Search NASA⌕ Search

SEARCH · Search NASA

Results for “Learning control”

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 1,063 records · Page 59
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Predicting synthetic mRNA stability using massively parallel kinetic measurements, biophysical modeling, and machine learning

Abstract mRNA degradation is a central process that affects all gene expression levels, though it remains challenging to predict the stability of a mRNA from its sequence, due to the many coupled interactions that control degradation rate. Here, we carried out massively parallel kinetic decay measurements on over 50,000 bacterial mRNAs, using a learn-by-design approach to develop and validate a predictive sequence-to-function model of mRNA stability. mRNAs were designed to systematically vary translation rates, secondary structures, sequence compositions, G-quadruplexes, i-motifs, and RppH activity, resulting in mRNA half-lives from about 20 seconds to 20 minutes. We combined biophysical models and machine learning to develop steady-state and kinetic decay models of mRNA stability with high accuracy and generalizability, utilizing transcription rate models to identify mRNA isoforms and translation rate models to calculate ribosome protection. Overall, the developed model quantifies the key interactions that collectively control mRNA stability in bacterial operons and predicts how changing mRNA sequence alters mRNA stability, which is important when studying and engineering bacterial genetic systems.

Cetnar, Daniel P.↗
DOE OSTI2025

Aerosol Influences on Cloud Water: Insights From ARM EPCAPE Observations With Explainable Machine Learning

This study employs an explainable machine learning (ML) framework (XGBoost-SHapley Additive exPlanations analysis) to investigate controlling factors on cloud liquid water path (LWP) using EPCAPE observations near the California coast. Aerosols are found to be the dominant factor explaining LWP variability, surpassing meteorological factors (MFs). By isolating aerosol effects from meteorological influences, the ML reveals a negative linear relationship between LWP and cloud droplet number concentration (Nd) in log space, likely driven by entrainment drying via evaporation-entrainment feedback. This aligns with the negative regime of the inverted-V relationship reported in previous studies, while no positive LWP responses are found due to a limited number of precipitating cases in EPCAPE. Furthermore, the sensitivity of LWP to Nd shows a non-linear dependence on MFs like moisture contrast between surface and free troposphere and lower-tropospheric stability. This occurs due to the interplay between the MFs' direct effects on entrainment drying and indirect effects through LWP adjustments.

EPCAPE observations↗
DOE OSTI2025

Architectural Approaches for Integrating ADMS and DERMS: Challenges, Comparisons, and Real-World Use Cases

The electrical distribution landscape is rapidly transforming due to the proliferation of distributed energy resources (DERs) such as solar panels, wind turbines, battery storage systems, combined heat and power units, and electric vehicles, introducing variability and uncontrollability that traditional grid operators are ill-equipped to manage. This transformation is further accelerated by advancements in Information and Communication Technology infrastructure that connects control centers with end devices, demanding automation and a deeper understanding of new technologies by utility personnel. Advanced grid control techniques using system-level optimization, Artificial Intelligence, and Machine Learning at the enterprise level and distributed level are evolving to address these issues. There is also an opportunity to utilize the enormous data created by these new DER technologies in the grid. Advanced Distribution Management Systems (ADMS) and Distributed Energy Resource Management Systems (DERMS) are critical in addressing these challenges by automating grid operations and enhancing reliability. Given the relatively recent development of ADMS and DERMS, and the still relatively low level of ADMS and DERMS deployment in the industry, there is a notable deficiency in the comprehensive understanding of the challenges and benefits associated with these new technologies, especially with their complementary natures and integration architectures. This paper aims to bridge the knowledge gap in ADMS and DERMS integration, presenting three distinct integration architectures currently available, and discussing the challenges and benefits of each architecture to guide utilities, industry professionals, and researchers in optimizing grid management and decision-making processes for a resilient and efficient energy future.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2016

Training on Transport Security of Nuclear/Radioactive Materials for Key Audiences

Beginning in 2013, the U.S. Department of Energy (DOE) Packaging Certification Program (PCP), Office of Packaging and Transportation, Office of Environmental Management has sponsored a series of three training courses on Security of Nuclear and Other Radioactive Materials during Transport. These courses were developed and hosted by Argonne National Laboratory staff with guest lecturers from both the U.S. and international organizations and agencies including the U.S. Nuclear Regulatory Commission (NRC), Federal Bureau of Investigation (FBI), the U.S. Department of Energy (DOE), National Nuclear Security Administration (NNSA), DOE national laboratories, the International Atomic Energy Agency (IAEA), the World Nuclear Transport Institute (WNTI), and the World Institute for Nuclear Security (WINS). Each of the three courses held to date were one-week in length. The courses delved in detail into the regulatory requirements for transport security, focusing on international and U.S.-domestic requirements and guidance documents. Lectures, in-class discussions and small group exercises, including tabletop (TTX) and field exercises were designed to enhance the learning objectives for the participants. For example, the field exercise used the ARG-US radio frequency identification (RFID) remote surveillance system developed by Argonne for DOE/PCP to track and monitor packages in a mock shipment, following in-class exercises of developing a transport security plan (TSP) for the mock shipment, performing a readiness review and identifying needed corrective actions. Participants were able to follow the mock shipment on the webpage in real time in the ARG-US Command Center at Argonne including “staged” incidents that were designed to illustrate the importance of control, command, communication and coordination in ensuring transport security. Great lessons were learned based on feedback from the participant’s course evaluations with the series of the courses. Since the development of the relevant teaching materials for the course have largely been completed, tailoring the course for targeted audiences becomes a relatively easy task, requiring less effort and providing more flexibility for both the lecturers and future participants. One-day or two-day courses with focus specifically on the U.S. transport security requirements can be delivered, at locations away from Argonne, by one or two principal lecturers to targeted audiences such as regulators, shippers, carriers, state and local law enforcement personnel, and emergency responders. This paper will highlight the lessons learned in hosting previous one-week courses and discuss the development of options for detailed and/or customized courses/workshops for targeted key audiences.

2016 Waste Management March 6-10 Training on Trans↗
DOE OSTI2024

Avoiding fusion plasma tearing instability with deep reinforcement learning

For stable and efficient fusion energy production using a tokamak reactor, it is essential to maintain a high-pressure hydrogenic plasma without plasma disruption. Therefore, it is necessary to actively control the tokamak based on the observed plasma state, to manoeuvre high-pressure plasma while avoiding tearing instability, the leading cause of disruptions. This presents an obstacle-avoidance problem for which artificial intelligence based on reinforcement learning has recently shown remarkable performance. However, the obstacle here, the tearing instability, is difficult to forecast and is highly prone to terminating plasma operations, especially in the ITER baseline scenario. Previously, we developed a multimodal dynamic model that estimates the likelihood of future tearing instability based on signals from multiple diagnostics and actuators. Here we harness this dynamic model as a training environment for reinforcement-learning artificial intelligence, facilitating automated instability prevention. We demonstrate artificial intelligence control to lower the possibility of disruptive tearing instabilities in DIII-D, the largest magnetic fusion facility in the United States. The controller maintained the tearing likelihood under a given threshold, even under relatively unfavourable conditions of low safety factor and low torque. In particular, it allowed the plasma to actively track the stable path within the time-varying operational space while maintaining H-mode performance, which was challenging with traditional preprogrammed control. This controller paves the path to developing stable high-performance operational scenarios for future use in ITER.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2019

Sequential Learning with Active Partial Labeling for Building Metadata

Modern buildings are instrumented with thousands of sensing and control points. The ability to automatically extract the physical context of each point, e.g., the type, location, and relationship with other points, is the key to enabling building analytics at scale. However, this process is costly as it usually requires domain expertise with a deep understanding of the building system and its point naming scheme. In this study, we aim to reduce the human effort required for mapping sensors to their context, i.e., metadata mapping. We formulate the problem as a sequential labeling process and use the conditional random field to exploit the regular and dependent structures observed in the metadata. We develop a suite of active learning strategies to adaptively select the most informative subsequences in point names for human labeling, which significantly reduces the inputs from domain experts.We evaluated our approach on three different buildings and observed encouraging performance in metadata mapping from the proposed solution.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2023

Increased Interpretability for Model-Driven Deception: MARS LDRD Project

Machine learning has been proposed as a solution to several cybersecurity solutions and one of the most promising applications is for digital twins for intrusion detection and driving deceptive defense. However, machine learning techniques often result in a black-box function that is difficult for end users to interpret which for deception limits their ability to effectively define decoys. In this report, an approach to validate the equations learned are accurate is provided and demonstrated. Following, begins the process of addressing this issue for a model-driven deception technology that produces equations representing the physical process controlled by operation technology devices. This research was performed by applying subject matter expert context to machine learned models.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Do Mandates Deliver Cost Reductions for Energy Storage?

In 2013, California implemented a mandate directing the state’s investor-owned utilities to procure 1325 MW of energy storage, to help integrate nondispatchable renewable sources of energy and assist the state in meeting its environmental goals. This paper evaluates this policy’s impact of both battery deployment, and cost, finding that as of 2019, the state was effective in spurring nearly 500 MWh of battery storage deployment over what would have been installed in absence of the policy. This additive deployment would have the effect of reducing global battery cell costs by roughly $1.00/ kWh, based on learning by doing. To support these findings, we utilize both a difference in differences estimation, and a synthetic control analysis, both of which allow us to compare battery deployment in California, to deployment in other states. To pair deployment to cost reduction, we use a learning curve analysis, which links battery shipments to cell and storage block costs. For policymakers, these results provide evidence to the effectiveness of mandates in promoting storage deployment and help explain how these policies can induce downstream effects.

Boff, Daniel S.↗
DOE OSTI2026

From IMT Device Measurements to Network-Level Consequences: When Learning Suppresses Beyond-LIF Neuron Dynamics

Emerging neuromorphic devices such as insulator--metal transition (IMT) devices exhibit complex temporal dynamics, including slow internal state memory, hysteresis, and burst-like firing, which are poorly captured by conventional leaky integrate-and-fire (LIF) neurons. However, it remains unclear when such dynamics influence learning and inference at the network level, particularly under commonly used unsupervised plasticity rules. We present a controlled, full-stack co-design study spanning experimental characterization of individual IMT devices, compact neuron model development, and large-scale spiking network simulations with identical architectures and learning rules. Rather than optimizing benchmark accuracy, our goal is to diagnose when neuron-level dynamics survive learning and competition, and when they are suppressed, to inform the co-design of devices, networks, and learning rules that can exploit beyond-LIF complexity.

42 ENGINEERING↗
DOE OSTI2021

Computational Math Problems for a Clean Energy Future

Cutting edge computational mathematics are ubiquitous in renewable energy research. Problems in resilient and reliable electric grid operations, infrastructure planning, wind farm yaw control, and more demand sophisticated and scalable computational tools that enable the transition of renewable energy technologies from proof of concept to deployment into our energy system. The mission of the Computational Science Center at NREL is to lead the lab's efforts to solve energy challenges using high-performance computing (HPC), computational science, applied mathematics, scientific data management, visualization, and informatics. In this poster, we provide a short overview of three areas of computational mathematics research at NREL: wind power scenario generation for stochastic grid operations and infrastructure planning, improved rational function approximations for electromagnetic transients codes, and wind farm yaw control using a combination of the Alternating Direction Method of Multipliers (ADMM) and reinforcement learning (RL). Increasing penetrations of renewable energy into power grids motivate the investigation of new approaches to characterizing uncertainty for five-minute economic dispatch problems. Similarly, as the penetration of distributed energy resources on power grids increases, it becomes important to revisit our methods of modelling transient phenomena, i.e. electromagnetic transients programs. Finally, the combination of ADMM and RL for wind farm yaw control presented here can potentially increase the efficiency of the deployed distributed controllers by orders of magnitude.

ADMM↗
DOE OSTI2018

Embedded Hardware Solution for Cybersecurity in Industrial Control Systems

Industrial Control Systems are the backbone of manufacturing, power, and critical infrastructure. These systems are made up of electronic and mechanical devices that operate on complex feedback systems that allow the production of consumer products, electricity, clean water, and nuclear industries. This broad reach of cybersecurity has earned it a place in the strategic roadmaps for many government agencies, including the Department of Energy. Their efforts stem from two general initiatives which are to improve cybersecurity in the energy sector and to strengthen effectiveness of Department of Energy incident management capabilities. Particular emphasis is in improving learning and preservations of knowledge at the labs, and to encourage collaboration between the labs. This project aims to develop Savannah River National Laboratory’s knowledge of industrial control systems cybersecurity by providing our engineers the opportunity to learn and execute advanced concepts in cybersecurity to real problems in industrial control systems. Successful execution of this project will enhance Savannah River National Laboratory’s knowledge and capability in the realm of Industrial Control System and Operational Technology cybersecurity as well as advance understanding of defensive needs in these environments. This will directly impact Savannah River National Laboratory’s capability to contribute and collaborate with Department of Energy, other Labs, and commercial partners in meeting Department of Energy national industrial control systems/Operations Technology cybersecurity goals.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Divide and conquer: separating the two probabilities in seismic phase picking

There are two fundamental probabilities in the seismic phase picking process—the probability of the existence of a seismic phase (detection probability) and the probability associated with the phase arrival time estimation (timing probability). The nearly ubiquitous approach in developing deep learning phase picking models is to use a kernel, such as a truncated Gaussian, to mask the labelled phase arrival time and train a segmentation model. Once a model is trained, the times of the peaks in the output are taken as phase arrival times (picks), and the height of the peaks are taken as ‘probability’ of the picks. Here, we show that this ‘probability’ represents neither the detection nor the timing probability because this approach forces the output to follow the shape of the kernel. We introduce an approach using two models to estimate these two distinct probabilities. We use a binary classifier with a calibrated confidence to address the detection probability and a multiclass classifier to obtain a probability mass function to address the timing probability. This new approach can make the deep learning-based phase picking process more interpretable and provide options to logically control seismic monitoring workflows.

58 GEOSCIENCES↗
DOE OSTI2019

Alliance Project: Secure Control Systems for the Energy Sector

The Alliance Project addresses Area of Interest 4: Secure Remote Access for the Energy Sector, by combining physical and cyber access under one cybersecurity access system. The Alliance Project built on the successful completion of the Lemnos and Padlock Project (DOE-Funded Project started in 2007 and 2010) and researched and developed a solution for an Ethernet Security Gateway with the functionality required to integrate the physical access control cyber system and interface with legacy and new proximity card readers used for physical access requests. This project focused on securing and enhancing the cyber system the physical access control system operates on. The team tested and demonstrated the system solution on the SEL campus. Currently the physical access cyber system is completely separate from the cyber access control cyber system. With a single system industry benefits include: (1) Single system to learn and teach employees; (2) Single system that collects and alerts on logs and events simplifying incident response plans and NERC CIP compliance; (3) Unifies trust management to a single system reducing the potential errors in privilege escalation or revocation; (4) Provides a stronger cybersecurity platform the physical access control system operates on. Today they are mostly plain text protocols and little cyber awareness; (5) Integration of physical access awareness allows the cyber system to react and adjust. In some cases, the cyber access can be enhanced with authorized physical access and other cases the cyber access can be more restricted with unauthorized physical access; and (6) Enables the utility to establish as large or as small a physical access control system as they require. One example would be when a utility shares a substation with a neighbor utility and can’t rely on the substation door for the physical access control. The Alliance technology enables them to lock equipment racks simply with no scalability issues because it stands on the cyber security infrastructure which is already highly scalable.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Delamination-informed lifecycle decisions: A dielectric and machine learning framework for composite sorting and recycling

Composite materials are widely used in aerospace, marine, and automotive sectors due to their high strength-to-weight ratio and durability. However, their long-term reliability can be compromised by damage accumulation. Specifically, delamination initiation serves as a precursor to structural failure, which is often difficult to detect during damage inspection. Identifying and sorting delamination initiation in samples not only increases operational safety while providing critical information for end-of-life decisions, which influences both the service life extension value and the efficiency of fiber extraction during recycling. This research addresses two challenges: (1) developing a nondestructive, ex-situ framework to sort composite materials based on damage severity, particularly delamination, and (2) understanding how damage in composites influences resin removal during pyrolysis. Both experimental work and finite element analysis were performed to predict critical stress levels that are associated with delamination onset. Based on these results, three loading levels 50 %, 75 %, and 90 % of maximum stress, were selected for controlled experiments, generating composite samples with varying extents of damage for machine learning model training. Microscopic imaging of these samples confirmed the damage progression from matrix cracking to delamination, validating the computational predictions. We explored supervised machine learning using dielectric measurements to classify damage states. Preliminary results show an artificial neural network can identify early delamination which is a potential precursor to failure, with 94.44 % accuracy on our dataset. A parallel investigation into the effect of damage severity on pyrolysis recycling showed that heavily delaminated samples required significantly less energy for comparable matrix removal than undamaged samples.

dielectric variables↗
DOE OSTI2021

A Modular and Transferable Reinforcement Learning Framework for the Fleet Rebalancing Problem

Mobility on demand (MoD) systems show great promise in realizing flexible and efficient urban transportation. However, significant technical challenges arise from operational decision making associated with MoD vehicle dispatch and fleet rebalancing. For this reason, operators tend to employ simplified algorithms that have been demonstrated to work well in a particular setting. To help bridge the gap between novel and existing methods, we propose a modular framework for fleet rebalancing based on model-free reinforcement learning (RL) that can leverage an existing dispatch method to minimize system cost. In particular, by treating dispatch as part of the environment dynamics, a centralized agent can learn to intermittently direct the dispatcher to reposition free vehicles and mitigate against fleet imbalance. We formulate RL state and action spaces as distributions over a grid partitioning of the operating area, making the framework scalable and avoiding the complexities associated with multiagent RL. Numerical experiments, using real-world trip and network data, demonstrate that RL reduces waiting time by 28% to 38% for the same-day evaluation, 17% to 44% for cross-day evaluation, and 22% to 25% for cross-season evaluation compared with no rebalancing scenarios. This approach has several distinct advantages over baseline methods including: improved system cost; high degree of adaptability to the selected dispatch method; and the ability to perform scale-invariant transfer learning between problem instances with similar vehicle and request distributions.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2020

Prediction of histone post-translational modifications using deep learning

Abstract Motivation Histone post-translational modifications (PTMs) are involved in a variety of essential regulatory processes in the cell, including transcription control. Recent studies have shown that histone PTMs can be accurately predicted from the knowledge of transcription factor binding or DNase hypersensitivity data. Similarly, it has been shown that one can predict PTMs from the underlying DNA primary sequence. Results In this study, we introduce a deep learning architecture called DeepPTM for predicting histone PTMs from transcription factor binding data and the primary DNA sequence. Extensive experimental results show that our deep learning model outperforms the prediction accuracy of the model proposed in Benveniste et al. (PNAS 2014) and DeepHistone (BMC Genomics 2019). The competitive advantage of our framework lies in the synergistic use of deep learning combined with an effective pre-processing step. Our classification framework has also enabled the discovery that the knowledge of a small subset of transcription factors (which are histone-PTM and cell-type-specific) can provide almost the same prediction accuracy that can be obtained using all the transcription factors data. Availabilityand implementation https://github.com/dDipankar/DeepPTM. Supplementary information Supplementary data are available at Bioinformatics online.

Baisya, Dipankar Ranjan (ORCID:0000000267847359)↗
DOE OSTI2023

Deep reinforcement learning assisted co-optimization of Volt-VAR grid service in distribution networks

With the increasing penetration of distributed energy resources in distribution networks, Volt-VAR control and optimization (VVC/VVO) have become very important to ensure an acceptable quality of service to all customers. System operators can rely on slow-responding utility devices, including capacitor banks and on-load tap changing transformers, along with fast-responding battery and photovoltaic (PV) inverters for the VVC/VVO implementation. Because of variations in response time of these two classes of devices, and different control actions (discrete versus continuous), coordinated and optimal scheduling and operation have become of utmost importance. Here, this paper develops a look-ahead deep reinforcement learning (DRL)-based multi-objective VVO technique to improve the voltage profile of active distribution networks, decrease network and inverter power loss, and save the operational cost of the grid. It proposes a deep deterministic policy gradient (DDPG)-based approach to schedule the optimal reactive and/or active power set-points of fast-responding inverters, and a deep Q-network (DQN)-based DRL agent to schedule the discrete decisions variables of slow-responding assets. The reactive power output of PV and battery smart inverters are scheduled at 30-minute intervals and the capacitors’ commitment status is scheduled with several hour intervals. The proposed framework is validated on the modified IEEE 34-bus and 123-bus test cases with embedded PV and PV-plus-storage. To validate the efficacy of the proposed VVO, it is compared with several scenarios, including the base case without VVO, localized droop control of DERs, DDPG-only, and twin delayed DDPG (TD3) agent-based DRL techniques. The results justify the superior performance of the proposed method to improve the voltage profile, reduce network power loss, and minimize the look-ahead grid operational cost while minimizing the undesirable power losses in inverters as a result of power factor adjustments.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

An adaptive, data-driven multiscale approach for dense granular flows

The accuracy of coarse-grained continuum models of dense granular flows is limited by the lack of high-fidelity closure models for granular rheology. One approach to addressing this issue, referred to as the hierarchical multiscale method, is to use a high-fidelity fine-grained model to compute the closure terms needed by the coarse-grained model. The difficulty with this approach is that the overall model can become computationally intractable due to the high computational cost of the high-fidelity model. In this work, we describe a multiscale modeling approach for dense granular flows that utilizes neural networks trained using high-fidelity discrete element method (DEM) simulations to approximate the constitutive granular rheology for a continuum incompressible flow model. Our approach leverages an ensemble of neural networks to estimate predictive uncertainty that allows us to determine whether the rheology at a given point is accurately represented by the neural network model. Additional DEM simulations are only performed when needed, minimizing the number of additional DEM simulations required when updating the rheology. This adaptive coupling significantly reduces the overall computational cost of the approach while controlling the error. In addition, the neural networks are customized to learn regularized rheological behavior to ensure well-posedness of the continuum solution. We first validate the approach using two-dimensional steady-state and decelerating inclined flows. We then demonstrate the efficiency of our approach by modeling three-dimensional sub-aerial granular column collapse for varying initial column aspect ratios, where our multiscale method compares well with the computationally expensive computational fluid dynamics (CFD)-DEM simulation.

Dense granular flows↗