machine-z predictions and the true redshift is nearly 0.6. At the same time, our high-z classifier can achieve 80 per cent recall of true high-redshift bursts, while incurring a false positive rate of 20 per cent. With 40 per cent false positive rate the classifier can achieve ~100 per cent recall. As a result, the most reliable selection of high-redshift GRBs is obtained by combining predictions from both the high-z classifier and the machine-z regressor.

79 ASTRONOMY AND ASTROPHYSICS↗