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 703 records · Page 39

Learning Stochastic Parametric Differentiable Predictive Control Policies

We present a scalable unsupervised learning-based method for obtaining explicit control policies for model predictive control problems for stochastic linear systems with additive uncertainties subject to nonlinear chance constraints. We call the proposed method stochastic parametric differentiable predictive control (SP-DPC), which extends the recently proposed deterministic DPC policy optimization algorithm. We formulate the SP-DPC as a deterministic approximation to the stochastic parametric constrained optimal control problem via independent sampling of the problem's parameters and uncertainties. This formulation allows us to directly compute the policy gradients via automatic differentiation of the problem's value function, evaluated over sampled parameters and uncertainties. In particular, the computed expectation of the problem's value function is backpropagated through the finite-time closed-loop system rollouts parametrized by a known nominal system dynamics model and neural control policy. We also provide theoretical probabilistic guarantees on closed-loop stability and chance constraints satisfaction for systems controlled by learned neural policies. We demonstrate the computational efficiency and scalability of the proposed policy optimization algorithm in three numerical examples, including systems with a large number of states or subject to nonlinear constraints.

Drgona, Jan↗

A reinforcement learning approach to long-horizon operations, health, and maintenance supervisory control of advanced energy systems

In this work, we develop a Reinforcement Learning (RL) approach to the supervisory control problem for advanced energy systems, such as novel nuclear reactors and other demand-driven, mission-critical, and component-health-sensitive energy plants. The inclusive problem landscape considered captures the stochastic confluence of plant performance, component health evolution, power demand from the grid, diverse maintenance actions, and operator-defined goals and constraints, all considered over meaningfully long-enough reasoning horizons. Key aspects of the proposed approach are a receding horizon control-inspired technique dictating time- or event-triggered supervisory policy (re-)constructions, as well as additional capability-enabling contributions such as timescale compression, to handle long reasoning horizons and uncertainty in parts of the problem, and practical yet demonstrably-effective handling of hybrid action spaces with continuous and discrete decision variables. The resulting algorithm consists of a simulation-based RL agent constructing stochastic supervisory control policies over nontrivial action spaces and for long horizons, applying the learned policy to the system for a much shorter interval, and perpetually repeating, to construct the next long-horizon policy. That next policy will only be applied, again, for a short interval, yet originally far-in-time events move progressively closer, their associated uncertainty decreases, and new events and aspects enter the reasoning horizon. The proposed methodology bridges fundamental receding horizon concepts with the unequivocally stronger and more scalable reasoning of contemporary RL. Numerical examples using Soft Actor–Critic Deep RL illustrate the operation and efficacy of the proposed technique for a power plant tasked with health-aware load following missions in a dynamic electricity market landscape.

97 MATHEMATICS AND COMPUTING↗

NWPEsSe: an Adaptive-Learning Global Optimization Algorithm for Nanosized Cluster Systems

Global optimization constitutes an important and fundamental problem in theoretical studies in many chemical fields, such as catalysis, materials or separations problems. In this paper, a novel algorithm has been developed for the global optimization of large systems including neat and ligated clusters in gas phase, and supported clusters in periodic boundary conditions. The method is based on an updated artificial bee colony (ABC) algorithm method, that allows for adaptive-learning during the search process. The new algorithm is tested against four classes of systems of diverse chemical nature: gas phase Au_55, ligated Au_8^(2+), Au_8 supported on graphene oxide and defected rutile, and a large cluster assembly ?[Co?_6 Te_8 (PEt_3 )_6][C_60 ]_n, with sizes ranging between 1 to 3 nm and containing up to 1300 atoms. Reliable global minima (GMs) are obtained for all cases, either confirming published data or reporting new lower energy structures. The algorithm and interface to other codes in the form of an independent program, Northwest Potential Energy Search Engine (NWPEsSe), is freely available and it provides a powerful and efficient approach for global optimization of nanosized cluster systems. The work described in this publication was performed at Pacific Northwest National Laboratory (PNNL), which is operated by Battelle for the United States Department of Energy (DOE) under Contract DE-AC05-76RL0180. J. Z. and V.-A. G. acknowledge support from DOE, Office of Science, Office of Basic Energy Sci-ences, Chemical, Geological and Biological Sciences Division and computing resources from PNNL’s Research Computing Facility and the National Energy Research Scientific Computing Center.

Zhang, Jun↗

Artificial Intelligence Application to D and D - 20492

As aging facilities across the DOE complex await decommissioning, there is an ongoing need to understand any changes in the structural conditions. Many of these facilities were built over 50 years ago and, in some cases, these facilities have gone beyond the expected operational lifetime. Many facilities have been placed in a state of 'cold and dark,' sitting unused and awaiting decommissioning. Especially challenging are the aging facilities that provide unique operational/production capabilities to support critical DOE missions and cannot be shut down. In any of these scenarios, the structural integrity of these facilities may become compromised as time passes. It is critical that adequate inspections be performed on a continual basis and that the data collected undergoes sufficient analysis to support timely identification of any new or worsening structural issues as well as prompt needed maintenance and repairs to maintain the facilities in a safe condition. In recent days, Artificial Intelligence (AI) [1] and its application to various domains are growing at fast speed. FIU is performing research in this area and exploring the associated technologies to solve nuclear decommissioning problems. Artificial intelligence refers to the capability of a program to autonomously act, react and adapt to the working environment. AI enables the machine to behave like humans and perform the cognitive functions such as 'learning' and 'problem solving'. AI systems gradually moving from traditional approaches (algorithms and expert systems) towards more efficient and advanced technologies (machine learning [1] and deep learning [2] [3]). AI is the study of algorithms and statistical models that is being used by computers to perform specific tasks without using explicit instructions. FIU is working to develop a pilot-scale infrastructure to implement structural health monitoring using AI technologies with focus on machine learning, deep learning. This research is focused on Computer Vision/Image Classification area of AI applications. This can also be expanded to other areas of AI related to Object Recognition and Character Recognition in images. In addition to utilizing existing data sets, FIU will collect and investigate image and video data using FIU test-bed mockups to monitor structural health of the facility. Resulting data will be processed and analyzed using machine learning/deep learning technologies. The proposed pilot system is intended to serve as a starting point to engage the DOE field sites on related data sets and their decision making needs. It is anticipated that proposed machine learning/deep learning technologies can be effectively employed using anomaly detection to solve EM challenges in surveillance and maintenance of the D and D facilities. FIU will work with research stakeholders to identify applications at various sites and other DOE facilities. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Physics-Informed Neural Networks for PDE-Constrained Optimization and Control

The goal of optimal control is to determine a sequence of inputs for maximizing or minimizing a given performance criterion subject to the dynamics and constraints of the system under observation. This work introduces Control Physics-Informed Neural Networks (PINNs), which simultaneously learn both the system states and the optimal control signal in a single-stage framework that leverages the system’s underlying physical laws. While prior approaches often follow a two-stage process-modeling, the system first and then devising its control—the presented novel framework embeds the necessary optimality conditions directly into the network architecture and loss function. We demonstrate the effectiveness of the novel methodology by solving various open-loop optimal control problems governed by analytical, one-dimensional, and two-dimensional partial differential equations (PDEs).

97 MATHEMATICS AND COMPUTING↗

MLCommons Science Benchmarks

Benchmarks are a cornerstone of modern machine learning practice, providing standardized eval- uations that enable reproducibility, comparison, and scientific progress. Yet, as AI systems particularly deep learning models become increasingly dynamic, traditional static benchmarking approaches are losing their relevance. Models rapidly evolve in architecture, scale, and capability; datasets shift; and deployment contexts continuously change, creating a moving target for evaluation. Without adaptive benchmarking frame- works, both scientific assessment and real-world de- ployment risk becoming misaligned with actual system behavior. Drawing on our experience from MLCommons, educa- tional initiatives, and government programs such as the DOE s Million Parameter Consortium, we identify key barriers that hinder the broader adoption and utility of benchmarking in AI. These include substantial resource demands, limited access to specialized hardware, lack of expertise in benchmark design, and uncertainty among practitioners about how to relate benchmark results to their own application domains. Moreover, current benchmarks often emphasize peak performance on leadership-class hardware, offering limited guidance for more diverse, real-world deployment scenarios. We argue that benchmarking itself must become dy- namic in order to incorporate evolving models, updated data, and heterogeneous computational platforms while maintaining transparency, reproducibility, and inter- pretability. Democratizing this process requires not only technical innovation, but also systematic educational efforts spanning undergraduate to professional levels to develop sustained expertise in benchmark design and use. Finally, benchmarks should be framed and com- municated to support application-relevant comparisons, enabling both developers and users to make informed, context-sensitive decisions. Advancing dynamic and inclusive benchmarking practices will be essential to ensure that evaluation keeps pace with the evolving AI landscape and supports responsible, reproducible, and accessible AI deployment.

Hawks, Benjamin G. [Fermilab]↗

Failure Analysis of a Complex Learning Framework Incorporating Multi-Modal and Semi-Supervised Learning

Machine learning is used in many applications, from machine vision to speech recognition to decision support systems, and is used to test applications. However, though much has been done to evaluate the performance of machine learning algorithms, little has been done to verify the algorithms or examine their failure modes. Moreover, complex learning frameworks often require stepping beyond black box evaluation to distinguish between errors based on natural limits on learning and errors that arise from mistakes in implementation. We present a conceptual architecture, failure model and taxonomy, and failure modes and effects analysis (FMEA) of a semi-supervised, multi-modal learning system, and provide specific examples from its use in a radiological analysis assistant system. The goal of the research described in this paper is to provide a foundation from which dependability analysis of systems using semi-supervised, multi-modal learning can be conducted. The methods presented provide a first step towards that overall goal.

99 GENERAL AND MISCELLANEOUS↗

Data-driven Feature Analysis in Control Design for Series-Compensated Transmission Systems

One challenge in power-system control designs is the gap between numerical model-based analysis and complex real-world power systems. With increased data and measurements being collected from power systems, data-driven analysis (e.g., machine learning) may provide an alternative approach to reveal hidden information through learning from the real system data, and provide insights for better control scheme design during the utility planning process. Data-driven feature analysis was performed to evaluate the relationships between series compensation, power generation, and path flows in a real transmission system, as well as temporal patterns. The main data-driven analysis methods, including statistical cross-correlation, multinomial logistical regression, and classification and regression trees, were integrated for feature selection and developing predictive models of series compensation. Analysis results demonstrated the effectiveness of the proposed methodology in feature analysis and the potential to help improve power-system control scheme design.

42 ENGINEERING↗

Multi-Area Distribution System State Estimation Using Decentralized Physics-Aware Neural Networks

The development of active distribution grids requires more accurate and lower computational cost state estimation. In this paper, the authors investigate a decentralized learning-based distribution system state estimation (DSSE) approach for large distribution grids. The proposed approach decomposes the feeder-level DSSE into subarea-level estimation problems that can be solved independently. The proposed method is decentralized pruned physics-aware neural network (D-P2N2). The physical grid topology is used to parsimoniously design the connections between different hidden layers of the D-P2N2. Monte Carlo simulations based on one-year of load consumption data collected from smart meters for a three-phase distribution system power flow are developed to generate the measurement and voltage state data. The IEEE 123-node system is selected as the test network to benchmark the proposed algorithm against the classic weighted least squares and state-of-the-art learning-based DSSE approaches. Numerical results show that the D-P2N2 outperforms the state-of-the-art methods in terms of estimation accuracy and computational efficiency.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Probabilistic Analysis of Passive Safety System Reliability in Advanced Small Modular Reactors: Methodologies and Lessons Learned

Many advanced small modular reactor designs rely on passive systems to fulfill safety functions during accident sequences. These systems depend heavily on boundary conditions to induce a motive force, meaning the system can fail to operate as intended due to deviations in boundary conditions, rather than as the result of physical failures. Furthermore, passive systems may operate in intermediate or degraded modes. These factors make passive system operation difficult to characterize with a traditional probabilistic framework that only recognizes discrete operating modes and does not allow for the explicit consideration of time-dependent boundary conditions. Argonne National Laboratory has been examining various methodologies for assessing passive system reliability within a probabilistic risk assessment for a station blackout event at an advanced small modular reactor. This paper describes the most promising options: mechanistic techniques, which share qualities with conventional probabilistic methods, and simulation-based techniques, which explicitly account for time-dependent processes. The primary intention of this paper is to describe the strengths and weaknesses of each methodology and highlight the lessons learned while applying the two techniques while providing high-level results. This includes the global benefits and deficiencies of the methods and practical problems encountered during the implementation of each technique.

Grabaskas, David↗

Predicting peak day and peak hour of electricity demand with ensemble machine learning

Battery energy storage systems can be used for peak demand reduction in power systems, leading to significant economic benefits. Two practical challenges are 1) accurately determining the peak load days and hours and 2) quantifying and reducing uncertainties associated with the forecast in probabilistic risk measures for dispatch decision-making. In this study, we develop a supervised machine learning approach to generate 1) the probability of the next operation day containing the peak hour of the month and 2) the probability of an hour to be the peak hour of the day. Guidance is provided on preparation and augmentation of data as well as selection of machine learning models and decision-making thresholds. The proposed approach is applied to the Duke Energy Progress system and successfully captures 69 peak days out of 72 testing months with a 3% exceedance probability threshold. On 90% of the peak days, the actual peak hour is among the 2 h with the highest probabilities.

25 ENERGY STORAGE↗

Harnessing Machine Learning to Predict MoS 2 Solid Lubricant Performance

Physical vapor deposited (PVD) molybdenum disulfide (MoS 2 ) solid lubricant coatings are an exemplar material system for machine learning methods due to small changes in process variables often causing large variations in microstructure and mechanical/tribological properties. Here, in this work, a gradient boosted regression tree machine learning method is applied to an existing experimental data set containing process, microstructure, and property information to create deeper insights into the process-structure–property relationships for molybdenum disulfide (MoS 2 ) solid lubricant coatings. The optimized and cross-validated models show good predictive capabilities for density, reduced modulus, hardness, wear rate, and initial coefficients of friction. The contribution of individual deposition variables (i.e., argon pressure, deposition power, target conditioning) on coating properties is highlighted through feature importance. The process-property relationships established herein show linear and non-linear relationships and highlight the influence of uncontrolled deposition variables (i.e., target conditioning) on the tribological performance.

MoS2↗

Stiff neural ordinary differential equations

Neural Ordinary Differential Equations (ODEs) are a promising approach to learn dynamical models from time-series data in science and engineering applications. This work aims at learning neural ODEs for stiff systems, which are usually raised from chemical kinetic modeling in chemical and biological systems. We first show the challenges of learning neural ODEs in the classical stiff ODE systems of Robertson’s problem and propose techniques to mitigate the challenges associated with scale separations in stiff systems. We then present successful demonstrations in stiff systems of Robertson’s problem and an air pollution problem. The demonstrations show that the usage of deep networks with rectified activations, proper scaling of the network outputs as well as loss functions, and stabilized gradient calculations are the key techniques enabling the learning of stiff neural ODEs. The success of learning stiff neural ODEs opens up possibilities of using neural ODEs in applications with widely varying time-scales, such as chemical dynamics in energy conversion, environmental engineering, and life sciences.

97 MATHEMATICS AND COMPUTING↗

Distributed Quantum Learning with co-Management in a Multi-tenant Quantum System

The rapid advancement of quantum computing has pushed classical designs into the quantum domain, breaking physical boundaries for computing-intensive and data-hungry applications with the hope that some systems may provide a quantum speedup. For example, variational quantum algorithms have been proposed for quantum neural networks to train deep learning models on qubits, achieving promising results. Existing quantum learning architectures and systems rely on single, monolithic quantum machines with abundant and stable resources, such as qubits. However, fabricating a large, monolithic quantum device is considerably more challenging than producing an array of smaller devices. In this paper, we investigate a distributed quantum system that combines multiple quantum machines into a unified system. We propose DQuLearn, which divides a quantum learning task into multiple subtasks. Each subtask can be executed distributively on individual quantum machines, with the results looping back to classical machines for subsequent training iterations. Additionally, our system supports multiple concurrent clients and dynamically manages their circuits according to the runtime status of quantum workers. Through extensive experiments, we demonstrate that DQuLearn achieves similar accuracies with significant runtime reduction, by up to 68.7% and an increase per-second circuit processing speed, by up to 3.99 times, in a 4-worker multi-tenant setting.

quantum computing↗

The Simons Observatory: HoloSim-ML: machine learning applied to the efficient analysis of radio holography measurements of complex optical systems

Near-field radio holography is a common method for measuring and aligning mirror surfaces for millimeter and sub-millimeter telescopes. In instruments with more than a single mirror, degeneracies arise in the holography measurement, requiring multiple measurements and new fitting methods. We present HoloSim-ML, a Python code for beam simulation and analysis of radio holography data from complex optical systems. This code uses machine learning to efficiently determine the position of hundreds of mirror adjusters on multiple mirrors with few micron accuracy. We apply this approach to the example of the Simons Observatory 6m telescope.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Intergovernmental Advanced Stationary PEM Fuel Cell System Demonstration (Final Report)

A program to complete the design, construction and demonstration of a PEMFC system fuelled by Ethanol, LPG or NG for telecom applications was initiated in October 2007. Early in the program the economics for Ethanol were shown to be unfeasible and permission was given by DOE to focus on LPG only. The design and construction of a prototype unit was completed in Jun 2009 using commercially available PEM FC stack from Ballard Power Systems. During the course of testing, the high pressure drop of the stack was shown to be problematic in terms of control and stability of the reformer. Also, due to the power requirements for air compression the overall efficiency of the system was shown to be lower than a similar system using internally developed low pressure drop FC stack. In Q3 2009, the decision was made to change to the Plug power stack and a second prototype was built and tested. Overall net efficiency was shown to be 31.5% at 3 kW output. Total output of the system is 6 kW. Using the new stack hardware, material cost reduction of 63% was achieved over the previous Alpha design. During a November 2009 review meeting Plug Power proposed and was granted permission, to demonstrate the new, commercial version of Plug Power's telecom system at CERL. As this product was also being tested as part of a DOE Topic 7A program, this part of the program was transferred to the Topic 7A program. In Q32008, the scope of work of this program was expanded to include a National Grid demonstration project of a micro-CHP system using hightemperature PEM technology. The Gensys Blue system was cleared for unattended operation, grid connection, and power generation in Aug 2009 at Union College in NY state. The system continues to operate providing power and heat to Beuth House. The system is being continually evaluated and improvements to hardware and controls will be implemented as more is learned about the system's operation. The program is instrumental in improving the efficiency and reducing costs of PEMFC based power systems using LPG fuel and continues to makes steps towards meeting DOE's targets. Plug Power would like to thank DOE for their support of this program.

24 POWER TRANSMISSION AND DISTRIBUTION↗