SEARCH · Engineering Papers

Results for “learning dynamics”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,387 records · Page 77

All sources NASA NTRS DOE OSTI

NASA NTRS1993

Hidden Markov models for fault detection in dynamic systems

The invention is a system failure monitoring method and apparatus which learns the symptom-fault mapping directly from training data. The invention first estimates the state of the system at discrete intervals in time. A feature vector x of dimension k is estimated from sets of successive windows of sensor data. A pattern recognition component then models the instantaneous estimate of the posterior class probability given the features, p(w(sub i) perpendicular to x), 1 less than or equal to i is less than or equal to m. Finally, a hidden Markov model is used to take advantage of temporal context and estimate class probabilities conditioned on recent past history. In this hierarchical pattern of information flow, the time series data is transformed and mapped into a categorical representation (the fault classes) and integrated over time to enable robust decision-making.

Smyth, Padhraic J.↗

NASA NTRS1995

Hidden Markov models for fault detection in dynamic systems

The invention is a system failure monitoring method and apparatus which learns the symptom-fault mapping directly from training data. The invention first estimates the state of the system at discrete intervals in time. A feature vector x of dimension k is estimated from sets of successive windows of sensor data. A pattern recognition component then models the instantaneous estimate of the posterior class probability given the features, p(w(sub i) (vertical bar)/x), 1 less than or equal to i isless than or equal to m. Finally, a hidden Markov model is used to take advantage of temporal context and estimate class probabilities conditioned on recent past history. In this hierarchical pattern of information flow, the time series data is transformed and mapped into a categorical representation (the fault classes) and integrated over time to enable robust decision-making.

Smyth, Padhraic J.↗

DOE OSTI2026

Revolutionizing Energy Storage: AI, Automation, and Advanced Modeling as Catalysts for Next-Generation Breakthroughs

The Presidential Symposium (PRES) at the 2025 Fall Meeting, hosted by the President’s Office and Energy and Fuels Division, American Chemical Society (ACS) in Washington, DC, brought together a diverse group of chemists, engineers, and materials scientists working in battery materials & systems, automation and artificial intelligence from academia, industry, and national laboratories. The accelerating demand for high-performance, scalable, and sustainable energy storage has catalyzed a paradigm shift in how materials are dis-covered, devices are engineered, and systems are optimized. This Presidential Symposium, entitled “Revolutionizing Energy Storage: AI, Automation, and Advanced Modeling Driving Next-Gen Breakthroughs”, brings together global leaders to unveil transformative strategies anchored in the AAA framework: Artificial Intelligence, Automation, and Advanced Modeling. Artificial Intelligence is redefining the frontiers of energy storage by enabling predictive design, real-time optimization, and intelligent control across diverse chemistries and architectures. Automation is streamlining the synthesis, characterization, and testing of battery materials, dramatically accelerating innovation cycles and unlocking scalable solutions for grid and mobility applications. Advanced Modeling, spanning atomic to system-level scales, provides unprecedented insight into electrochemical dynamics, degradation pathways, and thermal behavior, particularly when coupled with physics-informed machine learning and digital twin technologies. Digital twins, in turn, leverage the AAA framework by integrating real-time data, physics-based models, and AI predictions into dynamic virtual replicas, enabling proactive diagnostics, optimization, and system resilience. Together, these synergistic pillars are not only re-shaping the scientific landscape but also forging a new era of reproducible, data-driven, and resilient energy storage innovation. In conclusion, this symposium marks a pivotal moment in the convergence of computational intelligence and experimental rigor, charting the course for next-generation breakthroughs in lithium-ion, solid-state, and flow battery technologies.

Artificial Intelligence (AI)↗

DOE OSTI2025

Sensitive detection of structural dynamics using a statistical framework for comparative crystallography

Chemical and conformational changes are crucial to protein function and its pharmacological control. X-ray crystallography can reveal these changes in atomic detail, but standard analysis methods, which refine separate datasets, often overlook differences that are subtle or arise in only a subset of molecules. Direct comparison of crystallographic datasets is, in principle, more powerful, but systematic errors (“scales”) often mask changes in the crystallographic observables (“structure factors”). Machine learning algorithms that jointly estimate scales and structure factors can address this limitation. Here, we augment this approach with multivariate, structured priors derived from crystallographic theory, implemented in the variational deep learning framework Careless. Doing so strongly improves the detection of protein dynamics, element-specific anomalous signals, and the binding of drug candidates, offering a robust approach to comparative crystallography and, potentially, to detection of protein dynamics by other structure determination methods.

Hekstra, Doeke R. [Harvard Univ., Cambridge, MA (U↗

NASA NTRS1989

LEADER - An integrated engine behavior and design analyses based real-time fault diagnostic expert system for Space Shuttle Main Engine (SSME)

The LEADER expert system has been developed for automatic learning tasks encompassing real-time detection, identification, verification, and correction of anomalous propulsion system operations, using a set of sensors to monitor engine component performance to ascertain anomalies in engine dynamics and behavior. Two diagnostic approaches are embodied in LEADER's architecture: (1) learning and identifying engine behavior patterns to generate novel hypotheses about possible abnormalities, and (2) the direction of engine sensor data processing to perform resoning based on engine design and functional knowledge, as well as the principles of the relevant mechanics and physics.

Gupta, U. K.↗

DOE OSTI2015

Physics-based statistical learning approach to mesoscopic model selection

In materials science and many other research areas, models are frequently inferred without considering their generalization to unseen data. Here, we apply statistical learning using cross-validation to obtain an optimally predictive coarse-grained description of a two-dimensional kinetic nearest-neighbor Ising model with Glauber dynamics (GD) based on the stochastic Ginzburg-Landau equation (sGLE). The latter is learned from GD “training” data using a log-likelihood analysis, and its predictive ability for various complexities of the model is tested on GD “test” data independent of the data used to train the model on. Using two different error metrics, we perform a detailed analysis of the error between magnetization time trajectories simulated using the learned sGLE coarse-grained description and those obtained using the GD model. We show that both for equilibrium and out-of-equilibrium GD training trajectories, the standard phenomenological description using a quartic free energy does not always yield the most predictive coarse-grained model. Moreover, increasing the amount of training data can shift the optimal model complexity to higher values. Our results are promising in that they pave the way for the use of statistical learning as a general tool for materials modeling and discovery.

36 MATERIALS SCIENCE↗

DOE OSTI2026

Microsecond-latency feedback at a particle accelerator by online reinforcement learning on hardware

The commissioning and operation of future large-scale scientific experiments will challenge current tuning and control methods. Reinforcement learning (RL) algorithms are a promising solution due to their ability to dynamically adapt to changing environments and consider delayed consequences. In many real-world applications, RL policies must produce actions in real time, often within microseconds to milliseconds, imposing significant constraints on system latency and computational overhead that conventional machine learning libraries are not designed to handle. To control phenomena in real time at these timescales, RL needs to be deployed on-the-edge, namely on dedicated hardware located near the system it controls, without relying on a host CPU or cloud-based inference. In this work we present the design and deployment of an experience accumulator system in a particle accelerator. In this system, deep-RL algorithms run using hardware acceleration and act within a few microseconds, enabling the use of RL for control of phenomena like beam instabilities. The training uses the collected data offline to reduce the number of operations carried out on the acceleration hardware. The proposed architecture was tested in real experimental conditions at the Karlsruhe research accelerator, a synchrotron light source, where the system was used to control artificially induced horizontal betatron oscillations in real-time, with a control loop period of just 2.7 μs. The results showed a performance comparable to the commercial feedback system available at the accelerator, demonstrating the viability and potential of this approach. Due to the self-learning and reconfiguration capability of this implementation, a seamless application to other control problems is possible. Applications range from particle accelerators to large-scale research and industrial facilities.

FPGA↗

DOE OSTI2025

Data-Driven Approach for Controlled Icosahedral Boron- Rich Compound Growth

This final technical report summarizes the research accomplishments and research highlights at the end of the funding period. This project aimed to leverage existing and new computational data produced from first-principles and molecular dynamics simulations to understand the thermodynamic, mechanical, and electronic properties of icosahedral boron compounds. The goal is to achieve targeted material properties by controlling the synthesis routes of these boron-rich compounds.

36 MATERIALS SCIENCE↗

DOE OSTI2025

Intelligently Partitioned Phasor-EMT Hybrid Simulations of Large-Scale, High-IBR Power Systems

As the penetration level of power electronics-interfaced renewables such as photovoltaics (PV) and wind has surged in modern electric grids, new operational risks caused by the dynamics of those inverter-based resources (IBRs) are emerging in parallel. Lessons learned from various grid events include that the impact of IBRs on system-level grid stability will become prominent along with the increase of renewables and that the short-timescale dynamic impacts of IBRs on grid stability are not fully captured by current commercial dynamic simulation tools [1] [2]. For example, IBRs can be controlled to mitigate those destabilizing interactions, but conventional phasor-domain tools (e.g. PSS/E, PSLF) often cannot capture that; likewise, the existing electromagnetic transient (EMT) simulation tools (e.g. PSCAD, EMTP) can simulate detailed IBR controls, but for large power systems with many IBRs, slow simulation speeds severely impede the ability to study dynamic events [3] [4]. Massively paralleling simulations using high-performance computing (HPC) can help address this, especially now that cloud-based HPC capability is widely available, but today s EMT tools are not HPC-compatible, and parallelization of dynamic simulation solvers is not trivial because each region can dynamically affect the others. Thus, dynamic simulation of grids with very large numbers of IBRs potentially poses a barrier to the ongoing energy transition.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2019

Demonstration of Machine Learning-Based Model-Independent Stabilization of Source Properties in Synchrotron Light Sources

Synchrotron light sources, arguably among the most powerful tools of modern scientific discovery, are presently undergoing a major transformation to provide orders of magnitude higher brightness and transverse coherence enabling the most demanding experiments. In these experiments, overall source stability will soon be limited by achievable levels of electron beam size stability, presently on the order of several microns, which is still 1–2 orders of magnitude larger than already demonstrated stability of source position and current. Until now source size stabilization has been achieved through corrections based on a combination of static predetermined physics models and lengthy calibration measurements, periodically repeated to counteract drift in the accelerator and instrumentation. In this paper, we now demonstrate for the first time how the application of machine learning allows for a physics- and model-independent stabilization of source size relying only on previously existing instrumentation. Such feed-forward correction based on a neural network that can be continuously online retrained achieves source size stability as low as 0.2 μm (0.4%) rms, which results in overall source stability approaching the subpercent noise floor of the most sensitive experiments.

43 PARTICLE ACCELERATORS↗

DOE OSTI2025

Bridging the length scales in ionic separations via data-driving machine learning

We pursued a data science driven machine learning (ML) approach that blended molecular scale attributes informed from molecular dynamics (MD) simulation and materials properties to the selectivity and energy efficiency in targeted ionic separations using electric fields. The model mixtures investigated for ionic separations are pH sensitive and include organic acids, silica and boron, transition metals, such as copper and chromium. There were two major research thrusts of this project. Firstly, we investigated surrogate models and deep learning that relate material chemistries and structures to selective transport of ionic species under applied electric fields. Secondly we investigated how the bipolar junction interfacial design and water dissociation catalyst in bipolar membranes affect reverse bias polarization behavior and pH modulation in deionization platforms as a function of the platform operating parameters (e.g., cell voltage, residence time, and salt feed concentration). As a result of this work, we also were able to start a new direction, namely ML models for molecular design of surfactants.

36 MATERIALS SCIENCE↗

DOE OSTI2022

Multi-fidelity modeling to predict the rheological properties of a suspension of fibers using neural networks and Gaussian processes

Unveiling the rheological properties of fiber suspensions is of paramount interest to many industrial applications. There are multiple factors, such as fiber aspect ratio and volume fraction, that play a significant role in altering the rheological behavior of suspensions. Three-dimensional (3D) numerical simulations of coupled differential equations of the suspension of fibers are computationally expensive and time-consuming. Machine learning algorithms can be trained on the available data and make predictions for the cases where no numerical data are available. However, some widely used machine learning surrogates, such as neural networks, require a relatively large training dataset to produce accurate predictions. Multi-fidelity models, which combine high-fidelity data from numerical simulations and less expensive lower fidelity data from resources such as simplified constitutive equations, can pave the way for more accurate predictions. Here, we focus on neural networks and the Gaussian processes with two levels of fidelity, i.e., high and low fidelity networks, to predict the steady-state rheological properties, and compare them to the single-fidelity network. High-fidelity data are obtained from direct numerical simulations based on an immersed boundary method to couple the fluid and solid motion. The low-fidelity data are produced by using constitutive equations. Multiple neural networks and the Gaussian process structures are used for the hyperparameter tuning purpose. Results indicate that with the best choice of hyperparameters, both the multi-fidelity Gaussian processes and neural networks are capable of making predictions with a high level of accuracy with neural networks demonstrating marginally better performance.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

DOE OSTI2021

Learning with Delayed Rewards—A Case Study on Inverse Defect Design in 2D Materials

Defect dynamics in materials are of central importance to a broad range of technologies from catalysis to energy storage systems to microelectronics. Material functionality depends strongly on the nature and organization of defects-their arrangements often involve intermediate or transient states that present a high barrier for transformation. The lack of knowledge of these intermediate states and the presence of this energy barrier presents a serious challenge for inverse defect design, especially for gradient-based approaches. Here, we present a reinforcement learning (RL) [Monte Carlo Tree Search (MCTS)] based on delayed rewards that allow for efficient search of the defect configurational space and allows us to identify optimal defect arrangements in low-dimensional materials. Using a representative case of two-dimensional MoS 2 , we demonstrate that the use of delayed rewards allows us to efficiently sample the defect configurational space and overcome the energy barrier for a wide range of defect concentrations (from 1.5 to 8% S vacancies)-the system evolves from an initial randomly distributed S vacancies to one with extended S line defects consistent with previous experimental studies. Detailed analysis in the feature space allows us to identify the optimal pathways for this defect transformation and arrangement. Comparison with other global optimization schemes like genetic algorithms suggests that the MCTS with delayed rewards takes fewer evaluations and arrives at a better quality of the solution. The implications of the various sampled defect configurations on the 2H to 1T phase transitions in MoS 2 are discussed. In this study, we introduce a RL strategy employing delayed rewards that can accelerate the inverse design of defects in materials for achieving targeted functionality.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

Sim2Real Autonomous Robotic Exploration [Poster]

Autonomous robots offer promising solutions for exploration in environments that are inaccessible or hazardous to humans. Despite this, physical training of such robots is often constrained by safety risks, high cost or limited accessibility. This project presents an end-to-end simulation to reality pipeline leveraging Nvidia Isaac Sim and Boston Dynamics' Spot to enable autonomous navigation in indoor environments. A reinforcement learning policy is first trained using Nvidia Isaac Lab to establish Spot's locomotion pattern. Virtual LiDAR sensors are then integrated to perform SLAM-based navigation using simulated odometry. Finally, the simulated navigation scheme is transferred to a physical Spot robot to inspect and record images of a real-world room by repeating the learnt trajectory. The proposed framework highlights the potential of scalable training in simulation and reliable deployment in physical environments. Future directions include dynamic trajectory generation in unseen and challenging environments and integration of environmental sensing like temperature, radiation or humidity via sensor and material simulation.

97 - MATHEMATICS AND COMPUTING↗

DOE OSTI2020

Deep Learning Emulation of Subgrid-Scale Processes in Turbulent Shear Flows

Deep neural networks (DNNs) are developed from a data set obtained from the dynamic Smagorinsky model to emulate the subgrid-scale (SGS) viscosity (ν sgs ) and diffusivity (κ sgs ) for turbulent stratified shear flows encountered in the oceans and the atmosphere. These DNNs predict ν sgs and κ sgs from velocities, strain rates, and density gradients such that the evolution of the kinetic energy budget and density variance budget terms is similar to the corresponding values obtained from the original dynamic Smagorinsky model. These DNNs also compute ν sgs and κ sgs ~2–4 times quicker than the dynamic Smagorinsky model resulting in a ~2–2.5 times acceleration of the entire simulation. This study demonstrates the feasibility of deep learning in emulating the subgrid-scale (SGS) phenomenon in geophysical flows accurately in a cost-effective manner. In a broader perspective, deep learning-based surrogate models can present a promising alternative to the traditional parameterizations of the subgrid-scale processes in climate models.

58 GEOSCIENCES↗

DOE OSTI2025

Designing a quantum-accurate machine-learning potential to enable large-scale simulations of deuterium under shock

Large-scale molecular dynamics of deuterium under shock can elucidate kinetic processes vital to the target design in inertial confinement fusion and high-energy-density experiments. However, modeling the complex evolution of this material from an insulating molecular state at ambient pressure to an ionized, atomic fluid under strong shock is beyond the capability of simple pair and even bond order potentials. We thus train a quantum-accurate and broadly transferable machine-learning interatomic potential for deuterium using the Chebyshev Interaction Model for Efficient Simulations framework. We show that due to an improved description of the molecular-to-atomic transition, our model is able to better reproduce the ab initio equation of state, radial distribution functions, and principal Hugoniot than bond order potentials. This represents an important step toward large-scale quantum-accurate and nonequilibrium simulations of complicated systems under dynamic changes including phase transitions.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2017

Forecasting influenza-like illness dynamics for military populations using neural networks and social media

This work is the first to take advantage of recurrent neural networks to predict influenza-like-illness (ILI) dynamics from various linguistic signals extracted from social media data. Unlike other approaches that rely on timeseries analysis of historical ILI data [1, 2] and the state-of-the-art machine learning models [3, 4], we build and evaluate the predictive power of Long Short Term Memory (LSTMs) architectures capable of nowcasting (predicting in \real-time") and forecasting (predicting the future) ILI dynamics in the 2011 { 2014 influenza seasons. To build our models we integrate information people post in social media e.g., topics, stylistic and syntactic patterns, emotions and opinions, and communication behavior. We then quantitatively evaluate the predictive power of different social media signals and contrast the performance of the-state-of-the-art regression models with neural networks. Finally, we combine ILI and social media signals to build joint neural network models for ILI dynamics prediction. Unlike the majority of the existing work, we specifically focus on developing models for local rather than national ILI surveillance [1], specifically for military rather than general populations [3] in 26 U.S. and six international locations. Our approach demonstrates several advantages: (a) Neural network models learned from social media data yield the best performance compared to previously used regression models. (b) Previously under-explored language and communication behavior features are more predictive of ILI dynamics than syntactic and stylistic signals expressed in social media. (c) Neural network models learned exclusively from social media signals yield comparable or better performance to the models learned from ILI historical data, thus, signals from social media can be potentially used to accurately forecast ILI dynamics for the regions where ILI historical data is not available. (d) Neural network models learned from combined ILI and social media signals significantly outperform models that rely solely on ILI historical data, which adds to a great potential of alternative public sources for ILI dynamics prediction. (e) Location-specific models outperform previously used location-independent models e.g., U.S. only. (f) Prediction results significantly vary across geolocations depending on the amount of social media data available and ILI activity patterns.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2020

Influence of geochemical reactions on the creep behavior of Mt. Simon sandstone

The capture and subsurface storage of carbon dioxide is a sustainable option that is currently pursued worldwide to mitigate greenhouse gas effect. However, predicting the long-term mechanical integrity of CO 2 underground storage systems remains a challenge. To address that question, it is essential to understand the influence of fluid-rock chemo-mechanical interactions on the long-term and on the time-dependent mechanical properties. In turn, the long-term mechanical response and the time-dependent mechanical behavior can be represented by the creep response. We investigate the impact of CO 2 -induced geochemical reaction on the creep response of Mt. Simon sandstone with a 50–400 micron grain size. We perform static and dynamic flow experiments on Mt. Simon sandstone specimens under geological conditions, at a temperature of T = 50 - 53 °C and for CO 2 pressures of P = 8:62; 17:2 MPa under both static flow and dynamic flow-through conditions. After aging, we employ creep indentation testing, high-resolution SEM-EDS, computer vision, machine learning, and micromechanics modeling to probe changes on the microstructure and mechanical properties. Following both static and dynamic flow-through experiments, we observe a 10–22% decrease in quartz volume fraction and an increase in both the microporosity (7–28%) and nanoporosity (60–65%). Additional CO 2 -induced microstructural changes include an enlargement of pore throats and the formation of channels. These observations point to the presence of CO 2 -induced K-feldspar dissolution and clay dissolution reactions. Here, the macroscopic creep behavior is logarithmic and the macroscopic creep modulus varies depending on the microporosity and the relative quartz and feldspar content. As a result of these geochemical reactions and of the related microstructural changes, a 55-60% decrease in the macroscopic logarithmic creep modulus is predicted.

58 GEOSCIENCES↗