Search NASA⌕ Search

SEARCH · Search NASA

Results for “learning based 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 649 records · Page 36

Long Reach Robotic Arm

The Accelerator Division at Fermilab began a robotics program, known as the AD Robotics Initiative. A multi-axis robotic arm was proposed to be included in the program. This summer internship, our team began the planning and design for this project, called the Long Reach Robotic Arm. The problem is that critical systems around the magnets require analysis when water leaks cause them to fail. However, the tightly compacted parts and the quadrupole magnet, weighing approximately 1,000 pounds, cause access viewing problems. The process of having to dismantle and remove the magnet is time-consuming; it is not an efficient solution. The goal for the Long Reach Robotic Arm was to extend and reach behind the component of the Main Injector while "snaking" around and avoiding obstructions. At the start of the project, my teammate, Amanda Hoeksema, and I coded a program in the C language that will determine the number of links and their respective lengths for the robot arm. After, we began the 3D CAD model of the robot arm, base, and counterweight system. The design of the Long Reach Robotic Arm provided a learning experience in learning how to code in the C programming language, using SDL libraries and understanding mechanical engineering.

43 PARTICLE ACCELERATORS↗

Reconstruction and uncertainty quantification of lattice Hamiltonian model parameters from observations of microscopic degrees of freedom

The emergence of scanning probe and electron beam imaging techniques has allowed quantitative studies of atomic structure and minute details of electronic and vibrational structure on the level of individual atomic units. These microscopic descriptors, in turn, can be associated with local symmetry breaking phenomena, representing the stochastic manifestation of the underpinning generative physical model. In this work, we explore the reconstruction of exchange integrals in the Hamiltonian for a lattice model with two competing interactions from observations of microscopic degrees of freedom and establish the uncertainties and reliability of such analysis in a broad parameter-temperature space. In contrast to other approaches, we specifically specify a loss function inherent to thermodynamic systems and utilize it to estimate uncertainty in simulated realizations of different models. As an ancillary task, we develop a machine learning approach based on histogram clustering to predict phase diagrams efficiently using a reduced descriptor space. We further demonstrate that reconstruction is possible well above the phase transition and in the regions of parameter space when the macroscopic ground state of the system is poorly defined due to frustrated interactions. This suggests that this approach can be applied to the traditionally complex problems of condensed matter physics such as ferroelectric relaxors and morphotropic phase boundary systems, spin and cluster glasses, and quantum systems once the local descriptors linked to the relevant physical behaviors are known.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗

AVESTAR Center for Operational Excellence of Electricity Generation Plants

To address industry challenges in attaining operational excellence for electricity generation plants, the U.S. Department of Energy’s (DOE) National Energy Technology Laboratory (NETL) has launched a world-class facility for Advanced Virtual Energy Simulation Training and Research (AVESTARTM). This presentation will highlight the AVESTARTM Center simulators, facilities, and comprehensive training, education, and research programs focused on the operation and control of high-efficiency, near-zero-emission electricity generation plants. The AVESTAR Center brings together state-of-the-art, real-time, high-fidelity dynamic simulators with full-scope operator training systems (OTSs) and 3D virtual immersive training systems (ITSs) into an integrated energy plant and control room environment. AVESTAR’s initial offering combines--for the first time--a “gasification with CO2 capture” process simulator with a “combined-cycle” power simulator together in a single OTS/ITS solution for an integrated gasification combined cycle (IGCC) power plant with carbon dioxide (CO2) capture. IGCC systems are an attractive technology option for power generation, especially when capturing and storing CO2 is necessary to satisfy emission targets. The AVESTAR training program offers a variety of courses that merge classroom learning, simulator-based OTS learning in a control-room operations environment, and immersive learning in the interactive 3D virtual plant environment or ITS. All of the courses introduce trainees to base-load plant operation, control, startups, and shutdowns. Advanced courses require participants to become familiar with coordinated control, fuel switching, power-demand load shedding, and load following, as well as to problem solve equipment and process malfunctions. Designed to ensure work force development, training is offered for control room and plant field operators, as well as engineers and managers. Such comprehensive simulator-based instruction allows for realistic training without compromising worker, equipment, and environmental safety. It also better prepares operators and engineers to manage the plant closer to economic constraints while minimizing or avoiding the impact of any potentially harmful, wasteful, or inefficient events. The AVESTAR Center is also used to augment graduate and undergraduate engineering education in the areas of process simulation, dynamics, control, and safety. Students and researchers gain hands-on simulator-based training experience and learn how the commercial-scale power plants respond dynamically to changes in manipulated inputs, such as coal feed flow rate and power demand. Students also analyze how the regulatory control system impacts power plant performance and stability. In addition, students practice start-up, shutdown, and malfunction scenarios. The 3D virtual ITSs are used for plant familiarization, walk-through, equipment animations, and safety scenarios. To further leverage the AVESTAR facilities and simulators, NETL and its university partners are pursuing an innovative and collaborative R&D program. In the area of process control, AVESTAR researchers are developing enhanced strategies for regulatory control and coordinated plant-wide control, including gasifier and gas turbine lead, as well as advanced process control using model predictive control (MPC) techniques. Other AVESTAR R&D focus areas include high-fidelity equipment modeling using partial differential equations, dynamic reduced order modeling, optimal sensor placement, 3D virtual plant simulation, and modern grid. NETL and its partners plan to continue building the AVESTAR portfolio of dynamic simulators, immersive training systems, and advanced research capabilities to satisfy industry’s growing need for training and experience with the operation and control of clean energy plants. Future dynamic simulators under development include natural gas combined cycle (NGCC) and supercritical pulverized coal (SCPC) plants with post-combustion CO2 capture. These dynamic simulators are targeted for use in establishing a Virtual Carbon Capture Center (VCCC), similar in concept to the DOE’s National Carbon Capture Center for slipstream testing. The VCCC will enable developers of CO2 capture technologies to integrate, test, and optimize the operation of their dynamic capture models within the context of baseline power plant dynamic models. The objective is to provide hands-on, simulator-based “learn-by-operating” test platforms to accelerate the scale-up and deployment of CO2 capture technologies. Future AVESTAR plans also include pursuing R&D on the dynamics, operation, and control of integrated electricity generation and storage systems for the modern grid era. Special emphasis will be given to combining load-following energy plants with renewable and distributed generating supplies and fast-ramping energy storage systems to provide near constant baseload power.

97 MATHEMATICS AND COMPUTING↗

Deep learning–based digital twins for heat pumps

Heat pumps are effective cooling and heating appliances to save energy in buildings. However, traditional heat pump models are challenging to integrate with building demands in a co-simulation environment because of the nonlinear thermodynamics of refrigerants. Developing digital twin representatives for heat pumps capable of faster calculations with good accuracy is desirable. This study aimed to establish a generic deep learning–based digital twin for heat pumps with a large amount of high-fidelity data. Two refrigerants for two different heat pumps were considered: an air source heat pump with refrigerant R-410A, an air source heat pump with refrigerant CO 2 , a water source heat pump with refrigerant R-410A, and a water source heat pump with refrigerant CO 2 . Furthermore, results showed that the deep learning (long short-term memory) models effectively represented these four heat pumps as a digital twin: (a) accuracy for training and testing showed smaller than 0.02 for heating electricity and heating demands, and (b) the digital twins showed good consistency with original data for heating electricity and heating demands (root mean square errors of less than 0.12 W and 0.19 W, respectively). Therefore, deep learning–based heat pump models can be used in the co-simulation of building mechanical systems.

Air source heat pump↗

Comparison of machine learning systems trained to detect Alfvén eigenmodes using the CO 2 interferometer on DIII-D

Abstract A Machine-Learning (ML) based detection scheme that automatically detects Alfvén Eigenmodes (AE) in a labelled DIII-D database is presented here. Controlling AEs is important for the success of planned burning plasma devices such as ITER, since resonant fast ions can drive AEs unstable and degrade the performance of the plasma or damage the first walls of the machine vessel. Artificial Intelligence could be useful for real-time detection and control of AEs in steady-state plasma scenarios by implementing ML-based models into control algorithms that drive actuators for mitigation of AE impacts. Thus, the objective is to compare differences in performance between using two different recurrent neural network systems (Reservoir Computing Network and Long Short Term Memory Network) and two different representations of the C O 2 phase data (simple and crosspower spectrograms). All C O 2 interferometer chords are used to train both models, but only one is processed during each training step. The results from the model and data comparison show higher performance for the RCN model (True Positive Rate = 90% and False Positive Rate = 14%), and that using simple magnitude spectrograms is sufficient to detect AEs. Also, the vertical C O 2 interferometer chord passing near the center is better for ML-based detection of AEs.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Intra-hour Solar Irradiance Forecast in Multiple Locations using Deep Transfer Learning

In recent years, solar power system installation imposes several challenges on the operations of local and regional power grids due to the inherent variability of ground-level solar irradiance. This work proposes a novel real-time solar forecast methodology for intra-hour solar irradiance based on deep transfer learning from ground-based sky imager for time horizons ranging from 5-15 min. There are three unique aspects of the proposed methodology: (1) a Deep Learning based algorithm development which is modeled as a classification approach rather than a traditional regression approach; (2) the use of the Transfer Learning technique to show generalization capability, robustness, and portability of baseline model in the newly deployed location where availability of enough data for training is typically scarce, and (3) redefinition of point-based irradiation forecast error estimation technique with a window-based one that is more intuitive and user-friendly. The system is developed using multiple years of irradiance and sky image recording in New Jersey and one-year data from Colorado, USA. The method is validated against ground telemetry from these two locations of diverse geographic and climatic conditions. Results show that the forecasting method proposed in this work is robust and highly accurate (8% MAPE error) for multiple locations deployment.

Deep Learning, Convolution Neural Networks, transf↗

Determining Multi-Component Phase Diagrams with Desired Characteristics Using Active Learning

Herein, we demonstrate how to predict and experimentally validate phase diagrams for multi-component systems from a high-dimensional virtual space of all possible phase diagrams involving several elements based on small existing experimental data. The experimental data for bulk phases for known systems represents a sampling from this space, and screening the space allows multi-component phase diagrams with given design criteria to be built. This approach uses machine learning methods to predict phase diagrams and Bayesian experimental design to minimize experiments for refinement and validation, all within an active learning loop. The approach is proven by predicting and synthesizing the ferroelectric ceramic system (1-ω)(Ba 0.61 Ca 0.28 Sr 0.11 TiO 3 )-ω(BaTi 0.888 Zr 0.0616 Sn 0.0028 Hf 0.0476 O 3 ) with a relatively high transition temperature and triple point, as well as the NiTi-based pseudo-binary phase diagram (1-ω)(Ti 0.309 Ni 0.485 Hf 0.20 Zr 0.006 )-ω(Ti 0.309 Ni 0.485 Hf 0.07 Zr 0.068 Nb 0.068 ) designed for high transition temperature (ω ≤ 1). Each phase diagram is validated and optimized through only three new experiments. The complexity of these compounds is beyond the reach of today’s computational methods.

36 MATERIALS SCIENCE↗

AI-Enabled Robotic NDE for Structural Damage Assessment and Repair

The aim of this paper is to develop the concept and a prototype of an intelligent mobile robotic platform that is integrated with nondestructive evaluation (NDE) capabilities for autonomous live inspection and repair. In many industrial environments, such as the application of power plant boiler inspection, human inspectors often have to perform hazardous and challenging tasks. There is a significant chance of injury, considering the confined spaces and limited visibility of the inspection environment and hazards such as pressurization and improper water levels. In order to provide a solution to eliminate these dangers, the concept of a new robotic system was developed and prototyped that is capable of autonomously sweeping the region to be inspected. The robot design contains systematic integration of components from robotics, NDE, and artificial intelligence (AI). A magnetic track system is used to navigate over the vertical steel structures required for examination. While moving across the inspection area, the robot uses an NDE sensor to acquire data for inspection and repair. This paper presents a design of a portable NDE scanning system based on eddy current array probes, which can be customized and installed on various mobile robot platforms. Machine learning methods are applied for semantic segmentation that will simultaneously localize and recognize defects without the need of human intervention. Experiments were conducted that show the NDE and repair capabilities of the system. Improvements in human safety and structural damage prevention, as well as lowering the overall costs of maintenance, are possible through the implementation of this robotic NDE system.

Materials Science↗

Decentralized Distributed Proximal Policy Optimization (DD-PPO) for High Performance Computing Scheduling on Multi-User Systems

Resource allocation in High Performance Computing (HPC) environments presents a complex and multifaceted challenge for job scheduling algorithms. Beyond the efficient allocation of system resources, schedulers must account for and optimize multiple performance metrics, including job wait time and system throughput. Traditional heuristic-based scheduling algorithms increasingly struggle and lack the efficiency needed to meet the demands and address the complexity and scale of modern HPC systems. Consequently, recent research efforts have focused on leveraging advancements in Artificial Intelligence (AI) and Deep Learning (DL), particularly Reinforcement Learning (RL), to develop more adaptable and intelligent scheduling strategies. Previous RL-based scheduling approaches have explored a range of algorithms, from Deep Q-Networks (DQN) to Proximal Policy Optimization (PPO), and more recently, hybrid methods that integrate Graph Neural Networks (GNNs) with RL techniques. However, a common limitation across these methods is their reliance on relatively small datasets, with few methods being evaluated using large-scale, multi-million-job trace datasets representative of real-world HPC workloads. Moreover, existing RL schedulers face scalability issues due to centralized policy updates, which hinder training efficiency and performance when applied to large datasets. This study introduces a novel RL-based scheduler utilizing Decentralized Distributed Proximal Policy Optimization (DD-PPO) algorithm, which supports large-scale distributed training across multiple workers without requiring parameter synchronization at every step. By eliminating reliance on centralized updates to a shared policy, the DD-PPO scheduler enhances scalability, training efficiency, and sample utilization. Experimental validation using a large real-world dataset containing over 11.5 million job traces collected from petascale HPC systems over six years assesses the influence of dataset scale on training effectiveness and compares DD-PPO performance to traditional and advanced scheduling approaches. The experimental results demonstrate improved scheduling performance in comparison to both heuristic-based schedulers and existing RL-based scheduling algorithms.

AI↗

A Tailored Convolutional Neural Network for Nonlinear Manifold Learning of Computational Physics Data Using Unstructured Spatial Discretizations

In this work, we propose a nonlinear manifold learning technique based on deep convolutional autoencoders that is appropriate for model order reduction of physical systems in complex geometries. Convolutional neural networks have proven to be highly advantageous for compressing data arising from systems demonstrating a slow-decaying Kolmogorov n-width. However, these networks are restricted to data on structured meshes. Unstructured meshes are often required for performing analyses of real systems with complex geometry. Our custom graph convolution operators based on the available differential operators for a given spatial discretization effectively extend the application space of deep convolutional autoencoders to systems with arbitrarily complex geometry that are typically discretized using unstructured meshes. We propose sets of convolution operators based on the spatial derivative operators for the underlying spatial discretization, making the method particularly well suited to data arising from the solution of partial differential equations. We demonstrate the method using examples from heat transfer and fluid mechanics and show better than an order of magnitude improvement in accuracy over linear methods.

97 MATHEMATICS AND COMPUTING↗

Improving net ecosystem CO2 flux prediction using memory-based interpretable machine learning

Terrestrial ecosystems play a central role in the global carbon cycle and affect climate change. However, our predictive understanding of these systems is still limited due to their complexity and uncertainty about how key drivers and their legacy effects influence carbon fluxes. Here, we propose an interpretable Long Short-Term Memory (iLSTM) network for predicting net ecosystem CO 2 exchange (NEE) and interpreting the influence on the NEE prediction from environmental drivers and their memory effects. We consider five drivers and apply the method to three forest sites in the United States. Besides performing the prediction in each site, we also conduct transfer learning by using the iLSTM model trained in one site to predict at other sites. Results show that the iLSTM model produces good NEE predictions for all three sites and, more importantly, it provides reasonable interpretations on the input driver's importance as well as their temporal importance on the NEE prediction. Additionally, the iLSTM model demonstrates good across-site transferability in terms of both prediction accuracy and interpretability. The transferability can improve the NEE prediction in unobserved forest sites, and the interpretability advances our predictive understanding and guides process-based model development.

Liu, Siyan↗

Neural Lyapunov Differentiable Predictive Control

We present a learning-based predictive control methodology using the differentiable programming framework with sufficient Lyapunov-based guarantees. The neural Lyapunov differentiable predictive control (NLDPC) learns the policy by constructing a computational graph encompassing the system dynamics, state, and input constraints, and the necessary Lyapunov certification constraints, and thereafter using the automatic differentiation to update the neural policy parameters. In conjunction, our approach jointly learns a Lyapunov function that certifies the regions of state-space with stable dynamics. We also provide an initial condition sampling-based statistical guarantee for the training of NLDPC. Our offline training approach provides a computationally efficient and scalable alternative to classical model predictive control solutions, which now directly comes with Lyapunov based guarantees as shown in this paper. We substantiate the advantages of the proposed approach with simulations to stabilize the double integrator model and on an example of controlling an aircraft model.

Mukherjee, Sayak↗

Machine Learning Tools Set for Natural Gas Fuel Cell System Design

This study is focusing on leveraging the system design tools set for the next-generation solid oxide fuel cell (SOFC) based natural gas fuel cell (NGFC) system. Conventionally, system design and optimization of NGFC systems rely heavily on traditional reduced order model (ROM) techniques and designers’ experience level. For overcoming the technical barriers of system design, multiple multi-physics models and machine learning (ML) tools have been utilized to automate the conceptual design process and enhance the reliability of solutions for the NGFC system. The proposed tools set includes a physics-informed ML tool for automated ROM construction that leverages advances in deep neural networks to significantly reduce ROM prediction error for the NGFC power island compared to traditional approaches. The constructed physics-informed ML ROM can be used in system design, and optimization tools set Institute for the Design of Advanced Energy Systems (IDAES) Process Systems Engineering (PSE) framework. The tools set also provides a user-friendly graphic user interface built within Jupyter Notebooks, and the complete tools set is open-source public available.

Wang, Dewei↗

A review of computing-based automated fault detection and diagnosis of heating, ventilation and air conditioning systems

We report faults in Heating, Ventilation, and Air Conditioning (HVAC) systems of buildings result in significant energy waste in building operation. With fast-growing sensing data availability and advancement in computing, computational modeling has demonstrated strong capability to detect and diagnose HVAC system faults, hence, ensuring efficient building operation. This paper comprehensively reviews the state-of-the-art computing-based fault detection and diagnosis (FDD) for HVAC systems. Overall, the reviewed computing-based FDD methods are classified as two major approaches: knowledge-based and data-driven approaches. We then identify multiple important topics, including data availability, training data size, data quality, approach generality, capability, interpretability, and required modeling efforts, along with corresponding metrics to summarize the most updated FDD development. Generally, the knowledge-based approaches are further divided as physics-based modeling, Diagnostic Bayesian Network, and performance indicator-based methods while data-driven approaches include supervised learning, unsupervised learning, and regression and statistics-based methods. State-of-the-art FDD development, remaining challenges, and future research directions are further discussed to push forward FDD in practice. Availability of fault data, capability of existing methods to deal with complex fault situations (such as simultaneous faults), modeling interpretability for data-driven methods, and required engineering efforts for physics-based methods are identified as remaining challenges in FDD development. Improving modeling fidelity and reducing modeling efforts are essential for applying physics-based methods in real buildings. Meanwhile, addressing fault data availability, increasing algorithm adaptability, and handling multiple faults are essential to further enhance the applicability of data-driven FDD approaches.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Deep Learning-Based Dynamic Modeling of Three-Phase Voltage Source Inverters

Inverter-based resource (IBR) models are necessary to analyze modern power system stability and create effective control strategies. Modeling IBRs in converter-rich power systems is crucial, yet challenging due to the lack of commercial information on converter topologies and control parameters. This paper proposes novel convolutional neural network (CNN)–based data-driven techniques for modeling IBRs, addressing adaptability and proprietary concerns without requiring internal system physics knowledge. The proposed method is tested using real grid-tied commercial IBR transient data and demonstrates effectiveness and accuracy. Furthermore, the developed modeling approach is integrated and implemented in the open-source power distribution simulation and analysis tool, GridLAB-D, to illustrate the potentiality of dynamic analysis of large-scale power systems with high IBRs.

deep learning, artificial intelligence↗

Complementary workflows for identifying one-hop network behavior and multi-hop network dependencies

A network analysis tool evaluates network flow information in complementary workflows to identify one-hop behavior of network assets and also identify multi-hop dependencies between network assets. In one workflow (e.g., using association rule learning), the network analysis tool can identify significant one-hop communication patterns to and/or from network assets, taken individually. Based on the identified one-hop behavior, the network analysis tool can discover patterns of similar communication among different network assets, which can inform decisions about deploying patch sets, mitigating damage, configuring a system, or detecting anomalous behavior. In a different workflow (e.g., using deep learning or cross-correlation analysis), the network analysis tool can identify significant multi-hop communication patterns that involve network assets in combination. Based on the identified multi-hop dependencies, the network analysis tool can discover functional relationships between network assets, which can inform decisions about configuring a system, managing critical network assets, or protecting critical network assets.

97 MATHEMATICS AND COMPUTING↗

HPC Digital Twins for Evaluating Scheduling Policies, Incentive Structures and their Impact on Power and Cooling

Schedulers are critical for optimal resource utilization in high-performance computing. Traditional methods to evaluate sched- ulers are limited to post-deployment analysis, or simulators, which do not model associated infrastructure. In this work, we present the first-of-its-kind integration of scheduling and digital twins in HPC. This enables what-if studies to understand the impact of parameter configurations and scheduling decisions on the physical assets, even before deployment, or regarching changes not easily realizable in production. We (1) provide the first digital twin framework extended with scheduling capabilities, (2) integrate various top-tier HPC systems given their publicly available datasets, (3) implement extensions to integrate external scheduling simulators. Finally, we show how to (4) implement and evaluate incentive structures, as- well-as (5) evaluate machine learning based scheduling, in such novel digital-twin based meta-framework to prototype scheduling. Our work enables what-if scenarios of HPC systems to evaluate sustainability, and the impact on the simulated system.

Maiterth, Matthias [ORNL] (ORCID:000000018698460X)↗

5G integrated edge computing platform for efficient component monitoring in coal-fired power plants

This project developed a cutting-edge 5G-integrated edge computing framework to enhance operational efficiency and reliability in coal-fired power plants through real-time component monitoring and anomaly detection. The initiative focused on leveraging distributed machine learning, federated learning, and 5G-based dynamic network slicing to support scalable, fault-tolerant monitoring environments to meet the operational requirements in industrial control systems. With a Distributed Edge Computing Service (DECS) orchestration, this project enabled federated learning at edge for condition monitoring and introduced adaptive client selection strategies to minimize communication overhead. Scalable distributed training was achieved using the Horovod framework, thus enhancing performance across edge nodes. In the realm of 5G networking, the project designed and deployed reconfigurable, QoS-aware network slicing tailored for operational technology (OT) environments, integrating software-defined networks to bolster cyber-resilience and enabling dynamic slicing for federated learning workloads. A significant milestone was the development of a virtualized ICS environment with 5G core integration—which allowed elastic and fault tolerant distributed training on real-world datasets such as NASA Bearings, Hydraulic Systems, and TEP. To broaden the impact of the project, a TRL-3 virtualized ICS testbed for research and education was designed. This project engaged several graduate and undergraduate students to conduct research on the cutting-edge technology, and it resulted in one PhD dissertation, one MS thesis, and over 14 peer-reviewed publications. With the support of this project students also participated in national cybersecurity competitions to improve their professional development skills.

20 FOSSIL-FUELED POWER PLANTS↗