Search NASA⌕ Search

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.

At least 1,639 records · Page 91

Observations and Lessons Learned from Testing of the Hanford Waste Treatment Plant Standard High Solids Vessel Design - 18635

The Hanford Waste Treatment and Immobilization Plant (WTP) recently completed qualification testing of the mixing system for the standard high solids vessel design the U.S. Department of Energy (DOE) proposed to replace several vessels in the design of the plant Pretreatment Facility. Testing was split into two phases. The first phase exercised the pulse jet mixer control system to ensure that the control software could accommodate fluids across the complete range of expected densities and viscosities within the vessel for all operational modes. The second phase of testing was focused on the mixing performance of the vessel, specifically, whether mixing was adequate to support the transfer, de-inventory, throughput, and sampling functions of the vessel. Key observations and lessons learned from testing include: - Successful transfer of waste within and beyond the design basis slurry solids concentration; - Successful resuspension and transfer of large, heavy particles; - Effective performance of multi-level bubblers for process control and monitoring; - Effective controls performance; - Reduction of sparger flowrate from nominal design flow; - Liquid blending within about 15 minutes; - Insights into sample representativeness and uniformity of transfers to inform process control strategies. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Optimization of microwave emission from laser filamentation with a machine learning algorithm

We demonstrate that is it possible to optimize the yield of microwave radiation from plasmas generated by laser filamentation in atmosphere through manipulation of the laser wavefront. A genetic algorithm controls a deformable mirror that reconfigures the wavefront using the microwave waveform amplitude as feedback. Optimization runs performed as a function of air pressure show that the genetic algorithm can double the microwave field strength relative to when the mirror surface is flat. Here, an increase in the volume and brightness of the plasma fluorescence accompanies the increase in microwave radiation, implying an improvement in the laser beam intensity profile through the filamentation region due to the optimized wavefront.

Englesbe, Alexander↗

State predictive information bottleneck

We report the ability to make sense of the massive amounts of high-dimensional data generated from molecular dynamics simulations is heavily dependent on the knowledge of a low-dimensional manifold (parameterized by a reaction coordinate or RC) that typically distinguishes between relevant metastable states, and which captures the relevant slow dynamics of interest. Methods based on machine learning and artificial intelligence have been proposed over the years to deal with learning such low-dimensional manifolds, but they are often criticized for a disconnect from more traditional and physically interpretable approaches. To deal with such concerns, in this work we propose a deep learning based state predictive information bottleneck approach to learn the RC from high-dimensional molecular simulation trajectories. We demonstrate analytically and numerically how the RC learnt in this approach is connected to the committor in chemical physics and can be used to accurately identify transition states. A crucial hyperparameter in this approach is the time delay or how far into the future the algorithm should make predictions about. Through careful comparisons for benchmark systems, we demonstrate that this hyperparameter choice gives useful control over how coarse-grained we want the metastable state classification of the system to be. We thus believe that this work represents a step forward in systematic application of deep learning based ideas to molecular simulations.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Stomata in-sight: Integrating live confocal microscopy with leaf gas exchange and environmental control

Stomatal anatomy (aperture area, length, and width) influences leaf-level physiology traits including conductance to water vapor. Stomatal anatomy can be visualized in situ by microscopy, but the difficulty of regulating the atmospheric environment of a microscope stage means that the conditions under which imaging is done are rarely physiologically relevant. Alternatively, leaf gas exchange instruments that measure gas fluxes reflect stomatal anatomical characteristics in aggregate, but the relative strengths of anatomical traits to control water use (e.g. size vs density) cannot be firmly established. To reconcile the microscopic stomatal characteristics with leaf-level gas exchange, we describe a tool that combines laser scanning confocal microscopy, gas exchange instruments, and machine-learning image analysis to simultaneously observe anatomical characteristics of many (>40) stomata alongside leaf-level traits like photosynthesis, transpiration, and stomatal conductance. We demonstrate how the tool has the resolution capable of quantifying aperture sizes and variability in maize (Zea mays) leaves under 5 steady-state light/pCO 2 treatments while tightly controlling other environmental variables like relative humidity and temperature. A model used to calculate stomatal conductance from measured apertures and stomatal density accurately matched stomatal conductance measured by gas exchange. This technical advancement will provide insight on how stomatal anatomy and function trade off to influence stomatal conductance and leaf-level water use efficiency.

59 BASIC BIOLOGICAL SCIENCES↗

Multi-Task Learning of Scanning Electron Microscopy and Synthetic Thermal Tomography Images for Detection of Defects in Additively Manufactured Metals

One of the key challenges in laser powder bed fusion (LPBF) additive manufacturing of metals is the appearance of microscopic pores in 3D-printed metallic structures. Quality control in LPBF can be accomplished with non-destructive imaging of the actual 3D-printed structures. Thermal tomography (TT) is a promising non-contact, non-destructive imaging method, which allows for the visualization of subsurface defects in arbitrary-sized metallic structures. However, because imaging is based on heat diffusion, TT images suffer from blurring, which increases with depth. We have been investigating the enhancement of TT imaging capability using machine learning. In this work, we introduce a novel multi-task learning (MTL) approach, which simultaneously performs the classification of synthetic TT images, and segmentation of experimental scanning electron microscopy (SEM) images. Synthetic TT images are obtained from computer simulations of metallic structures with subsurface elliptical-shaped defects, while experimental SEM images are obtained from imaging of LPBF-printed stainless-steel coupons. MTL network is implemented as a shared U-net encoder between the classification and the segmentation tasks. Results of this study show that the MTL network performs better in both the classification of synthetic TT images and the segmentation of SEM images tasks, as compared to the conventional approach when the individual tasks are performed independently of each other.

36 MATERIALS SCIENCE↗

Evaluating county-level lung cancer incidence from environmental radiation exposure, PM 2.5 , and other exposures with regression and machine learning models

Characterizing the interplay between exposures shaping the human exposome is vital for uncovering the etiology of complex diseases. For example, cancer risk is modified by a range of multifactorial external environmental exposures. Environmental, socioeconomic, and lifestyle factors all shape lung cancer risk. However, epidemiological studies of radon aimed at identifying populations at high risk for lung cancer often fail to consider multiple exposures simultaneously. For example, moderating factors, such as PM 2.5 , may affect the transport of radon progeny to lung tissue. This ecological analysis leveraged a population-level dataset from the National Cancer Institute’s Surveillance, Epidemiology, and End-Results data (2013–17) to simultaneously investigate the effect of multiple sources of low-dose radiation (gross γ activity and indoor radon) and PM 2.5 on lung cancer incidence rates in the USA. County-level factors (environmental, sociodemographic, lifestyle) were controlled for, and Poisson regression and random forest models were used to assess the association between radon exposure and lung and bronchus cancer incidence rates. Tree-based machine learning (ML) method perform better than traditional regression: Poisson regression: 6.29/7.13 (mean absolute percentage error, MAPE), 12.70/12.77 (root mean square error, RMSE); Poisson random forest regression: 1.22/1.16 (MAPE), 8.01/8.15 (RMSE). The effect of PM 2.5 increased with the concentration of environmental radon, thereby confirming findings from previous studies that investigated the possible synergistic effect of radon and PM 2.5 on health outcomes. In summary, the results demonstrated (1) a need to consider multiple environmental exposures when assessing radon exposure’s association with lung cancer risk, thereby highlighting (1) the importance of an exposomics framework and (2) that employing ML models may capture the complex interplay between environmental exposures and health, as in the case of indoor radon exposure and lung cancer incidence.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗

Machine Learning of Plasma Science for Next Generation Microelectronics (Project Final Report)

Low temperature plasmas (LTPs) are an enabling technology behind reducing device dimensions and the continuation of Moore’s Law. It is estimated that 40-45% of all process steps necessary to manufacture semiconductor devices involve LTPs. However, challenges in plasma process design and continuous incorporation of novel materials for new device architectures are pushing the limits of what is possible with current plasma technology. For example, creating higher aspect ratio structures and etching features at the atomic scale both require finer control of the ion energy/velocity at wafer surfaces. To support these types of future innovations in the plasma processing systems that Sandia and the DOE rely upon, we have developed novel diagnostics, simulations, and machine learning capabilities to discover, characterize, and predict plasma phenomena affecting the ion energy/velocity distribution function (IEDF). These efforts also supported research program development and external collaboration with industry and academia through Sandia’s Plasma Research Facility (PRF). This report will focus on the following topics and accomplishments of this three year LDRD project, briefly summarized.

42 ENGINEERING↗

Neural Network Based Intrusion Detection System for Critical Infrastructures

Resiliency and security in control systems such as SCADA and Nuclear plant’s in today’s world of hackers and malware are a relevant concern. Computer systems used within critical infrastructures to control physical functions are not immune to the threat of cyber attacks and may be potentially vulnerable. Tailoring an intrusion detection system to the specifics of critical infrastructures can significantly improve the security of such systems. The IDS-NNM – Intrusion Detection System using Neural Network based Modeling, is presented in this paper. The main contributions of this work are: 1) the use and analyses of real network data (data recorded from an existing critical infrastructure); 2) the development of a specific window based feature extraction technique; 3) the construction of training dataset using randomly generated intrusion vectors; 4) the use of a combination of two neural network learning algorithms – the Error-Back Propagation and Levenberg-Marquardt, for normal behavior modeling. The presented algorithm was evaluated on previously unseen network data. The IDS-NNM algorithm proved to be capable of capturing all intrusion attempts presented in the network communication while not generating any false alerts.

97 MATHEMATICS AND COMPUTING↗

Automated experimental design of safe rampdowns via probabilistic machine learning

Abstract Typically the rampdown phase of a shot consists of a decrease in current and injected power and optionally a change in shape, but there is considerable flexibility in the rate, sequencing, and duration of these changes. On the next generation of tokamaks it is essential that this is done safely as the device could be damaged by the stored thermal and electromagnetic energy present in the plasma. This works presents a procedure for automatically choosing experimental rampdown designs to rapidly converge to an effective rampdown trajectory. This procedure uses probabilistic machine learning methods paired with acquisition functions taken from Bayesian optimization. In a set of 2022 experiments at DIII-D, the rampdown designs produced by our method maintained plasma control down to substantially lower current and energy levels than are typically observed. The actions predicted by the model significantly improved as the model was able to explore over the course of the experimental campaign.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Machine learning models of intermittent operation of RO wellhead water treatment for salinity reduction and nitrate removal

Machine learning models were developed for intermittent multi-mode operation of a wellhead reverse osmosis water purification and desalination system to predict salt passage, nitrate passage, and permeate flux. The models, based on long short-term memory (LSTM) recurrent neural network (RNN) architecture, included an attention mechanism to increase model performance in proximity of the regulatory limit for nitrate. Training and testing of the models for the Startup, Production, Shutdown and Flushing operational modes were based on operational data (consisting of 22 process variables per data sample) acquired every 2–5 s over a six-month period. The significant sets of model input attributes for the different operational modes were assessed via Spearman ranking correlation, Self-Organizing Map (SOM) analysis and feed forward feature selection (FFFS). Although the variability of nitrate passage, salt passage and permeate flux was significant over the four operational modes, prediction performance for the three outcomes were with R2 and Average Absolute Relative Error (AARE) of 0.78–0.95 and 2.96–6.16 %, respectively. Model updates post membrane elements replacement demonstrated similar levels of prediction accuracy. The study results suggest that there is merit in exploring the utility of multi-mode models for sensor fault detection, data imputation, and for potential use in model-predictive control.

Intermittent RO operation↗

Multi-Agent Reinforcement Learning for Distribution System Critical Load Restoration

Grid resilience has become a critical topic recently because of the increasing occurrence of extreme events and the growing integration of intermittent renewable energy sources. To build a resilient distribution system, this paper develops a multiagent reinforcement learning-based (MARL) method to coordinate distribution energy resources (DERs) dispatch, load pickup, and network reconfiguration for load restoration after a system outage. With the help of two types of control agents, namely critical load restoration (CLR) and coordination (COR) agents, system loads can be restored efficiently, given available resources. The effectiveness and superiority of the proposed algorithm are demonstrated through simulations and comparative studies on a real distribution feeder in Western Colorado.

distribution system↗

Multi-Agent Reinforcement Learning for Distribution System Critical Load Restoration: Preprint

Grid resilience has become a critical topic recently because of the increasing occurrence of extreme events and the growing integration of intermittent renewable energy sources. To build a resilient distribution system, this paper develops a multi-agent reinforcement learning-based (MARL) method to coordinate distribution energy resources (DERs) dispatch, load pickup, and network reconfiguration for load restoration after a system outage. With the help of two types of control agents, namely critical load restoration (CLR) and coordination (COR) agents, system loads can be restored efficiently, given available resources. The effectiveness and superiority of the proposed algorithm are demonstrated through simulations and comparative studies on a real distribution feeder in Western Colorado.

distribution system↗

A Q-Learning-Based Approach for Distributed Beam Scheduling in mmWave Networks

We consider the problem of distributed downlink beam scheduling and power allocation for millimeter-Wave (mmWave) cellular networks where multiple base stations (BSs) belonging to different service operators share the same unlicensed spectrum with no centralized control or explicit coordination among them. Our goal is to design efficient distributed beam scheduling and power allocation schemes such that the network-level payoff, defined as the weighted sum of the total throughput and a power penalization term, can be maximized. To this end, we propose a distributed scheduling approach to power allocation and adaptation for efficient interference management over the shared spectrum by modeling each BS as an independent Q-learning agent. As a baseline, we compare the proposed approach to the state-of-the-art non-cooperative game-based approach which was previously developed for the same problem. We conduct extensive experiments under various scenarios to verify the effect of multiple factors on the performance of both approaches. Experiment results show that the proposed approach adapts well to different interference conditions by learning from experience and thus can achieve higher payoff than the game-based approach. The proposed approach can also be integrated into our previously developed Lyapunov stochastic optimization framework for the purpose of network utility maximization with optimality guarantee. As a result, the weights in the payoff function can be automatically and optimally determined by the virtual queue values from the sub-problems derived from the Lyapunov optimization framework.

99 GENERAL AND MISCELLANEOUS↗

Modeling Subsurface Performance of a Geothermal Reservoir Using Machine Learning

Geothermal power plants typically show decreasing heat and power production rates over time. Mitigation strategies include optimizing the management of existing wells—increasing or decreasing the fluid flow rates across the wells—and drilling new wells at appropriate locations. The latter is expensive, time-consuming, and subject to many engineering constraints, but the former is a viable mechanism for periodic adjustment of the available fluid allocations. In this study, we describe a new approach combining reservoir modeling and machine learning to produce models that enable such a strategy. Our computational approach allows us, first, to translate sets of potential flow rates for the active wells into reservoir-wide estimates of produced energy, and second, to find optimal flow allocations among the studied sets. In our computational experiments, we utilize collections of simulations for a specific reservoir (which capture subsurface characterization and realize history matching) along with machine learning models that predict temperature and pressure timeseries for production wells. We evaluate this approach using an “open-source” reservoir we have constructed that captures many of the characteristics of Brady Hot Springs, a commercially operational geothermal field in Nevada, USA. Selected results from a reservoir model of Brady Hot Springs itself are presented to show successful application to an existing system. In both cases, energy predictions prove to be highly accurate: all observed prediction errors do not exceed 3.68% for temperatures and 4.75% for pressures. In a cumulative energy estimation, we observe prediction errors that are less than 4.04%. A typical reservoir simulation for Brady Hot Springs completes in approximately 4 h, whereas our machine learning models yield accurate 20-year predictions for temperatures, pressures, and produced energy in 0.9 s. This paper aims to demonstrate how the models and techniques from our study can be applied to achieve rapid exploration of controlled parameters and optimization of other geothermal reservoirs.

15 GEOTHERMAL ENERGY↗

Generative Adversarial Network based Autoencoder: Application to fault detection problem for closed loop dynamical systems

Fault detection problem for closed loop uncertain dynamical systems, is investigated in this paper, using different deep learning based methods. Traditional classifier based method does not perform well, because of the inherent difficulty of detecting system level faults for closed loop dynamical system. Specifically, acting controller in any closed loop dynamical system, works to reduce the effect of system level faults. A novel Generative Adversarial based deep Autoencoder is designed to classify datasets under normal and faulty operating conditions. This proposed network performs significantly well when compared to any available classifier based methods, and moreover, does not require labeled fault incorporated datasets for training purpose. Finally, this aforementioned network's performance is tested on a high complexity building energy system dataset.

deep learning, Active fault detection↗

Investigation of the selective sites on graphitic carbons for oxidative dehydrogenation of isobutane

Reaction network analysis of the oxidative dehydrogenation (ODH) reaction of isobutane over model carbon catalysts with tailored open-edge graphitic structure and uniform oxygenated functionalities was used to identify the selective pathways for the formation of isobutene. Carbon-based materials have been widely used in catalysis, but the active sites are not well-understood due to the complexity of the carbon structure. Correct identification of these sites is essential for learning how to manipulate material structure to achieve high catalytic yields of the desired products. In this study, we created model catalysts with controllable surface concentration of oxygenated functionalities based on graphitized mesoporous carbon (GMC). The concentration of the oxygenated functional groups on the surface of the GMCs was varied in a continuous manner through a simply control of the burn-off level. Our studies reveal that the ODH reaction of isobutane on carbon catalysts is a parallel-consecutive pathway with partial oxidative dehydrogenation for the formation of isobutene and deep oxidation pathway for the direct formation of CO and CO2 from isobutane. These two pathways show different dependence on the quinone-type oxygen sites: the rate constant leading to the desired partial oxidation product does not show a strong correlation to the density of oxygen sites, whereas the rate constant leading to the unselective COx products increases continuously with the density of oxygen sites. These results may give insight on the rational design of carbon catalysts for ODH reactions with desirable properties.

2-METHYLPROPANE↗

On decomposition, degradation, and voltammetric deviation: the electrochemist's field guide to identifying precatalyst transformation

What is the identity of the true electrocatalytic species? This basic question has plagued the molecular electrocatalysis community during its decades-long search for selective and efficient transition-metal based electrocatalysts for fuel forming reactions. Identifying when the added species is a precatalyst that transforms into the active catalyst in situ is an extraordinarily complex endeavor. Thankfully, the last decade has witnessed a resurgence of interest in understanding and controlling these transformations, leading to an expansion of the experimental toolkit available to probe catalyst identity. Here in this Tutorial Review, researchers will learn how the nature of the active catalyst can be uncovered using state-of-the-art electrochemical and spectroscopic methods. Analysis of catalytic voltammograms can quickly furnish qualitative evidence of precatalyst transformation and a library of these tell-tale signs is discussed, along with the chemical phenomena underpinning each feature. Complementary electrochemical and spectroscopic methods for identifying in situ generation of heterogeneous catalysts are also presented, outlining the conditions required for correct application with special emphasis on potential pitfalls when studying weakly-adsorbed material. Case studies are presented to showcase how these different probes can be integrated to develop a comprehensive picture of precatalyst transformation.

08 HYDROGEN↗

Harnessing the power of gradient-based simulations for multi-objective optimization in particle accelerators

Abstract Particle accelerator operation requires simultaneous optimization of multiple objectives. Multi-objective optimization (MOO) is particularly challenging due to trade-offs between the objectives. Evolutionary algorithms, such as genetic algorithms (GAs), have been leveraged for many optimization problems, however, they do not apply to complex control problems by design. This paper demonstrates the power of differentiability for solving MOO problems in particle accelerators using a deep differentiable reinforcement learning (DDRL) algorithm. We compare the DDRL algorithm with model-free reinforcement learning (MFRL), GA, and Bayesian optimization (BO) for simultaneous optimization of heat load and trip rates in the continuous electron beam accelerator facility. The underlying problem enforces strict constraints on both individual states and actions as well as cumulative (global) constraints on energy requirements of the beam. Using historical accelerator data, we develop a physics-based surrogate model which is differentiable and allows for back-propagation of gradients. The results are evaluated in the form of a Pareto-front with two objectives. We show that the DDRL outperforms MFRL, BO, and GA on high dimensional problems.

43 PARTICLE ACCELERATORS↗