Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning systems”

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 OSTI2020

Distributed fiber sensor and machine learning data analytics for pipeline protection against extrinsic intrusions and intrinsic corrosions

This paper presents an integrated technical framework to protect pipelines against both malicious intrusions and piping degradation using a distributed fiber sensing technology and artificial intelligence. A distributed acoustic sensing (DAS) system based on phase-sensitive optical time-domain reflectometry (φ-OTDR) was used to detect acoustic wave propagation and scattering along pipeline structures consisting of straight piping and sharp bend elbow. Signal to noise ratio of the DAS system was enhanced by femtosecond induced artificial Rayleigh scattering centers. Data harnessed by the DAS system were analyzed by neural network-based machine learning algorithms. The system identified with over 85% accuracy in various external impact events, and over 94% accuracy for defect identification through supervised learning and 71% accuracy through unsupervised learning.

Peng, Zhaoqiang↗
NASA NTRS1990

Learning control for minimizing a quadratic cost during repetitions of a task

In many applications, control systems are asked to perform the same task repeatedly. Learning control laws have been developed over the last few years that allow the controller to improve its performance each repetition, and to converge to zero error in tracking a desired trajectory. This paper generates a new type of learning control law that learns to minimize a quadratic cost function for tracking. Besides being of interest in its own right, this objective alleviates the need to specify a desired trajectory that can actually be performed by the system. The approach used here is to adapt appropriate methods from numerical optimization theory in order to produce learning control algorithms that adjust the system command from repetition to repetition in order to converge to the quadratic cost optimal trajectory.

Longman, Richard W.↗
DOE OSTI2022

Deep Reinforcement Learning based Model-free On-line Dynamic Multi-Microgrid Formation to Enhance Resilience

Multi-microgrid formation (MMGF) is a promising solution for enhancing power system resilience. This paper proposes a new deep reinforcement learning (RL) based model-free on-line dynamic MMGF scheme. Additionally, the dynamic MMGF problem is formulated as a Markov decision process, and a complete deep RL framework is specially designed for the topologytransformable micro-grids. In order to reduce the large action space caused by flexible switch operations, a topology transformation method is proposed and an action-decoupling Q-value is applied. Then, a convolutional neural network (CNN) based multi-buffer double deep Q-network (CM-DDQN) is developed to further improve the learning ability of the original DQN method. The proposed deep RL method provides real-time computing to support the on-line dynamic MMGF scheme, and the scheme handles a long-term resilience enhancement problem using an adaptive on-line MMGF to defend changeable conditions. The effectiveness of the proposed method is validated using a 7-bus system and the IEEE 123-bus system. The results show strong learning ability, timely response for varying system conditions and convincing resilience enhancement.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Improving North American Wildfire Prediction by Integrating a Machine-Learning Fire Model in a Land Surface Model

Wildfires have shown increasing trends in both frequency and severity across the Contiguous United States (CONUS). However, process-based fire models have difficulties in accurately simulating the burned area over the CONUS due to a simplification of the physical process and cannot capture the interplay among fire, ignition, climate, and human activities. The deficiency of burned area simulation deteriorates the description of fire impact on energy balance, water budget, and carbon fluxes in the Earth System Models (ESMs). Alternatively, machine learning (ML) based fire models, which capture statistical relationships between the burned area and environmental factors, have shown promising burned area predictions and corresponding fire impact simulation. We develop a hybrid framework (ML4Fire-XGB) that integrates a pretrained eXtreme Gradient Boosting (XGBoost) wildfire model with the Energy Exascale Earth System Model (E3SM) land model (ELM) version 2.1. A Fortran-C-Python deep learning bridge is adapted to support online communication between ELM and the ML fire model. Specifically, the burned area predicted by the ML-based wildfire model is directly passed to ELM to adjust the carbon pool and vegetation dynamics after disturbance, which are then used as predictors in the ML-based fire model in the next time step. Evaluated against the historical burned area from Global Fire Emissions Database 5 from 2001-2020, the ML4Fire-XGB model outperforms process-based fire models in terms of spatial distribution and seasonal variations. Sensitivity analysis confirms that the ML4Fire-XGB well captures the responses of the burned area to rising temperatures. The ML4Fire-XGB model has proved to be a new tool for studying vegetation-fire interactions, and more importantly, enables seamless exploration of climate-fire feedback, working as an active component in E3SM.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

A Deep Learning Modeling Framework to Capture Mixing Patterns in Reactive-Transport Systems

Prediction and control of chemical mixing are vital for many scientific areas such as subsurface reactive transport, climate modeling, combustion, epidemiology, and pharmacology. Due to the complex nature of mixing in heterogeneous and anisotropic media, the mathematical models related to this phenomenon are not analytically tractable. Numerical simulations often provide a viable route to predict chemical mixing accurately. However, contemporary modeling approaches for mixing cannot utilize available spatial-temporal data to improve the accuracy of the future prediction and can be compute-intensive, especially when the spatial domain is large and for long-term temporal predictions. To address this knowledge gap, in this work we will present in this paper a deep learning (DL) modeling framework applied to predict the progress of chemical mixing under fast bimolecular reactions. This framework uses convolutional neural networks (CNN) for capturing spatial patterns and long short-term memory (LSTM) networks for forecasting temporal variations in mixing. By careful design of the framework—placement of non-negative constraint on the weights of the CNN and the selection of activation function, the framework ensures non-negativity of the chemical species at all spatial points and for all times. Our DL-based framework is fast, accurate, and requires minimal data for training. The time needed to obtain a forecast using the model is a fraction (≈ O(-6)) of the time needed to obtain the result using a high-fidelity simulation. To achieve an error of 10% (measured using the infinity norm) for capturing local-scale mixing features such as interfacial mixing, only 24% to 32% of the sequence data for model training is required. To achieve the same level of accuracy for capturing global-scale mixing features, the sequence data required for model training is 64% to 70% of the total spatial-temporal data. Hence, the proposed approach—a fast and accurate way to forecast long-time spatial-temporal mixing patterns in heterogeneous and anisotropic media—will be a valuable tool for modeling reactive-transport in a wide range of applications.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2022

How Well Does Kohn–Sham Regularizer Work for Weakly Correlated Systems?

Kohn–Sham regularizer (KSR) is a differentiable machine learning approach to finding the exchange-correlation functional in Kohn–Sham density functional theory that works for strongly correlated systems. Here we test KSR for a weak correlation. We propose spin-adapted KSR (sKSR) with trainable local, semilocal, and nonlocal approximations found by minimizing density and total energy loss. We assess the atoms-to-molecules generalizability by training on one-dimensional (1D) H, He, Li, Be, and Be 2+ and testing on 1D hydrogen chains, LiH, BeH 2 , and helium hydride complexes. The generalization error from our semilocal approximation is comparable to other differentiable approaches, but our nonlocal functional outperforms any existing machine learning functionals, predicting ground-state energies of test systems with a mean absolute error of 2.7 mH.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Elastic Resource Management for Deep Learning Applications in a Container Cluster

The increasing demand for learning from massive datasets is restructuring our economy. Effective learning, however, involves nontrivial computing resources. Most businesses utilize commercial infrastructure providers (e.g., AWS) to host their computing clusters in the cloud, where various jobs compete for available resources. While cloud resource management is a fruitful research field that has made many advances in production, such as Kubernetes and YARN, few efforts have been invested to further optimize the system performance, especially for deep learning (DL) training jobs in a container cluster. This work introduces FlowCon, a system that is able to monitor the individual evaluation functions of DL jobs at runtime, and thus to make placement decisions on resource allocations elastically. Here, we present a detailed design and implementation of FlowCon and conduct intensive experiments over various DL models. The results demonstrate that FlowCon significantly improves DL job completion time and resource utilization efficiency, compared to default systems. According to the results, FlowCon is able to improve the completion time by up to 68.8% and meanwhile, reduce the makespan by 18.0%, in the presence of various DL job workloads.

97 MATHEMATICS AND COMPUTING↗
NASA NTRS2001

The Integration of COTS/GOTS within NASA's HST Command and Control System

NASA's mission critical Hubble Space Telescope (HST) command and control system has been re-engineered with commercial-off-the-shelf (COTS/GOTS) and minimal custom code. This paper focuses on the design of this new HST Control Center System (CCS) and the lessons learned throughout its development. CCS currently utilizes more than 30 COTS/GOTS products with an additional 1/2 million lines of custom glueware code; the new CCS exceeds the capabilities of the original system while significantly reducing the lines of custom code by more than 50%. The lifecycle of COTS/GOTS products will be examined including the package selection process, evaluation process, and integration process. The advantages, disadvantages, issues, concerns, and lessons learned for integrating COTS/GOTS into the NASA's mission critical HST CCS will be examined in detail. This paper will reveal the many hidden costs of COTS/GOTS solutions when compared to traditional custom code development efforts; this paper will show the high cost of COTS/GOTS solutions including training expenses, consulting fees, and long-term maintenance expenses.

Pfarr, Thomas↗
NASA NTRSDate not supplied

Nearest-Neighbor Machine Learning Feature Selection for Interpretation of Microbial Molecular Signatures from Isotope Ratio Mass Spectrometry Data

Mass spectrometry (MS) promises to be a powerful tool for potential biosignature detection during astrobiological missions on ocean worlds in our solar system. Accurate and generalizable machine learning methods could enhance science return on investment by predicting seawater chemistry and classifying isotopic biosignatures, either as a signature consistent with microbial life (biotic) or as a novelty (unclassified/unique). However, machine learning models are likely to be complex and involve interactions between MS features, making biosignatures difficult to interpret. Feature selection methods provide biological and chemical context that help interpret the mechanisms of machine learning models, but these methods also need the ability to detect complex interactions. Previously, we developed a machine learning feature selection algorithm called nearest-neighbor projected distance regression (NPDR) that has the ability to identify important model features that involve complex interactions and automatically reduce correlation and the dimensionality in a high-dimensional variable space. The standard distance metrics used in NPDR – Manhattan and Euclidean – assume the multivariate data are isotropic, which is often violated in real data due to differences in the covariance between variables. Thus, we extend NPDR to include a random forest distance, and other anisotropic distance metrics, for computing nearest neighbors. We also augment the isotope-ratio MS data with time-series features from the raw MS signal to improve biotic classification. We test NPDR on our novel experimental ocean world seawater analog MS data. We measure isotope fractionations of volatile CO 2 that could be measured in exospheres or plumes. Samples include baseline abiotic conditions using a range of possible seawater chemistry consistent with Europa and Enceladus, and biotic samples that include microbes in these seawaters. We use penalized NPDR with random forest proximity to identify interpretable microbial molecular signatures. We compare features with random forest importance, and we train a classifier that discriminates between biotic and abiotic samples with high accuracy. These ML-trained ocean-world analog MS data could be used to assist in identifying biosignatures during future missions.

geochemistry↗
NASA NTRS2019

Lessons Learned from the Flight Unit Testing of the Near Earth Asteroid Scout Flight System

The Near Earth Asteroid Scout flight mission is set to launch on the maiden voyage of the Space Launch System as a secondary payload. The spacecraft will be jettisoned in cis-lunar space and embark on an ambitious 2.5 year mission to image an asteroid. The spacecraft is uniquely equipped with an 85m2 solar sail as the main propulsion system. The monolithic sail system is designed to package within a 6U volume for launch and then deploy during flight. The NEA Scout team has presented in the past to the International Symposium on Solar Sailing topics related to the engineering development unit and design efforts to achieve flight hardware build. This paper will focus on the lessons learned from building and testing the NEA Scout flight system. Focus will be on the mechanical, software, and electrical interfaces as well as preparation for subsystem environmental tests, including thermal vacuum. Due to the unique design of the spacecraft, the solar sail subsystem was required to be located in the center of the spacecraft. This requirement lead to design challenges such as designing and accommodating critical cable harnesses to run through the center of the sail subsystem, packaging and deployment design of the sail subsystem, and integrated testing efforts through an avionics test bed to verify and validate a complete system architecture.

Lockett, Tiffany Russell↗
NASA NTRS1990

Fault diagnosis

The objective of the research in this area of fault management is to develop and implement a decision aiding concept for diagnosing faults, especially faults which are difficult for pilots to identify, and to develop methods for presenting the diagnosis information to the flight crew in a timely and comprehensible manner. The requirements for the diagnosis concept were identified by interviewing pilots, analyzing actual incident and accident cases, and examining psychology literature on how humans perform diagnosis. The diagnosis decision aiding concept developed based on those requirements takes abnormal sensor readings as input, as identified by a fault monitor. Based on these abnormal sensor readings, the diagnosis concept identifies the cause or source of the fault and all components affected by the fault. This concept was implemented for diagnosis of aircraft propulsion and hydraulic subsystems in a computer program called Draphys (Diagnostic Reasoning About Physical Systems). Draphys is unique in two important ways. First, it uses models of both functional and physical relationships in the subsystems. Using both models enables the diagnostic reasoning to identify the fault propagation as the faulted system continues to operate, and to diagnose physical damage. Draphys also reasons about behavior of the faulted system over time, to eliminate possibilities as more information becomes available, and to update the system status as more components are affected by the fault. The crew interface research is examining display issues associated with presenting diagnosis information to the flight crew. One study examined issues for presenting system status information. One lesson learned from that study was that pilots found fault situations to be more complex if they involved multiple subsystems. Another was pilots could identify the faulted systems more quickly if the system status was presented in pictorial or text format. Another study is currently under way to examine pilot mental models of the aircraft subsystems and their use in diagnosis tasks. Future research plans include piloted simulation evaluation of the diagnosis decision aiding concepts and crew interface issues. Information is given in viewgraph form.

Abbott, Kathy↗
DOE OSTI2025

Techno-economic implications and cost of forecasting errors in solar PV power production using optimized deep learning models

Accurate solar Photovoltaic (PV) power forecasting is important for enhancing both the performance and economic feasibility of PV systems. This study evaluates several deep learning models, including Dense Neural Networks (DNN), Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and a hybrid LSTMCNN model, for predicting PV power production one day in advance. Prior to optimization, the models exhibited relatively high errors, with the best model (DNN) achieving a Root Mean Square Error (RMSE) of 31.13 kW and a coefficient of determination (R 2 ) of 62.15 %. After employing Bayesian optimization, the LSTM-CNN model demonstrated the best performance, with the RMSE reduced to 9.79 kW and R 2 improved to 97.62 %, showcasing significant enhancement in predictive accuracy. Here, the economic evaluation considered three cases: rewards for underestimation (0.08 USD/kWh), no rewards, and penalties for both over-and underestimation (120 % of the utility tariff). In the rewards scenario, the LSTM-CNN model reduced the Levelized Cost of Electricity (LCOE) by 4 %, while in the penalty scenario, a backup diesel generator would have increased the LCOE by 49 %. Additionally, the LSTM-CNN model minimized financial losses, achieving the lowest penalties and maximizing net cash flow compared to other models, demonstrating its overall technical and economic superiority.

Deep learning↗
DOE OSTI2018

Predicting 2CS protein pairs with Deep Learning

Neural network was trained on the amino acid sequences of known two-component systems (2CS) pairs. The recommender algorithm uses learned model to select the most likely 2CS pair from an arbitrary set of protein pairs whose amino acid sequences are known.

Balewski, Jan↗
DOE OSTI2019

Evolution of Induced Fracture Networks Using Machine Learning Correlation Image Analysis

Enhanced geothermal systems (EGS) can enrich the Nation’s energy portfolio by increasing the amount of renewable baseload power available to the electrical grid. Microseismic activity, due to fluid resource injection and production, provides critical insight into the processes that occur within EGS subsurface fracture networks. To more precisely characterize these fracture networks, we leverage recent advances in deep neural network (DNN) image analysis techniques. Using seismic spectrogram data collected during a meso scale EGS field experiment as image inputs, we developed a new approach to correlate microseismic events. Our results indicate that our chosen DNN is able to estimate the correlation value between highly correlated events (i.e., cross-correlation coefficients greater than approximately 0.7), but has difficulty estimating correlation values between poorly correlated events. In physical systems however, the highly correlated microseismic events are the events of interest. Therefore, this data-driven method has shown potential for improving domestic Energy and Resource Security, advancing the current methods available to image subsurface EGS thermal reservoirs to enhance the availability of clean and reliable energy to the national electric grid.

58 GEOSCIENCES↗
DOE OSTI2025

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↗
NASA NTRS1993

Entry Systems Panel

As general findings, lessons learned from shuttle are: (1) bridge established between development center (JSC) Research Centers (ARC, LARC), and industry (RI, LMSC, Corning, Mansville, 3M LTV, Union Carbide, Hexcel) for shuttle TPS; (2) not all test results adequately analyzed or in hindsight, completely encompassing all failure modes; (3) gap heating effects from ground facilities not totally indicative of flight experience; (4) need to design with operations in mind (not just to cost) example: moisture intrusion of GR/EP, many other examples; (5) RSI- developed as point design for maneuvering entry vehicle of high L/D; and (6) RSI - 15 years from invention to use on flight hardware.

Rasky, Daniel J.↗
NASA NTRS2004

Overview of High Speed Close-Up Imaging in an Icing Environment

The Icing Branch and Imaging Technology Center at NASA Glenn Research Center have recently been involved in several projects where high speed close-up imaging was used to investigate water droplet impact/splash, and also ice particle impact/bounce in an icing wind tunnel. The combination of close-up and high speed imaging capabilities were required because the particles being studied were relatively small (d < 1 mm in diameter), and the impact process occurred in a very short time period (t(sub impact) << 1 sec). High speed close-up imaging was utilized to study the dynamics of droplet impact and splash in simulated Supercooled Large Droplet (SLD) icing conditions. The objective of this test was to evaluate the capability of a ultra high speed camera system to acquire quantitative information about the impact process (e.g., droplet size, velocity). Imaging data were obtained in an icing wind tunnel for spray cloud MVD > 50 m. High speed close-up imaging was also utilized to characterize the impact of ice particles on an airfoil with a thermally protected leading edge. The objective of this investigation was to determine whether ice particles tend to "stick" or "bounce" after impact. Imaging data were obtained for cases where the airfoil surface was heated and unheated. Based on the results from this test, follow on tests were conducted to investigate ice particle impact on the sensing elements of water content measurement devices. This paper will describe the use of the imaging systems to support these experimental investigations, present some representative results, and summarize what was learned about the use of these systems in an icing environment.

Miller, Dean R.↗
NASA NTRS2018

Overview of RS-25 Adaptation Hot-Fire Test Series for SLS, Status and Lessons Learned

This paper discusses the engine system design, hot-fire test history and analyses for the RS-25 Adaptation Engine test series, a major hot-fire test series supporting the Space Launch System (SLS) program. The RS-25 is an evolution of the Space Shuttle Main Engine (SSME). Since the SLS mission profile and engine operating conditions differ from that experienced by the SSME, a test program was needed to verify that SLS-unique requirements could be met by the adapted legacy engines. A series of 18 tests, including one engine acceptance test, was conducted from January 2015 to October 2017, to directly support Exploration Mission-1 (EM-1), the first flight of SLS. These tests were the first hot-firings of legacy SSME hardware since 2009. Major findings are described along with top level overview of the engine system.

Vetcha, Naveen↗