Discrete real-time learning of quantum-state subspace evolution of many-body systems in the presence of time-dependent control fields
Not Available
Gui, Shaojun (ORCID:0009000328744255)↗
SEARCH · Search NASA
Results for “Learning control”
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
1981 LTA technology assessment - Past and present
A four-part presentation is made of (1) lessons learned from the design and operation of the 'classic' airships of the 1920s and 30s, with respect to such issues as construction, propulsion, control, instrumentation, ground handling, habitability, aerodynamics, and structure and construction; (2) lessons learned from the development of such specialized lighter-than-air (LTA) concepts as metal-clad airships, semi-buoyant lifting bodies, experimental, sport and commercial free balloons, high-altitude platforms, and tethered aerostats; (3) the current status of LTA technology in various countries, with emphasis on significant developments in configuration, dynamics, control, structures, materials, and propulsion; and (4) a projection of future trends. It is concluded that socio-economic factors will strongly influence and encourage LTA development in the 1990s.
Ashford, R. L.↗
Metric Learning to Accelerate Convergence of Operator Splitting Methods
Recent developments in machine learning have led to promising advances in accelerating the solution of constrained optimization problems. Increasing demand for real-time decision-making capabilities in applications such as artificial intelligence and optimal control has led to a variety of proposed strategies for learning to produce fast solutions to optimization problems. For example, recent works have shown that it is possible to accelerate the convergence of optimization algorithms by learning to select their parameters, such as gradient descent stepsizes. This work proposes a new approach, in which the underlying metric spaces of proximal operator splitting algorithms are learned to maximize convergence rate. While prior works in optimization theory have derived optimal metrics in simple cases, no such result exists for many practical problem forms including general Quadratic Programming (QP). This paper shows how differentiable optimization can enable the end-to-end learning of proximal metrics, enhancing the convergence of proximal algorithms for QP problems beyond what is possible based on known theory. Additionally, the results illustrate a strong connection between the learned proximal metrics and active constraints at the optima, leading to an interpretation in which the predicted proximal metrics can be viewed as a form of active set prediction.
King, Ethan [BATTELLE (PACIFIC NW LAB)]↗
Prediction of DIII-D Pedestal Structure from Externally Controllable Parameters
The sharp increase of pressure at the edge of a high confinement mode (H-mode) plasma, the pedestal, strongly impacts overall plasma performance. Predicting the pedestal is a necessity to control and optimize tokamak operations. An experimental data-driven machine learning (ML) approach is presented that predicts the pedestal heights and widths of electron density (ne) and electron temperature (Te) profiles as well as the separatrix ne from externally controllable parameters such as the plasma shape, heating method and power, and gas puff rate and integrated gas puff. The OMFIT framework was used with DIII-D data to efficiently, robustly, and automatically build a database of pedestal parameters to train machine learning models. Database creation was enabled by the search engine tool for DIII-D data, TokSearch, which parallelizes data fetching, enabling fast searches through basic signals of thousands of DIII-D shots and selection of relevant time intervals. Principal Component Analysis (PCA) separated the database into three clusters that represent classes of plasma shapes that are regularly used in DIII-D. The most important parameters for setting the pedestal structure were plasma current (Ip), toroidal magnetic field (Bφ), neutral beam heating power (PNBI) and shaping quantities. The Deep Jointly Informed Neural Networks (DJINN) algorithm was applied to identify suitable neural network (NN) architectures that appropriately capture the features of the pedestal database. Separate NNs were implemented for each pedestal parameter, and ensembling methods were used to improve the prediction accuracy and allowed estimation of the prediction uncertainty. The pedestal predictions of the test dataset lie within the measurement uncertainties of the pedestal parameters. The NN outperformed simple Linear Regression (LR) analysis, indicating non-linear dependencies in the pedestal structure. The presented achievements illustrate a promising path for future research, using feature extraction to infer experimental trends and thereby improve pedestal models as well as deploying NN for a fast pedestal prediction in DIII-D scenario development.
70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
Digital twins and deep learning segmentation of defects in monolayer MX 2 phases
Developing methods to understand and control defect formation in nanomaterials offers a promising route for materials discovery. Monolayer MX 2 phases represent a particularly compelling case for defect engineering of nanomaterials due to the large variability in their physical properties as different defects are introduced into their structure. However, effective identification and quantification of defects remain a challenge even as high-throughput scanning transmission electron microscopy methods improve. This study highlights the benefits of employing first principles calculations to produce digital twins for training deep learning segmentation models for defect identification in monolayer MX 2 phases. Around 600 defect structures were obtained using density functional theory calculations, with each monolayer MX 2 structure being subjected to multislice simulations for the purpose of generating the digital twins. Several deep learning segmentation architectures were trained on this dataset, and their performances evaluated under a variety of conditions such as recognizing defects in the presence of unidentified impurities, beam damage, grain boundaries, and with reduced image quality from low electron doses. Further, this digital twin approach allows benchmarking different deep learning architectures on a theory dataset, which enables the study of defect classification under a broad array of finely controlled conditions. It thus opens the door to resolving the underpinning physical reasons for model shortcomings and potentially chart paths forward for automated discovery of materials defect phases in experiments.
36 MATERIALS SCIENCE↗
MO-DE-BRA-01: Flipped Physics Courses Within a Radiologic Technologist Program: Video Production and Long Term Outcomes
Purpose: To determine if the flipped class format has an effect on examination results for a radiologic technologist (RT) program and discuss benefits from creating video resources. Methods: From 2001–2015, students had taken both a radiological physics and quality control (QC) class as a part of their didactic training. In 2005/2006, the creation of videos of didactic lectures and QC test demonstrations allowed for a flip where content was studied at home while exercises and reviews were done in-class. Final examinations were retrospectively reviewed from this timeframe. 12 multiple choice physics questions (MCP) and 5 short answer QC questions (SAQC) were common to pre and post flip exams. The RT program’s ARRT exam scores were also obtained and compared to national averages. Results: In total, 36 lecture videos and 65 quality control videos were created for the flipped content. Data was ∼2.4GB and distributed to students via USB or CD media. For MCP questions, scores improved by 7.9% with the flipped format and significance (Student’s t-test, p<0.05) was found for 3 of the 12 questions. SAQC questions showed improvement by 14.6% and significance was found for 2 of the 5 questions. Student enrollment increased from ∼14 (2001–2004) to ∼23 students (2005–15). Content was continuously added post-flip due to the efficiency of delivery. The QC class in 2003 covered 45 test setups in-class while 65 were covered with video segments in 2014. Flipped materials are currently being repurposed. In 2015, this video content was restructured into an ARRT exam review guide and in 2016, the content was reorganized for fluoroscopy training for physicians. Conclusion: We believe that flipped classes can improve efficiency of content delivery and improve student performance even with an increase in class size. This format allows for flexibility in learning as well as re-use in multiple applications.
07 ISOTOPE AND RADIATION SOURCES↗
SECURED: Simulator-Enhanced Control and Understanding of Reactor systems for cyber-Event Defense
The study discusses a learning approach for analyzing cyber-events in reactor systems using integrated hardware and personal computer simulator models. Key points include the rise in cyber-attacks and their sophistication in industrial control systems (ICS), the necessity for awareness, understanding, resource allocation, and preparation to combat these threats, and the digital transformation of old and new nuclear plants, increasing their exposure to cyber threats. It highlights the cyber vulnerabilities of advanced reactor systems, which rely on digital instrumentation and control for operations and safety functions, making them susceptible to cyber-attacks. The approach involves demonstrating reactor system plant ICS cyber-attacks under various operational conditions utilizing tools like simulator models and hardware-based kits. A strategic solution approach tailored to critical infrastructure is emphasized, along with community engagement for public and government support, adopting effective learning approaches, and the preparation for anticipated future challenges. The presentation concludes with a call to action to address challenges, leverage opportunities, and advance through lesson learning in cybersecurity for nuclear energy systems.
21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
Software Architecture to Support the Evolution of the ISRU RESOLVE Engineering Breadboard Unit 2 (EBU2)
The In-Situ Resource Utilization (ISRU) Regolith & Environmental Science and Oxygen & Lunar Volatiles Extraction (RESOLVE) software provides operation of the physical plant from a remote location with a high-level interface that can access and control the data from external software applications of other subsystems. This software allows autonomous control over the entire system with manual computer control of individual system/process components. It gives non-programmer operators the capability to easily modify the high-level autonomous sequencing while the software is in operation, as well as the ability to modify the low-level, file-based sequences prior to the system operation. Local automated control in a distributed system is also enabled where component control is maintained during the loss of network connectivity with the remote workstation. This innovation also minimizes network traffic. The software architecture commands and controls the latest generation of RESOLVE processes used to obtain, process, and quantify lunar regolith. The system is grouped into six sub-processes: Drill, Crush, Reactor, Lunar Water Resource Demonstration (LWRD), Regolith Volatiles Characterization (RVC) (see example), and Regolith Oxygen Extraction (ROE). Some processes are independent, some are dependent on other processes, and some are independent but run concurrently with other processes. The first goal is to analyze the volatiles emanating from lunar regolith, such as water, carbon monoxide, carbon dioxide, ammonia, hydrogen, and others. This is done by heating the soil and analyzing and capturing the volatilized product. The second goal is to produce water by reducing the soil at high temperatures with hydrogen. This is done by raising the reactor temperature in the range of 800 to 900 C, causing the reaction to progress by adding hydrogen, and then capturing the water product in a desiccant bed. The software needs to run the entire unit and all sub-processes; however, throughout testing, many variables and parameters need to be changed as more is learned about the system operation. The Master Events Controller (MEC) is run on a standard laptop PC using Windows XP. This PC runs in parallel to another laptop that monitors the GC, and a third PC that monitors the drilling/ crushing operation. These three PCs interface to the process through a CompactRIO, OPC Servers, and modems.
Moss, Thomas↗
Improving and testing machine learning methods for benchmarking soil carbon dynamics representation of land surface models
Representation of soil organic carbon (SOC) dynamics in Earth system models (ESMs) is a key source of uncertainty in predicting carbon climate feedbacks. The magnitude of this uncertainty can be reduced by accurate representation of environmental controllers of SOC stocks in ESMs. In this study, we used data of environmental factors, field SOC observations, ESM projections and machine learning approaches to identify dominant environmental controllers of SOC stocks and derive functional relationships between environmental factors and SOC stocks. Our derived functional relationships predicted SOC stocks with similar accuracy as the machine learning approach. We used the derived relationships to benchmark the coupled model intercomparison project phase six ESM representation of SOC stocks. We found divergent environmental control representation in ESMs in comparison to field observations. Representation of SOC in ESMs can be improved by including additional environmental factors and representing their functional relationships with SOC consistent with observations.
54 ENVIRONMENTAL SCIENCES↗
Are We Adapting to Floods? Evidence from Global Flooding Fatalities
There has been a growing interest in understanding whether and how people adapt to extreme weather events in a changing climate. This article presents one of the first empirical analyses of adaptation to flooding on a global scale. Using a sample of 97 countries between 1985 and 2010, we investigate the extent and pattern of flood adaptation by estimating the effects of a country's climatological risk, recent flood experiences, and socioeconomic characteristics on its flood-related fatalities. Our results provide mixed evidence on adaptation: countries facing greater long-term climatological flooding risks do not necessarily adapt better and suffer fewer fatalities; however, after controlling for the cross-country heterogeneity, we find that more recent flooding shocks have a significant and negative effect on fatalities from subsequent floods. These findings may suggest the short-term learning dynamics of adaptation and potential inefficacy of earlier flood control measures, particularly those that promote increased exposure in floodplains. Our findings provide important implications for climate adaptation policy making and climate modeling.
54 ENVIRONMENTAL SCIENCES↗
ARM-IRL: Adaptive Resilience Metric Quantification Using Inverse Reinforcement Learning
The resilience of safety-critical systems is gaining importance due to the rise in cyber and physical threats, especially within critical infrastructure. Traditional static resilience metrics may not capture dynamic system states, leading to inaccurate assessments and ineffective responses to cyber threats. This work aims to develop a data-driven, adaptive method for resilience metric learning. We propose a data-driven approach using inverse reinforcement learning (IRL) to learn a single, adaptive resilience metric. The method infers a reward function from expert control actions. Unlike previous approaches using static weights or fuzzy logic, this work applies adversarial inverse reinforcement learning (AIRL), training a generator and discriminator in parallel to learn the reward structure and derive an optimal policy. The proposed approach is evaluated on multiple scenarios: optimal communication network rerouting, power distribution network reconfiguration, and cyber–physical restoration of critical loads using the IEEE 123-bus system. The adaptive, learned resilience metric enables faster critical load restoration in comparison to conventional RL approaches.
97 MATHEMATICS AND COMPUTING↗
Building intelligent systems - Artificial intelligence research at NASA Ames Research Center
The basic components that make up the goal of building autonomous intelligent systems are discussed, and ongoing work at the NASA Ames Research Center is described. It is noted that a clear progression of systems can be seen through research settings (both within and external to NASA) to Space Station testbeds to systems which actually fly on the Space Station. The starting point for the discussion is a 'truly' autonomous Space Station intelligent system, responsible for a major portion of Space Station control. Attention is given to research in fiscal 1987, including reasoning under uncertainty, machine learning, causal modeling and simulation, knowledge from design through operations, advanced planning work, validation methodologies, and hierarchical control of and distributed cooperation among multiple knowledge-based systems.
Friedland, Peter↗
Building intelligent systems: Artificial intelligence research at NASA Ames Research Center
The basic components that make up the goal of building autonomous intelligent systems are discussed, and ongoing work at the NASA Ames Research Center is described. It is noted that a clear progression of systems can be seen through research settings (both within and external to NASA) to Space Station testbeds to systems which actually fly on the Space Station. The starting point for the discussion is a truly autonomous Space Station intelligent system, responsible for a major portion of Space Station control. Attention is given to research in fiscal 1987, including reasoning under uncertainty, machine learning, causal modeling and simulation, knowledge from design through operations, advanced planning work, validation methodologies, and hierarchical control of and distributed cooperation among multiple knowledge-based systems.
Friedland, P.↗
Reinforcement Learning for Small Autonomous Ground Vehicle
Microcontroller: • ESP-WROOM 32 control board • Wi-Fi 802.11 b/g/n Actuators: • 2 Futaba S3003 Servos • Commanded angles of 0 to 180 • Effectors • Piano wire “legs” and “feet” • Current, Voltage, Power Sensor: • Adafruit INA260 • Range Finder (1D LiDAR) Sensor: • SparkFun VL53L1X • Power Supply: • Battery powered, Adafruit UN3480 Li Ion Polymer 1200 mAh • Adafruit JST 2 PH power breakout board • Body: • Additively manufactured frame
Wells, William Willie↗
Modernizing Accelerator Responsiveness and Controls in Operations
Accelerators increasingly use artificial intelligence (AI) and machine learning (ML) software and workflows for a variety of tasks, from optimization to fault detection and recovery. Efficient and sustainable application of these technologies necessitates specialized and facility-specific infrastructure commitments. Accelerator facilities also introduce unique radiation and security hazards, placing additional demands on operational infrastructure. These needs further escalate the prioritization of effective collaboration models and associated funding mechanisms and legal frameworks.
43 PARTICLE ACCELERATORS↗
Fast and accurate reduced-order modeling of a MOOSE-based additive manufacturing model with operator learning
One predominant challenge in additive manufacturing (AM) is to achieve specific material properties by manipulating manufacturing process parameters during the runtime. Such manipulation tends to increase the computational load imposed on existing simulation tools employed in AM. The goal of the present work is to construct a fast and accurate reduced-order model (ROM) for an AM model developed within the Multiphysics Object-Oriented Simulation Environment (MOOSE) framework, ultimately reducing the time/cost of AM control and optimization processes. Our adoption of the operator learning (OL) approach enabled us to learn a family of differential equations produced by altering process variables in the laser’s Gaussian point heat source. More specifically, we used the Fourier neural operator (FNO) and deep operator network (DeepONet) to develop ROMs for time-dependent responses. Furthermore, we benchmarked the performance of these OL methods against a conventional deep neural network (DNN)-based ROM. Ultimately, we found that OL methods offer comparable performance and, in terms of accuracy and generalizability, even outperform DNN at predicting scalar model responses. The DNN-based ROM afforded the fastest training time. Furthermore, all the ROMs were faster than the original MOOSE model yet still provided accurate predictions. FNO had a smaller mean prediction error than DeepONet, with a larger variance for time-dependent responses. Unlike DNN, both FNO and DeepONet were able to simulate time series data without the need for dimensionality reduction techniques. Finally, the present work can help facilitate the AM optimization process by enabling faster execution of simulation tools while still preserving evaluation accuracy.
36 MATERIALS SCIENCE↗
Quantum-Inspired Bayesian Sampling for Uncertainty Quantification and Machine Learning (Final Technical Report)
With increasing simulation and measurement data, machine learning and artificial intelligence have been widely used in computational decision-making of complex engineering systems. The resulting tools, such as uncertainty quantification solvers, reinforcement learning, and physics-informed machine learning, have achieved great success in critical DOE tasks such as material discovery and design, energy system modeling and control, and numerical weather and climate prediction. A core topic in scientific machine learning and artificial intelligence is Bayesian inference: given an observed data set, people want to estimate the posterior distribution of a (possibly large) number of hidden parameters. Due to the flexibility and weak assumptions, Bayesian sampling has been the mainstream Bayesian inference solvers despite the rapid progress of approximate Bayesian inference. Classical Bayesian sampling methods such as Markov-chain Monte Carlo suffer from a low-acceptance rate due to the random walk nature, therefore state-of-the-art techniques use Hamiltonian Monte Carlo and its variants to efficiently draw posterior samples in a high dimension. The key idea of Hamiltonian Monte Carlo and its variants is to simulate the Hamiltonian dynamics of a classical particle with a fixed mass, and their performance significantly degrades when the posterior distribution is highly spiky or has multiple modes. Leveraging the idea of quantum physics, this project has investigated new theory, algorithms and applications of Bayesian inference (especially Bayesian sampling). The main results include: (1) novel quantum-inspired Bayesian sampling methods that can lead to better accuracy for challenging multi-modal or spiky distributions, (2) more scalable machine learning framework leveraging tensor-compressed Bayesian inference, and (3) Bayesian and sampling approaches for verifying the robustness of continuous and binary neural networks.
97 MATHEMATICS AND COMPUTING↗