Search NASA⌕ Search

SEARCH · Search NASA

Results for “learning systems”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

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

At least 307 records · Page 17
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Quadrature Based Neural Network Learning of Stochastic Hamiltonian Systems

Hamiltonian Neural Networks (HNNs) provide structure-preserving learning of Hamiltonian systems. In this paper, we extend HNNs to structure-preserving inversion of stochastic Hamiltonian systems (SHSs) from observational data. We propose the quadrature-based models according to the integral form of the SHSs’ solutions, where we denoise the loss-by-moment calculations of the solutions. The integral pattern of the models transforms the source of the essential learning error from the discrepancy between the modified Hamiltonian and the true Hamiltonian in the classical HNN models into that between the integrals and their quadrature approximations. This transforms the challenging task of deriving the relation between the modified and the true Hamiltonians from the (stochastic) Hamilton–Jacobi PDEs, into the one that only requires invoking results from the numerical quadrature theory. Meanwhile, denoising via moments calculations gives a simpler data fitting method than, e.g., via probability density fitting, which may imply better generalization ability in certain circumstances. Numerical experiments validate the proposed learning strategy on several concrete Hamiltonian systems. The experimental results show that both the learned Hamiltonian function and the predicted solution of our quadrature-based model are more accurate than that of the corrected symplectic HNN method on a harmonic oscillator, and the three-point Gaussian quadrature-based model produces higher accuracy in long-time prediction than the Kramers–Moyal method and the numerics-informed likelihood method on the stochastic Kubo oscillator as well as other two stochastic systems with non-polynomial Hamiltonian functions. Moreover, the Hamiltonian learning error εH arising from the Gaussian quadrature-based model is lower than that from Simpson’s quadrature-based model. These demonstrate the superiority of our approach in learning accuracy and long-time prediction ability compared to certain existing methods and exhibit its potential to improve learning accuracy via applying precise quadrature formulae.

Mathematics↗
DOE OSTI2026

Explaining System-Level Prognostics with Established Machine Learning Methods

System-level prognostics is crucial for ensuring reliability and enabling predictive maintenance in complex systems with interconnected components. This study presents a framework that integrates data-driven methods to predict the remaining useful life (RUL) of a subsystem under multiple and concurrent faults within a nuclear power plant system with explainable artificial intelligence (XAI). A nuclear power plant (NPP) operation was simulated to model the degradation behavior of NPP components, and four machine learning models—Gradient Boosting Regressor (GBR), Support Vector Regressor (SVR), Fully Connected Neural Network (FCNN), and Long Short-Term Memory (LSTM)—were evaluated for prognostics with a novel system RUL parameter. The LSTM model demonstrated potential superior repeatability, while SHAP (SHapley Additive exPlanations) for explainability provided consistent and trustworthy global explanations. In contrast, LIME (Local Interpretable Model-agnostic Explanations) offered localized interpretability but showed reduced stability for sequential data. Key findings include the interplay between component-level degradation and system-wide performance, with LSTM effectively capturing these dynamics through sequence-level predictions. The XAI techniques enhanced transparency by identifying critical features influencing model predictions and aligning with domain knowledge. Furthermore, this framework has significant implications for improving trust and understanding in predictive maintenance, particularly in safety-critical industries like nuclear energy.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
NASA NTRS2010

Heritage and Advanced Technology Systems Engineering Lessons Learned from NASA Deep Space Missions

In the design and development of complex spacecraft missions, project teams frequently assume the use of advanced technology systems or heritage systems to enable a mission or reduce the overall mission risk and cost. As projects proceed through the development life cycle, increasingly detailed knowledge of the advanced and heritage systems within the spacecraft and mission environment identifies unanticipated technical issues. Resolving these issues often results in cost overruns and schedule impacts. The National Aeronautics and Space Administration (NASA) Discovery & New Frontiers (D&NF) Program Office at Marshall Space Flight Center (MSFC) recently studied cost overruns and schedule delays for 5 missions. The goal was to identify the underlying causes for the overruns and delays, and to develop practical mitigations to assist the D&NF projects in identifying potential risks and controlling the associated impacts to proposed mission costs and schedules. The study found that optimistic hardware/software inheritance and technology readiness assumptions caused cost and schedule growth for four of the five missions studied. The cost and schedule growth was not found to result from technical hurdles requiring significant technology development. The projects institutional inheritance and technology readiness processes appear to adequately assess technology viability and prevent technical issues from impacting the final mission success. However, the processes do not appear to identify critical issues early enough in the design cycle to ensure project schedules and estimated costs address the inherent risks. In general, the overruns were traceable to: an inadequate understanding of the heritage system s behavior within the proposed spacecraft design and mission environment; an insufficient level of development experience with the heritage system; or an inadequate scoping of the system-wide impacts necessary to implement an advanced technology for space flight applications. The paper summarizes the study's lessons learned in more detail and offers suggestions for improving the project's ability to identify and manage the technology and heritage risks inherent in the design solution.

Barley, Bryan↗
DOE OSTI2022

Deep Reinforcement Learning for Distribution System Restoration Using Distributed Energy Resources and Tie-Switches

Distributed energy resources (DERs), such as solar PVs and energy storage, can be used to restore distribution system critical loads after the extreme weather events to increase grid resilience. However, coordinating multiple DERs together with tie-switches for multi-step restoration process under renewable uncertainty is challenging. This paper proposes a deep reinforcement learning to control discrete actions of switching on/off tie switches and DERs for critical load restoration. The restoration problem is first cast into the Markov decision process suitable for DRL. Then, the original soft actor critic (SAC) method for continuous actions has been extended to handle discrete and continuous actions. Numerical comparison results with other stochastic optimization-based approaches on the modified IEEE 33-bus system show that the proposed method can achieve fast critical load restoration in the presence of substation power outage while maintaining system voltage limit throughout the restoration process.

active distribution systems↗
NASA NTRS1994

A fuzzy classifier system for process control

A fuzzy classifier system that discovers rules for controlling a mathematical model of a pH titration system was developed by researchers at the U.S. Bureau of Mines (USBM). Fuzzy classifier systems successfully combine the strengths of learning classifier systems and fuzzy logic controllers. Learning classifier systems resemble familiar production rule-based systems, but they represent their IF-THEN rules by strings of characters rather than in the traditional linguistic terms. Fuzzy logic is a tool that allows for the incorporation of abstract concepts into rule based-systems, thereby allowing the rules to resemble the familiar 'rules-of-thumb' commonly used by humans when solving difficult process control and reasoning problems. Like learning classifier systems, fuzzy classifier systems employ a genetic algorithm to explore and sample new rules for manipulating the problem environment. Like fuzzy logic controllers, fuzzy classifier systems encapsulate knowledge in the form of production rules. The results presented in this paper demonstrate the ability of fuzzy classifier systems to generate a fuzzy logic-based process control system.

Karr, C. L.↗
DOE OSTI2025

Deep Reinforcement Learning for Distribution System Operations: A Tutorial and Survey

Here, the rapid evolution of modern electric power distribution systems into complex networks of interconnected active devices, distributed generation (DG), and storage poses increasing difficulties for system operators. The large-scale integration of distributed energy resources (DERs) and the rapid exchange of measurement data via communication networks present major opportunities for advancing grid operations but also introduce greater uncertainty, higher data dimensionality, more complex network and device models, and challenging control and optimization problems. Deep reinforcement learning (DRL) algorithms are promising in addressing these challenges. However, they have not been effectively adapted for power systems applications, requiring extensive customization for implementation and evaluation. This has resulted in reproducibility challenges and a steep learning curve for researchers new to applying DRL algorithms to the power systems domain. To bridge these gaps, this tutorial aims to serve as a valuable resource for researchers interested in exploring learning-based algorithms to operate active power distribution networks. Specifically, this work presents a generalized process for translating sequential decision-making problems in power distribution systems into Markov decision process (MDP) formulations, illustrated through concrete grid service examples. Additionally, we introduce a simple environment design strategy to develop and evaluate example DRL algorithms for distribution system applications, complete with an included code repository to guide users through environment construction.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems [SWR-22-07]

NREL's PowerGridworld provides a modular simulation environment for training heterogenous, grid-aware, multi-agent reinforcement learning (RL) policies at scale. The package enables the user to create component gym environments that can be composed into more complex agents. For example, a grid interactive building environment can be created by composing together component environments each encapsulating the building, PV, and battery physics. These multi-component environments can then be combined into multi-agent simulation where each agent's power consumption/injection becomes an input for solving the optimal power flow on a distribution feeder modeled in OpenDSS. Information from OpenDSS, such as bus voltages and line flows, can be included in the agents' observation spaces to enable grid-aware rewards. The default API for the PowerGridworld simulator conforms to RLLib's MultiAgent API and thus enables distributed training using HPC and cloud resources.

Biagioni, David↗
NASA NTRS1989

RSRA/X-Wing flight control system development - Lessons learned

The X-Wing, in concept, marries the efficiencies of a helicopter and fixed wing aircraft through the use of a four-bladed wing/rotor that can be rotated or stopped in flight. The RSRA/X-Wing flight test program was a technology demonstration of this concept which, after three successful flights, was discontinued in late 1987. In spite of many technical challenges in this program, such as the use of circulation control, the fabrication of a large all-composite rotor, the development of an advanced, quadruplex digital flight control system, and the need for higher harmonic control, no major technical problems had been encountered at the time of the stop-work order. This paper addresses the issues of flight control system development and focuses on lessons learned. As with other such programs, software development was the most consuming issue. Other subjects of discussion include the problems of balancing program goals with technical goals, software- and hard-ware-related problems, safety issues, and system testing.

Corliss, Lloyd D.↗
DOE OSTI2023

Deep Reinforcement Learning for Distribution System Cyber Attack Defense with DERs

The use of smart inverter capabilities of distributed energy resources (DERs) enhances the grid reliability but in the meanwhile exhibits more vulnerabilities to cyber-attacks. This paper proposes a deep reinforcement learning (DRL)-based defense approach. The defense problem is reformulated as a Markov decision making process to control DERs and minimizing load shedding to address the voltage violations caused by cyber-attacks. The original soft actor-critic (SAC) method for continuous actions has been extended to handle discrete and continuous actions for controlling DERs' setpoints and loadshedding scenarios. Numerical comparison results with other control approaches, such as Volt-VAR and Volt-Watt on the modified IEEE 33-node, show that the proposed method can achieve better voltage regulation and have less power losses in the presence of cyber-attacks.

active distribution systems↗
DOE OSTI2022

Deception-Based Cyber Attacks on Hierarchical Control Systems using Domain-Aware Koopman Learning

Industrial control systems are subject to cyber attacks that produce physical consequences. These attacks can be both hard to detect and protracted. Here, we focus on deception-based sensor bias attacks made against a hierarchical control system where the attacker attempts to be stealthy. We develop a a data-driven, optimization-based attacker model and use the Koopman operator to represent the system dynamics in a domain-aware and computationally efficient manner. Using this model, we compute several different attacks against a high-fidelity commercial building emulator and compare the impacts of those attacks to each other. Finally, we discuss some computational considerations and identify avenues for future research.

koopman operator, Cyber-Physical Security, machine↗
NASA NTRS2005

Quicker Q-Learning in Multi-Agent Systems

Multi-agent learning in Markov Decisions Problems is challenging because of the presence ot two credit assignment problems: 1) How to credit an action taken at time step t for rewards received at t' greater than t; and 2) How to credit an action taken by agent i considering the system reward is a function of the actions of all the agents. The first credit assignment problem is typically addressed with temporal difference methods such as Q-learning OK TD(lambda) The second credit assi,onment problem is typically addressed either by hand-crafting reward functions that assign proper credit to an agent, or by making certain independence assumptions about an agent's state-space and reward function. To address both credit assignment problems simultaneously, we propose the Q Updates with Immediate Counterfactual Rewards-learning (QUICR-learning) designed to improve both the convergence properties and performance of Q-learning in large multi-agent problems. Instead of assuming that an agent s value function can be made independent of other agents, this method suppresses the impact of other agents using counterfactual rewards. Results on multi-agent grid-world problems over multiple topologies show that QUICR-learning can achieve up to thirty fold improvements in performance over both conventional and local Q-learning in the largest tested systems.

Agogino, Adrian K.↗
DOE OSTI2022

Anomalous phase separation in a correlated electron system: Machine-learning–enabled large-scale kinetic Monte Carlo simulations

Significance Phase separation is crucial to the functionalities of many correlated electron materials with notable examples including colossal magnetoresistance in manganites and high- T c superconductivity in cuprates. However, the nonequilibrium phase-separation dynamics in such systems are poorly understood theoretically, partly because the required multiscale modeling is computationally very demanding. With the aid of machine-learning methods, we have achieved large-scale dynamical simulations in a representative correlated electron system. We observe an unusual relaxation process that is beyond the framework of classical phase-ordering theories. We also uncover a correlation-induced freezing behavior, which could be a generic feature of phase separation in correlated electron systems.

Zhang, Sheng↗
NASA NTRSDate not supplied

Developing Deep Learning Models for System Remaining Useful Life Predictions: Application to Aircraft Engines

Prognostics and health management (PHM) is an important part of ensuring reliable operations of complex safety- critical systems. System-level remaining useful life (RUL) estimation is a much more complex problem than making estimations at the component level, and system-level RUL methodologies remain sparse in the literature. Model-based approaches have traditionally worked in the past for components such as capacitors, MOSFETs, batteries, or hard-drives (to name a few examples), but developing high fidelity dynamics models of cyber physical systems that can be used to study the effects of multiple degrading components in the system remains a challenging task. Some initial work on model-based System RUL predictions was demonstrated in Khorasgani, et al [1], but, to generalize the system-level prognostics problem, we have to resort to pure data driven and hybrid approaches. In this work, we propose an end-to-end data- driven framework for developing deep learning models to predict remaining useful life of cyber physical systems operating under unknown faulty conditions. The raw data is organized with a data schema that improves the model development process and down stream data analysis tasks. Due to the unknown faulty conditions, the raw sensor data is transformed into signals that expose the underlying degradation processes, which are then used for model development. Bayesian Optimization is used to tune the model parameters prior to training and validation. We show that this approach results in accurate predictions within 3 cycles to end of life (EOL). We demonstrate the effectiveness of our approach by applying it to the N-CMAPSS turbofan engine dataset recently released by NASA, which includes high fidelity degradation modeling, real world operating conditions, and a large set of fault operating modes.

Prognostics↗
DOE OSTI2023

Passive Safety System Reliability Analysis: Lessons Learned and Open Items

Passive safety systems have multiple benefits, largely stemming from their high functional reliability due to their simplicity and lack of dependencies. However, accurately assessing the reliability of passive systems can be challenging due in large part to the possibility of functional failures. Argonne National Laboratory (Argonne) has been involved in several recent efforts concerning the reliability assessment of passive safety systems for advanced, non-light water reactors (non-LWRs). These efforts have focused on the development and application of mechanistic methods for the evaluation of passive system reliability, which rely on system modelling and uncertainty analyses to derive reliability values for use in probabilistic safety assessments (PSAs). Further information on these efforts is provided in ref [1]. The current paper reviews key lessons learned through these projects, along with outstanding open items regarding the reliability assessment of passive systems.

Grabaskas, David↗
DOE OSTI2026

Protection System Validation with Machine Learning Anomaly Classification

A poster for the Early Career Poster Session. Power system protection devices have transitioned over the past few decades from mechanical to analog devices, then to solid state and finally digital. Relays and their associated critical network of equipment have significantly increased in complexity. Even internally, relays have gained significant intricacy, with relatively simple overcurrent or differential functions now being assisted by a myriad of other functions. This is necessary as the grid becomes more complex, but it brings increased difficulty in monitoring and upkeep. Misoperation caused by improper relay settings or malicious actions is a constant challenge faced by all utilities. These improper settings can be difficult to identify and may require exhaustive post-mortem analysis, typically after a major outage event has already occurred. A mechanism is needed for monitoring the behavior of protection systems to validate that they act and perform as expected. This work presents a concept for a machine learning (ML) system capable of validating the performance of protection systems by classifying anomalous events and characterizing protection system responses based solely on available current and voltage measurements. As a first step in its development, an experimental dataset is generated, and a random forest model is implemented with high accuracy in distinguishing four power system scenarios.

24 - POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2021

Selecting durable building envelope systems with machine learning assisted hygrothermal simulations database

Hygrothermal simulations provide insight into the energy performance and moisture durability of building envelope components under dynamic conditions. The inputs required for hygrothermal simulations are extensive, and carrying out simulations and analyses requires expert knowledge. An expert system, the Building Science Advisor (BSA), has been developed to predict the performance and select the energy-efficient and durable building envelope systems for different climates. The BSA consists of decision rules based on expert opinions and thousands of parametric simulation results for selected wall systems. The number of potential wall systems results in millions, too many to simulate all of them. We present how machine learning can help predict durability data, such as mold growth, while minimizing the number of simulations needed to run. The simulation results are used for training and validation of machine learning tools for predicting wall durability. We tested Artificial Neural Network (ANN) and Gradient Boosted Decision Trees (GBDT) for their applicability and model accuracy. Models developed with both methods showed adequate prediction performance (root mean square error of 0.195 and 0.209, respectively). Finally, we introduce how the information supports guidance for envelope design via an easy-to-use web-based tool that does not require the end-user to run hygrothermal simulations.

Salonvaara, Mikael↗
NASA NTRS1992

Tradeoffs in the utility of learned knowledge

Planning systems which make use of domain theories can produce more accurate plans and achieve more goals as the quality of their domain knowledge improves. MTR, a multi-strategy learning system, was designed to learn from system failures and improve domain knowledge used in planning. However, augmented domain knowledge can decrease planning efficiency. We describe how improved knowledge that becomes expensive to use can be approximated to yield calculated tradeoffs in accuracy and efficiency.

Kedar, Smadar↗