Search NASA⌕ Search

SEARCH · Search NASA

Results for “Safe Learning”

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 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

A safe reinforcement learning algorithm for supervisory control of power plants

Traditional control theory-based methods require tailored engineering for each system and constant fine-tuning. In power plant control, one often needs to obtain a precise representation of the system dynamics and carefully design the control scheme accordingly. Model-free Reinforcement learning (RL) has emerged as a promising solution for control tasks due to its ability to learn from trial-and-error interactions with the environment. It eliminates the need for explicitly modeling the environment’s dynamics, which is potentially inaccurate. However, the direct imposition of state constraints in power plant control raises challenges for standard RL methods. To address this, we propose a chance-constrained RL algorithm based on Proximal Policy Optimization for supervisory control. Our method employs Lagrangian relaxation to convert the constrained optimization problem into an unconstrained objective, where trainable Lagrange multipliers enforce the state constraints. In conclusion, our approach achieves the smallest distance of violation and violation rate in a load-follow maneuver for an advanced Nuclear Power Plant design.

constrained optimization↗
DOE OSTI2024

Optimal Management of Grid-Interactive Efficient Buildings via Safe Reinforcement Learning

Reinforcement learning (RL)-based methods have achieved significant success in managing grid-interactive efficient buildings (GEBs). However, RL does not carry intrinsic guarantees of constraint satisfaction, which may lead to severe safety consequences. Besides, in GEB control applications, most existing safe RL approaches rely only on the regularisation parameters in neural networks or penalty of rewards, which often encounter challenges with parameter tuning and lead to catastrophic constraint violations. To provide enforced safety guarantees in controlling GEBs, this paper designs a physics-inspired safe RL method whose decision-making is enhanced through safe interaction with the environment. Different energy resources in GEBs are optimally managed to minimize energy costs and maximize customer comfort. The proposed approach can achieve strict constraint guarantees based on prior knowledge of a set of developed hard steady-state rules. Simulations on the optimal management of GEBs, including heating, ventilation, and air conditioning (HVAC), solar photovoltaics, and energy storage systems, demonstrate the effectiveness of the proposed approach.

Huo, Xiang↗
DOE OSTI2025

Safe Reinforcement Learning-Based Transient Stability Control for Islanded Microgrids With Topology Reconfiguration

This paper proposes a safe reinforcement learning (RL)-based transient stability emergency control (TSEC) method for islanded microgrids. RL requires extensive interaction with the environment to learn control strategies, hence, a data-driven approach is used as a substitute for time-consuming time-domain simulation calculations. Deep sigma point processes (DSPP), which is a Gaussian process model, is utilized to predict the normal distribution of transient stability of microgrids and to construct a transient stability chance constraint. Reward-constrained policy optimization (RCPO) can simultaneously achieve objective prediction, policy learning, and constraint cost coefficient update across multiple timescales. RCPO interacts with the DSPP-based microgrid environment through a multi-process parallel manner, greatly increasing the training speed. Case studies on a real islanded microgrid demonstrate that the proposed method can efficiently and quickly obtain the optimal emergency control strategy while adhering to all hard constraints.

14 SOLAR ENERGY↗
DOE OSTI2026

Safe Deep Reinforcement Learning for Robust Frequency and Voltage-Constrained Networked Microgrid Restoration

Here, this paper proposes a safe soft actor-critic reinforcement learning (RL) algorithm–based controller for networked microgrid restoration. It formulates the post black-start start as a finite-horizon constrained Markov decision process. The RL agent co-optimizes real and reactive power set-points for both grid-forming and grid-following inverters under explicit voltage and frequency constraints, while enforcing proper power sharing via the Mean Active Power Sharing Index (MPSI) and Mean Reactive Power Sharing Index (MQSI). Numerical results obtained on the IEEE 123-bus distribution system show that the proposed method achieves a mean voltage build-up time of 0.01 s without breaching the 5% sharing-violation budget under various load scenarios, considering MPSI and MQSI indices. These findings demonstrate that the proposed method yields fast and safe black-start schedules without resorting to heuristic penalties.

Selim, Alaa [Dartmouth College, Hanover, NH (Unite↗
DOE OSTI2026

Safe Deep Reinforcement Learning for Active Distribution System Model Predictive Control with EVs and DERs

The temporal and spatial mismatch between PV generation and electric vehicle (EV) charging and discharging may cause voltage violations in active distribution networks. Despite the widespread use of deep reinforcement learning (DRL) in power system optimization and control, it lacks guarantees on constraint satisfaction during both training and deployment. This paper proposes a Lagrangian-based safe DRL approach for model predictive control (MPC) of active distribution systems with large-scale integration of PVs, EVs, and energy storage systems (ESSs). A Transformer-LSTM time-series model is proposed to forecast EV charging demand, which is then formulated as a constraint to ensure charging requirements are met. Using this prediction, a Lagrangian-based safe soft actor-critic (SAC) framework is developed for real-time control in a three-phase unbalanced distribution system, enforcing voltage safety constraints while optimizing the cumulative net reward. By integrating the forecasting model with multi-period constraints, the proposed framework jointly coordinates PV systems, EV charging and discharging, and ESS scheduling within the MPC horizon. Numerical experiments on a modified IEEE 123-bus system with real-world data show that, under a high PV penetration scenario, the proposed method increases the net reward by 30.74% and reduces average voltage violations from 0.0011 p.u. to 0.0002 p.u. compared with standard SAC. Compared with the optimal power flow (OPF) approach, it achieves similar voltage security while yielding lower line losses. It also maintains real-time control capability, reducing operation latency to 53.21 ms per 15-minute control interval. The proposed method remains effective under varying PV/EV penetrations and load conditions.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Safe Physics-Informed Machine Learning for Dynamics and Control

This tutorial paper focuses on safe physics-informed machine learning in the context of dynamics and control, providing a comprehensive overview of how to integrate physical models and safety guarantees. As machine learning techniques enhance the modeling and control of complex dynamical systems, ensuring safety and stability remains a critical challenge, especially in safety-critical applications like autonomous vehicles, robotics, medical decision-making, and energy systems. We explore various approaches for embedding and ensuring safety constraints, including structural priors, Lyapunov and Control Barrier Functions, predictive control, projections, and robust optimization techniques. Additionally, we delve into methods for uncertainty quantification and safety verification, including reachability analysis and neural network verification tools, which help validate that control policies remain within safe operating bounds even in uncertain environments. The paper includes illustrative examples demonstrating the implementation aspects of safe learning frameworks that combine the strengths of data-driven approaches with the rigor of physical principles, offering a path toward the safe control of complex dynamical systems.

Drgona, Jan↗
DOE OSTI2026

Online LIBS–ML Framework for Dynamic Characterization of Heterogeneous Waste-Derived Gasification Feedstocks

LIBS−ML framework for real time feedstock characterization during continuous conveyor transport Heterogeneous waste derived feedstocks (e.g., waste coal, biomass and blends) introduce rapid variability in heating value and ash chemistry that affect gasifier operation, yet conventional laboratory characterization techniques are too slow to support proactive control. To address this gap, this study reports on an online, in situ, dynamic characterization framework that couple’s laser-induced breakdown spectroscopy (LIBS) with leakage safe machine learning (ML) regression to deliver real time, decision quality predictions of gasifier relevant properties. A controlled sample matrix spanning two different waste coals, two different biomasses, and engineered blends under two particle size conditions were constructed and benchmarked using standardized laboratory analyses for proximate/ultimate properties and ash composition. LIBS spectra were acquired dynamically as material flowed on a conveyor belt, using high energy 1064 nm laser ablation and shot averaging to improve repeatability and precision. Supervised regression models (multi layer perceptron (MLP) /artificial neural network (ANN), random forest (RF), and support vector regression (SVR)) and an optimized weighted ensemble were trained on emission line feature sets using nested cross validation with Bayesian hyperparameter tuning and validated against an independent hold out set. The proposed LIBS−ML workflow achieves near laboratory predictive fidelity across parametric targets (including higher heating value (HHV), ash content, fixed carbon, sulfur, major ash forming oxides, and initial deformation temperature (IDT)), with the weighted ensemble providing a robust default predictor under dynamic measurement conditions. These results demonstrate a practical pathway for real time feedstock characterization that can enable feedforward adjustments and more resilient gasifier operation for variable quality waste derived fuels.

Biomass↗
DOE OSTI2024

Infrared-safe energy weighting does not guarantee small nonperturbative effects

Infrared and collinear (IRC) safety has long been used a proxy for robustness when developing new jet substructure observables. This guiding philosophy has been carried into the deep learning era, where IRC-safe neural networks have been used for many jet studies. For graph-based neural networks, the most straightforward way to achieve IRC safety is to weight particle inputs by their energies. However, energy-weighting by itself does not guarantee that perturbative calculations of machine-learned observables will enjoy small nonperturbative corrections. Here, in this paper, we demonstrate the sensitivity of IRC-safe networks to nonperturbative effects, by training an energy flow network (EFN) to maximize its sensitivity to hadronization. We then show how to construct Lipschitz energy flow networks (L-EFNs), which are both IRC safe and relatively insensitive to nonperturbative corrections. We demonstrate the performance of L-EFNs on generated samples of quark and gluon jets, and showcase fascinating differences between the learned latent representations of EFNs and L-EFNs.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2025

Safe and Robust Binary Classification and Fault Detection Using Reinforcement Learning

In this paper, we propose a learning-based method utilizing the Soft Actor-Critic (SAC) algorithm to train a binary Support Vector Machine (SVM) classifier. This classifier is designed to identify valid input spaces in high-dimensional, highly constrained systems while minimizing the total runtime of offline simulations. The simulations adapt their runtime based on the likelihood that a given training input will be informative to the classifier. Furthermore, we introduce a method for using the trained SAC model to predict whether a desired system input is likely to violate constraints, along with a technique to adjust the input as necessary. Additionally, we explore the potential of this model to detect faults or adversarial attacks within the system. The effectiveness of our approach is demonstrated through various simulations of challenging classification problems and a constrained quadrotor model.

Netter, Josh [Georgia Institute of Technology, Atl↗
DOE OSTI2026

Control Room of the Future Testbed Workshop – After-Action Report

The U.S. Department of Energy’s Office of Electricity is supporting a one-year, multi-laboratory effort to define the needs and requirements for a Control Room of the Future testbed, or CROFT. The effort responds to increasing grid complexity driven by large new loads, dynamic generation resources, and the growing adoption of advanced technologies and tools, including artificial intelligence (AI) and machine learning (ML). To support safe, secure, and effective grid modernization, CROFT will focus on how emerging technologies and tools can be rigorously evaluated in realistic operational settings, with attention to human-machine interaction, cognitive load, and workforce readiness. The project team includes Argonne National Laboratory, Idaho National Laboratory, National Laboratory of the Rockies, and Pacific Northwest National Laboratory. As part of the scoping effort, the team conducted two industry-focused workshops: one at DTECH on February 5, 2026, informed by prior industry interviews, and a second on May 4, 2026, adjacent to IEEE T&D. These engagements brought together utilities, vendors, consultants, national laboratories, academia, and government stakeholders to identify and prioritize use cases, barriers, validation needs, data-sharing constraints, and near- and longer-term requirements. This feedback will directly inform CROFT’s architecture and research focus areas, ensuring the testbed is grounded in real-world operational needs and designed to evaluate emerging technologies and tools in realistic control-room environments.

artificial intelligence↗
DOE OSTI2026

Moving from Information Assurance to Functional Assurance with Engineered Controls

Cyber threats to operational technology demand more than traditional IT defenses—they require full-spectrum mission assurance. Cyber-Informed Engineering (CIE) is an approach that embeds engineered controls into system design to ensure critical functions remain safe and reliable, even under attack. Unlike conventional cybersecurity tools, engineered controls act directly on physical processes to prevent unacceptable outcomes such as equipment damage or mission failure. This session will outline the CIE framework and share examples of consequence-based design that deliver true resilience, not just fail-safe behaviors. Attendees will learn how to integrate these principles into the engineering lifecycle to support resilient-by-design architectures and inform emerging standards. This talk sets the stage for the panel discussion on advancing CIE across sectors as digital and physical systems converge.

24 - POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2024

Is infrared-collinear safe information all you need for jet classification?

Machine learning-based jet classifiers are able to achieve impressive tagging performance in a variety of applications in high-energy and nuclear physics. However, it remains unclear in many cases which aspects of jets give rise to this discriminating power, and whether jet observables that are tractable in perturbative QCD such as those obeying infrared-collinear (IRC) safety serve as sufficient inputs. In this article, we introduce a new classifier, Jet Flow Networks (JFNs), in an effort to address the question of whether IRC unsafe information provides additional discriminating power in jet classification. JFNs are permutation-invariant neural networks (deep sets) that take as input the kinematic information of reconstructed subjets. The subjet radius and a cut on the subjet’s transverse momenta serve as tunable hyperparameters enabling a controllable sensitivity to soft emissions and nonperturbative effects. We demonstrate the performance of JFNs for quark vs. gluon and Z vs. QCD jet tagging. For small subjet radii and transverse momentum cuts, the performance of JFNs is equivalent to the IRC-unsafe Particle Flow Networks (PFNs), demonstrating that infrared-collinear unsafe information is not necessary to achieve strong discrimination for both cases. As the subjet radius is increased, the performance of the JFNs remains essentially unchanged until physical thresholds that we identify are crossed. For relatively large subjet radii, we show that the JFNs may offer an increased model independence with a modest tradeoff in performance compared to classifiers that use the full particle information of the jet. These results shed new light on how machines learn patterns in high-energy physics data.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Concrete Thermal Energy Storage Enabling Flexible Operation without Coal Plant Cycling

The work described in this report is responsive to the Office of Fossil Energy program “Energy Storage for Fossil Power Generation.” The pilot plant built as a result of this project demonstrated the feasibility and performance of a concrete thermal energy storage (CTES) system integrated with a supercritical coal power plant. The 10 MWh electrical (>25 MWh thermal) CTES unit, developed by Storworks Power, was designed to enable flexible operation of coal plants without cycling damage. The project's key technical achievements showcase a significant advancement in energy storage technology. A modular CTES system using 42 “Bolderblocs” units was successfully designed and constructed at Alabama Power’s Plant Gaston Unit 5, with each block containing embedded stainless-steel coils in specialized, cost-effective high-temperature concrete. The system interfaced seamlessly with the plant's 3500 psig (241 barg), 1000°F (538°C) supercritical steam, demonstrating operational flexibility. Over 86 full cycles, the CTES exhibited rapid charging and discharging capabilities, effectively mimicking steam turbine feed conditions and handling varying load profiles and storage durations. Performance validation confirmed the system's ability to consistently meet design target steam conditions of 75 bar-a and ~400°C for nominal baseline discharge. The concrete material withstood repeated thermal cycling without degradation, validating earlier lab-scale tests. Integration of balance of plant components, including a condensate management system with storage tank and air-cooled condenser, minimized plant interfaces and water consumption. A robust control scheme ensured safe, automated operation across various scenarios. Key learnings from the project were invaluable: 1. Initial concrete drying and commissioning procedures were refined for future deployments, enhancing efficiency in subsequent installations. 2. System flexibility exceeded expectations, with rapid response to changing conditions. 3. Design improvements were identified including optimized insulation and piping that will enhance overall system efficiency in future deployments 4. Full cycle thermal roundtrip efficiencies exceeded 88%. While the roundtrip electrical efficiency was somewhat limited by known challenges using input steam, such constraints may be mitigated by swapping steam for hot air as thermal input. 5. A summary of key performance parameters for the pilot test and predicted performance of a full scale commercial system with specified improvements determined from the pilot are shown in Section 8. The project faced challenges, including COVID-19 delays and host plant availability constraints. However, these were overcome through adaptive planning and execution. The successful management of these obstacles demonstrated the resilience and adaptability of the project team and the robustness of the CTES technology. This successful pilot demonstrates the potential for CTES to enhance coal plant flexibility, supporting grid stability as renewable penetration increases. The validated design and operational data provide a solid foundation for scaling up to utility-scale implementations, potentially transforming how thermal plants operate in evolving energy landscapes. The system's ability to rapidly respond to changing grid conditions while maintaining high efficiency makes it a promising solution for balancing intermittent renewable energy sources. Furthermore, the project highlighted the potential for even greater efficiencies in future iterations. The use of air as an input medium could potentially eliminate the limitations observed with steam input, opening new possibilities for energy storage applications beyond coal plant integration. In conclusion, this pilot project not only achieved its primary goals but also uncovered additional benefits and potential applications of the CTES technology. It represents a significant step forward in addressing the challenges of grid stability and flexibility in an increasingly renewable-driven energy landscape.

01 COAL, LIGNITE, AND PEAT↗
DOE OSTI2025

Encrypted Control Using Modified Learning With Errors-based Schemes

Cyber-physical systems (CPSs) require reliable, safe, and secure control of critical infrastructure, combining computational and networking capabilities, which heighten the risk of cyber attacks. These attacks can disrupt the physical process, causing unforeseen consequences. One solution is the use of fully homomorphic encryption (FHE) to protect the control loop, allowing for secure computations and communications without compromising signal and control system privacy. The challenge with FHE, however, is its requirement for inputs to be integers. This paper introduces a modified Learning With Errors (LWE) FHE approach that encodes control system dynamics and signals into integers. Our proposed scheme leverages a generalized LWE encoding function and modifies the Gentry-Sahai-Waters (GSW) gadget decomposition tool to encrypt the control system. Using the modified LWE scheme, we formalize a fully encrypted control system, supported by simulated results.

42 - ENGINEERING↗
DOE OSTI2025

Aided Active Learning (AAL) for Enhanced Critical Heat Flux Prediction

Accurate prediction of critical heat flux (CHF) is crucial for the safe and efficient operation of nuclear reactors. Traditional CHF modeling methods often require extensive experimental data, which are hard to obtain. This study introduces the Aided Active Learning (AAL) framework, which strategically minimizes data requirements without sacrificing model accuracy. Unlike conventional Active Learning (AL), AAL introduces an additional step of randomly selecting a subset from the sample pool before applying the query strategy. To evaluate the performance of AAL, two query strategies—uncertainty-based sampling and error-reduction sampling—were evaluated across the following models: random forest (RF), feedforward neural network (FNN), and variational feedforward neural network (vFNN). The proposed framework demonstrated that AAL effectively reduces the number of training samples needed to achieve comparable predictive accuracy. For the RF model, AL required only 710 samples to achieve an R2 score of 0.98, as compared to the 4,785 samples needed by random sampling. Similarly, the FNN model achieved the same R2 score with just 355 samples when using AL, a significant improvement over the 825 samples required by random sampling. In case of uncertainty-based sampling strategy, vFNN attained an R2 of 0.98 with 3,420 samples, reducing the sample requirement by 47% relative to the 6,440 samples needed for random sampling. Its performance suggests that larger training data are required to fully leverage its uncertainty quantification capabilities.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Operator learning for energy-efficient building ventilation control with computational fluid dynamics simulation of a real-world classroom

Energy-efficient ventilation control plays an important role in reducing building energy consumption while ensuring occupant health and comfort. While Computational Fluid Dynamics (CFD) simulations provide detailed and physically accurate representations of indoor airflow, their high computational cost limits their use in real-time building control. In this work, we present a neural operator learning framework that combines the physical accuracy of CFD with the computational efficiency of machine learning to enable building ventilation control with the high-fidelity fluid dynamics models. Our method jointly optimizes the airflow supply rates and vent angles to reduce energy use and adhere to air quality constraints. We train an ensemble of neural operator transformer models to learn the mapping from building control actions to airflow fields using high-resolution CFD data. This learned neural operator is then embedded in an optimization-based control framework for building ventilation control. Experimental results show that our approach achieves significant energy savings compared to maximum airflow rate control, rule-based control, as well as data-driven control methods using spatially averaged CO 2 prediction and deep learning–based reduced-order models, while consistently maintaining safe indoor air quality. These results highlight the practicality and scalability of our method in maintaining energy efficiency and indoor air quality in real-world buildings.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2024

Impurity gas detection for SNF canisters using probabilistic deep learning and acoustic sensing *

Abstract Monitoring impurity gases in spent nuclear fuel (SNF) canisters is a novel structural health monitoring approach for SNF in dry storage. The SNF canisters are sealed containers that do not facilitate visual access to the inside. Acoustic sensing can be deployed by taking advantage of the pathways unobstructed by internal hardware. Although the ultrasonic time-of-flight measurement can provide valuable information, it is limited in its ability to discern the concentration of only one impurity gas. As such, deep learning algorithms, particularly convolutional neural networks (CNNs), offer a promising solution. In this study, CNN-based probabilistic deep learning models were implemented to detect and quantify multiple impurity gases in helium. An experimental platform was established to simulate canister conditions, and ultrasonic test data were collected. The presence of argon and air in helium at concentrations ranging from 0% to 1.2% at increments of 0.05% was considered. The multi-layer perceptron, decision tree, and logistic regression classifiers achieved high accuracies when distinguishing pure helium from helium with impurities. CNN with dropout layers and CNN using maximum likelihood estimation showed a similar performance, indicating their ability to capture uncertainties. The ensemble CNN model exhibited improved predictions and the ability to balance individual gas concentration by integrating 1D- and 2D-CNN models. These findings contribute probabilistic deep learning solutions for impurity gas detection and analysis within SNF canisters, thus ensuring safe storage and management of SNFs.

47 OTHER INSTRUMENTATION↗