Search NASA⌕ Search

SEARCH · Search NASA

Results for “learning based 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 541 records · Page 30
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Multi-Objective PMU Allocation for Resilient Power System Monitoring

Phasor measurement units (PMUs) enable better system monitoring and security enhancement in smart grids. In order to enhance power system resilience against outages and blackouts caused by extreme weather events or man-made attacks, it remains a major challenge to determine the optimal number and location of PMUs. In this paper, a multi-objective resilient PMU placement (MORPP) problem is formulated, and solved by a modified Teaching-Learning-Based optimization (MO-TLBO) algorithm. Three objectives are considered in the MORPP problem, minimizing the number of PMUs, maximizing the system observability, and minimizing the voltage stability index. The effectiveness of the proposed method is validated through testing on IEEE 14-bus, 30-bus, and 118-bus test systems. The advantage of the MO-TLBO-based MORPP is demonstrated through the comparison with other methods in the literature, in terms of iteration number, optimality and time of convergence.

Multi-Objective Optimization↗
DOE OSTI2021

Thermodynamic properties of the Nd-Bi system via emf measurements, $\mathrm{DFT}$ calculations, machine learning, and $\mathrm{CALPHAD}$ modeling

Thermodynamic properties of the Nd-Bi system were investigated using a combination of experimental measurements, first-principles calculations based on density functional theory (DFT), data mining and machine learning (DM + ML) predictions, and calculation of phase diagrams (CALPHAD) modeling. The electromotive force (emf) of Nd-Bi alloys in molten LiCl-KCl-NdCl 3 at 773–973 K was measured via coulometric titration of Nd into Bi for the determination of thermochemical properties such as activity coefficients and solubilities of Nd in Bi. A new peritectic reaction of [liquid + NdBi 2 = Nd 3 Bi 7 ] at 774 K was confirmed using differential scanning calorimetry, structural (X-ray diffraction), and microstructural (scanning electron microscopy) analyses. The unknown crystal structure of NdBi2 was suggested to be a mixture of the anti-La 2 Sb configuration and the La 2 Te-type configuration based on ML predictions for over 26,000 data-mined AB 2 -type configurations together with DFT-based verifications. Using the newly acquired experimental data and DFT-based calculations, the thermodynamic description of the Nd-Bi system was remodeled, and a more complete Nd-Bi phase diagram was calculated, including the Nd 3 Bi 7 compound, invariant transition reactions, and liquidus temperatures.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Efficient and assured reinforcement learning-based building HVAC control with heterogeneous expert-guided training

Abstract Building heating, ventilation, and air conditioning (HVAC) systems account for nearly half of building energy consumption and $$20\%$$ of total energy consumption in the US. Their operation is also crucial for ensuring the physical and mental health of building occupants. Compared with traditional model-based HVAC control methods, the recent model-free deep reinforcement learning (DRL) based methods have shown good performance while do not require the development of detailed and costly physical models. However, these model-free DRL approaches often suffer from long training time to reach a good performance, which is a major obstacle for their practical deployment. In this work, we present a systematic approach to accelerate online reinforcement learning for HVAC control by taking full advantage of the knowledge from domain experts in various forms . Specifically, the algorithm stages include learning expert functions from existing abstract physical models and from historical data via offline reinforcement learning, integrating the expert functions with rule-based guidelines, conducting training guided by the integrated expert function and performing policy initialization from distilled expert function. Moreover, to ensure that the learned DRL-based HVAC controller can effectively keep room temperature within the comfortable range for occupants, we design a runtime shielding framework to reduce the temperature violation rate and incorporate the learned controller into it. Experimental results demonstrate up to 8.8 X speedup in DRL training from our approach over previous methods, with low temperature violation rate.

Xu, Shichao↗
DOE OSTI2024

ML based control systems for nuclear physics experiments

The Experimental Physics Software and Computing Infrastructure (EPSCI) group at Jefferson Lab is leading the use of machine learning (ML) to enhance control systems in nuclear physics experiments. Collaborating closely with domain experts and data scientists, we have developed an ML-based control system that uses a Gaussian process to dynamically adjust the high voltage of the GlueX Central Drift Chamber. This results in stable detector performance by adapting to environmental changes, thereby reducing the offline calibration effort. Furthermore, we are developing ML-driven systems for optimizing the polarization of photon beams and polarized cryotargets. These systems will maintain the optimal microwave frequency in cryogenic targets and make real-time adjustments to diamond radiators for polarized photon sources, tasks traditionally handled by human operators. By automating these functions, we aim to optimize the polarization, reduce downtime, and minimize human error. This talk will highlight the development of reliable ML-based control systems and the policies to ensure they are both effective and trustworthy.

Jeske, Torri↗
NASA NTRS1998

Hybrid Motion Planning with Multiple Destinations

In our initial proposal, we laid plans for developing a hybrid motion planning system that combines the concepts of visibility-based motion planning, artificial potential field based motion planning, evolutionary constrained optimization, and reinforcement learning. Our goal was, and still is, to produce a hybrid motion planning system that outperforms the best traditional motion planning systems on problems with dynamic environments. The proposed hybrid system will be in two parts the first is a global motion planning system and the second is a local motion planning system. The global system will take global information about the environment, such as the placement of the obstacles and goals, and produce feasible paths through those obstacles. We envision a system that combines the evolutionary-based optimization and visibility-based motion planning to achieve this end.

Clouse, Jeffery↗
NASA NTRSDate not supplied

Applicability of Loads Estimation Techniques Using Sparse Acceleration Sensor Data to Spacecraft Structural Health Monitoring

The use of structural health monitoring systems on spacecraft structures can play a crucial role in ensuring the safety, reliability, and longevity of the structure by gathering and analyzing onboard sensor data. Of specific importance is monitoring for excessive loading at critical interfaces as any off-nominal structural excitations experienced by spacecraft structures can cause early unpredicted high structural life consumption or damage. The availability and cost of flight-certified sensors along with the size of spacecraft structures and allowable payload mass drives the need for a method to estimate loads using sparsely-located sensors. Numerous approaches such as physics-based, statistical learning, and physics-enhanced statistical learning algorithms have gained popularity among structural prognostics applications. However, developing noise-robust prediction models to assess loads and structural life predictions from a sparse multi-sensor data acquisition system can be a challenging task. This paper discusses the evaluation of physics-based versus machine-learning algorithms for predicting loads and structural life at mission critical locations on the spacecraft structure using a finite element loads analysis with the application of simulated noise and noise reduction techniques. To estimate the loads from accelerations, the physics-based algorithm leverages a loads transformation matrix from a Craig-Bampton reduced finite element model. A System Equivalent Reduction Expansion Process (SEREP) and a pseudo-inverse approach are considered to expand from the onboard sensor degrees of freedom to the Craig-Bampton model degrees of freedom. The machine learning algorithm provides a data driven solution/mapping of the sensor accelerations to the loads at the mission critical locations using a high dimensionality analysis. Although these strategies produce comparable loads prediction without noise, the limitations of these strategies with incorporating simulated noise and noise reduction techniques with low signal to noise ratio signals are evaluated. The study demonstrates the immense potential of statistical learning algorithms for sparse structural prognostic models and enhancing signal denoising techniques. These findings also highlight the need for noise-resilient prognostic models and low-noise data acquisition systems onboard spacecraft structures.

Spacecraft Structural Health Monitoring↗
DOE OSTI2023

High-bandwidth image-based predictive laser stabilization via optimized Fourier filters

Controlling the delivery of kHz-class pulsed lasers is of interest in a variety of industrial and scientific applications, from next-generation laser-plasma acceleration to laser-based x-ray emission and high-precision manufacturing. The transverse position of the laser pulse train on the application target is often subject to fluctuations by external drivers (e.g., room cooling and heating systems, motorized optics stages and mounts, vacuum systems, chillers, and/or ground vibrations). For typical situations where the disturbance spectrum exhibits discrete peaks on top of a broad-bandwidth lower-frequency background, traditional PID (proportional-integral-derivative) controllers may struggle, since as a general rule PID controllers can be used to suppress vibrations up to only about 5%–10% of the sampling frequency. Here, a predictive feed-forward algorithm is presented that significantly enhances the stabilization bandwidth in such laser systems (up to the Nyquist limit at half the sampling frequency) by online identification and filtering of one or a few discrete frequencies using optimized Fourier filters. Furthermore, the system architecture demonstrated here uses off-the-shelf CMOS cameras and piezo-electric actuated mirrors connected to a standard PC to process the alignment images and implement the algorithm. To avoid high-end, high-cost components, a machine-learning-based model of the piezo mirror’s dynamics was integrated into the system, which enables high-precision positioning by compensating for hysteresis and other hardware-induced effects. A successful demonstration of the method was performed on a 1 kHz laser pulse train, where externally-induced vibrations of up to 400 Hz were attenuated by a factor of five, far exceeding what could be done with a standard PID scheme.

Natal, Joseph↗
DOE OSTI2026

Ensemble Federated Machine Learning‐Based Cybersecurity Situational Awareness in Microgrid Network

Cyber-physical microgrids are vulnerable to stealthy cybersecurity threats that disguise their actions through the exploitation of system knowledge. Such actions can severely impacts microgrids deployed in defense bases, slowing the response time of military forces during national emergencies. Several machine-learning algorithms have been proposed to detect intrusions in the grid networks; however, these traditional machine-learning algorithms lack data privacy and are subject to several adversarial machine-learning threats. This paper proposes a novel federated machine learning (FML)-based three-model framework to detect and identify stealthy data-integrity attacks while ensuring data privacy in microgrid networks. The proposed architecture uses a variational mode decomposition technique to extract derived features from incoming measurement and control datasets. The extraction of these derived features allows FML models to learn minute variations in data patterns that allow them to perform significantly better than the models trained with generic datasets consisting of raw features. Our experimental results show the efficient performance of the proposed methodology against different types of data integrity attacks while considering primary and secondary controllers in microgrids. Further, the applied FML-integrated random forest ensemble algorithm outperforms the existing generic FML algorithms during noisy and noise-free datasets with prediction latencies of only 91–134 µs per sample within the 0.1 s sampling interval and requires communication bandwidth of around ∼8.25 KB/s at the control center and ∼2.7 KB/s per edge client for communication.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Reinforcement learning for adaptive maintenance policy optimization under imperfect knowledge of the system degradation model and partial observability of system states

Maintenance policy optimization usually is faced with challenges that arise from an imperfect knowledge of system degradation models and from the partial observability of system degradation states. Here, this paper proposes a reinforcement learning method to address these two challenges for a class of maintenance problems with Markov degradation processes. The reinforcement learning approach consists of a learning component and a planning component. Using sequentially collected observations, at each step of decision-making the learning component improves the knowledge of system degradation in terms of the probability distributions of the transition rates based on sequential Bayesian inference. Using the updated transition rates, at each step of decision-making the maintenance policy optimization problem is then formulated as a partially observable Markov decision problem, and the planning component computes the optimal maintenance policy that maximizes the expected cumulative reward. The proposed method is illustrated using a numerical example with repair and inspection maintenance actions. The result shows that as more observations are collected, the learning component progressively learns the true system degradation process, and the planning component adjusts the optimal maintenance policy accordingly as well, which leads to increased reward.

42 ENGINEERING↗
NASA NTRS1994

The Pacor 2 expert system: A case-based reasoning approach to troubleshooting

The Packet Processor 2 (Pacor 2) Data Capture Facility (DCF) acquires, captures, and performs level-zero processing of packet telemetry for spaceflight missions that adhere to communication services recommendations established by the Consultative Committee for Space Data Systems (CCSDS). A major goal of this project is to reduce life-cycle costs. One way to achieve this goal is to increase automation. Through automation, using expert systems, and other technologies, staffing requirements will remain static, which will enable the same number of analysts to support more missions. Analysts provide packet telemetry data evaluation and analysis services for all data received. Data that passes this evaluation is forwarded to the Data Distribution Facility (DDF) and released to scientists. Through troubleshooting, data that fails this evaluation is dumped and analyzed to determine if its quality can be improved before it is released. This paper describes a proof-of-concept prototype that troubleshoots data quality problems. The Pacor 2 expert system prototype uses the case-based reasoning (CBR) approach to development, an alternative to a rule-based approach. Because Pacor 2 is not operational, the prototype has been developed using cases that describe existing troubleshooting experience from currently operating missions. Through CBR, this experience will be available to analysts when Pacor 2 becomes operational. As Pacor 2 unique experience is gained, analysts will update the case base. In essence, analysts are training the system as they learn. Once the system has learned the cases most likely to recur, it can serve as an aide to inexperienced analysts, a refresher to experienced analysts for infrequently occurring problems, or a training tool for new analysts. The Expert System Development Methodology (ESDM) is being used to guide development.

Sary, Charisse↗
NASA NTRS1995

Constraint-Based Scheduling System

Report describes continuing development of software for constraint-based scheduling system implemented eventually on massively parallel computer. Based on machine learning as means of improving scheduling. Designed to learn when to change search strategy by analyzing search progress and learning general conditions under which resource bottleneck occurs.

Zweben, Monte↗
NASA NTRS2005

On Automating Failure Mode Analysis and Enforcing its Integrity

This paper reports our experience on the development of a design-for-safety (DFS) workbench called Risk Assessment and Management Environment (RAME) for microelectronic avionics systems. Our objective is to transform DFS practice from an ad-hoc, inefficient, error-prone approach to a stringent engineering process such that DFS can keep up with the rapidly growing complexity of avionics systems. In particular, RAME is built upon an information infrastructure that comprises a fault model, a knowledge base, and a failure reporting/tracking system. This infrastructure permits systematic learning from prior projects and enables the automation of failure modes, effects and criticality analysis (FMECA). Among other unique features, the most important advantage of RAME is its capability of directly accepting design source code in hardware description languages (HDLs) for automated failure mode analysis, which enables RAME to be compatible and to evolve with most electronic-computer-aided-design systems. Through an initial experimental evaluation of the RAME prototype, we show that our approach to FMECA automation improves failure mode analysis turn-around-time, completeness, and accuracy.

design for safety↗
NASA NTRS2012

Image Mapping and Visual Attention on the Sensory Ego-Sphere

The Sensory Ego-Sphere (SES) is a short-term memory for a robot in the form of an egocentric, tessellated, spherical, sensory-motor map of the robot s locale. Visual attention enables fast alignment of overlapping images without warping or position optimization, since an attentional point (AP) on the composite typically corresponds to one on each of the collocated regions in the images. Such alignment speeds analysis of the multiple images of the area. Compositing and attention were performed two ways and compared: (1) APs were computed directly on the composite and not on the full-resolution images until the time of retrieval; and (2) the attentional operator was applied to all incoming imagery. It was found that although the second method was slower, it produced consistent and, thereby, more useful APs. The SES is an integral part of a control system that will enable a robot to learn new behaviors based on its previous experiences, and that will enable it to recombine its known behaviors in such a way as to solve related, but novel, task problems with apparent creativity. The approach is to combine sensory-motor data association and dimensionality reduction to learn navigation and manipulation tasks as sequences of basic behaviors that can be implemented with a small set of closed-loop controllers. Over time, the aggregate of behaviors and their transition probabilities form a stochastic network. Then given a task, the robot finds a path in the network that leads from its current state to the goal. The SES provides a short-term memory for the cognitive functions of the robot, association of sensory and motor data via spatio-temporal coincidence, direction of the attention of the robot, navigation through spatial localization with respect to known or discovered landmarks, and structured data sharing between the robot and human team members, the individuals in multi-robot teams, or with a C3 center.

Fleming, Katherine Achim↗
NASA NTRSDate not supplied

Open-source Techniques for Automated Landslide Inventory Generation for Rapid Response

Manual mapping is the most used method for generating landslide inventories. For rapid response scenario this method becomes tedious and time consuming. The Landslide team at NASA Goddard Space Flight Center has been developing open-source landslide mapping systems for rapid generation of landslide inventories. We have developed a Python-based landslide mapping framework known as the Semi-Automatic Landslide Detection (SALaD) system that uses Object-based Image Analysis and machine learning. For production of event-based inventories, SALaD was modified to include a change detection module (SALaD-CD). Utilizing high-resolution imagery form from Planet and Maxar, we have generated multiple rapid response landslide inventories that have been used by emergency responders on the ground, the NASA Disasters program, and academia. Currently, we are exploiting deep learning frameworks for landslide mapping. We are interested to learn about efficient way to harmonize multi-sensor data for creating a long-term record of landslides, training strategies and ongoing deep learning-based efforts for natural hazard characterization within NASA and UMD.

Pukar Amatya↗
DOE OSTI2021

Physics-Informed Machine Learning-Aided System Space Discretization

Decision-making is the process of identifying and choosing alternatives based on an agreed-upon set of metrics and preferences established by the decision-maker. There are options to be considered during the decision-making process and each option offers a different trajectory and associated success profile in moving from a given system state to the desired system state. The decision-making process typically involves uncertainties associated with the current component and system states. In this sense, probabilistic risk assessment (PRA) can be an analytical method and tool for accomplishing the probabilistic aspect of the decision-making process. Dynamic PRA is an evolution of conventional PRA methodology in which driving forces on modeled plant elements and the element behaviors are explicitly modeled over time. In the recent past, risk assessment methodologies have evolved to address risk issues in a continuously evolving environment and a novel probabilistic dynamics framework in continuous time and state-space discretization forms has been proposed. While state-space discretization has shown its strength in both consequence and causal reasoning modes, several challenges, including the computational requirement and physically meaningful system state identification, exist. Conventional system space discretization has usually been done by either the equal width discretization method or a data-driven method. Those methods naturally possess challenges coming from the physical understanding of discretized system space (i.e., system state) and the trajectory moving from a given system state to another system state. The purpose of this paper is to present a physics-based and data-driven system state discretization method such that one can justify what the discretized system space implies and understand the state trajectory from the viewpoint of operational actions.

Kim, Junyung↗
DOE OSTI2020

Machine Learning for Synchrophasor Analysis

The report presents results from the development of a cloud-based, Big Data analysis framework for power systems. The computational pipeline uses the Apache Spark framework running in an OpenStack cloud infrastructure. A real-world phasor measurement unit (PMU) dataset has been used to carry out the analysis. Several Machine Learning (ML) methods have been developed and implemented for event and anomaly detection and classification. Actual examples of power system events detection and analysis using synchrophasor data are presented. It has been shown that applications of the cloud-based computing environment and the Apache Spark framework enable a significant increase in the computational efficiency of large-scale PMU data analysis.

20 FOSSIL-FUELED POWER PLANTS↗
DOE OSTI2025

Physics-based hybrid machine learning for critical heat flux prediction with uncertainty quantification

Critical heat flux (CHF) is a key quantity in nuclear system modeling due to its impact on heat transfer, safety margins, and reactor performance. This study develops and validates an uncertainty-aware hybrid modeling approach that combines machine learning with physics-based models to predict CHF in cases of dryout. The Biasi and Bowring empirical correlations were paired with three ML uncertainty quantification (UQ) techniques: deep neural network (DNN) ensembles, Bayesian neural networks (BNNs), and deep Gaussian processes (DGPs). A pure ML model without a base model was evaluated for comparison. Model performance was assessed under plentiful (7,350 points) and limited (9 points) training data scenarios using parity, uncertainty distributions, and calibration curves. Results show that the Biasi hybrid DNN ensemble achieved the best overall performance, with a mean absolute relative error of 1.846%, and well-calibrated uncertainty estimates. The BNN-based hybrids showed slightly higher error (2.14%) but superior uncertainty calibration. DGP models underperformed, with over 6% error and poor uncertainty calibration. All hybrid models outperformed pure machine learning configurations, demonstrating resistance against data scarcity. These findings indicate that hybrid modeling significantly improves predictive accuracy, interpretability, and resilience to data scarcity. The integration of uncertainty awareness provides actionable confidence in CHF predictions, which is vital for safety-critical decisions in nuclear applications. This hybrid approach offers a viable pathway for deploying ML models in reactor analysis tools while preserving domain knowledge and physical consistency.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
NASA NTRS2019

Accelerated Simulation of Air Pollution Using NVIDIA RAPIDS

Atmospheric chemistry models are a central tool to study and forecast the impact of air pollution on the environment, vegetation, and human health. However, the numerical simulation of chemical kinetics is computationally expensive due to the stiffness of the system of ordinary differential equations that describes atmospheric chemistry. Here we present an alternative approach to the computation of atmospheric chemistry based on machine learning. Our training data set is produced using the NASA Goddard Earth Observing System (GEOS) model with GEOS-Chem chemistry, run on the NASA Center for Climate Simulation (NCCS) Discover supercomputing cluster on 384 Intel Xeon Haswell cores. This model spends more than 50% of total run time on solving atmospheric chemistry. The data set contains as input features the air pollution concentrations before solving the differential equations, together with some key physical parameters such as temperature and sun intensity. As target variables we define the air pollution concentrations after solving the differential equations. Using Dask-cuDF and Dask-XGBoost on the NVIDIA RAPIDS platform on 8 Tesla V100 GPUs, we generate from this training set gradient boosted decision tree models that can reproduce the simulation of chemical kinetics. We do this on the NCCS Advanced Data Analytics Platform (ADAPT) science cloud environment. Our application takes full advantage of recent advances in Dask-XGBoost, such as multi-node and multi-GPU scaling for distributed training with large data sets. The increase in training data size enabled by this is critical to capture the full range of chemical environments encountered across the globe and all annual seasons.The boosted tree models offer good predictability and show many of the features of the full chemistry reference simulation. Further improvements can be achieved through mass balance considerations and by accounting for error correlations. We incorporate the boosted tree models into the GEOS reference model using XGBoost's C API. This enables a seamless integration of the GPU trained models into GEOS-Chem, which is written in Fortran and optimized for use in a massively parallel CPU environment. We show the benefits of this approach and discuss the potential speedup of this machine learning accelerated atmospheric chemistry model.

Keller, Christoph A.↗