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 1,189 records · Page 66

Lessons Learned on Benchmarking from the International Human Reliability Analysis Empirical Study

The International Human Reliability Analysis (HRA) Empirical Study is a comparative benchmark of the prediction of HRA methods to the performance of nuclear power plant crews in a control room simulator. There are a number of unique aspects to the present study that distinguish it from previous HRA benchmarks, most notably the emphasis on a method-to-data comparison instead of a method-to-method comparison. This paper reviews seven lessons learned about HRA benchmarking from conducting the study: (1) the dual purposes of the study afforded by joining another HRA study; (2) the importance of comparing not only quantitative but also qualitative aspects of HRA; (3) consideration of both negative and positive drivers on crew performance; (4) a relatively large sample size of crews; (5) the use of multiple methods and scenarios to provide a well-rounded view of HRA performance; (6) the importance of clearly defined human failure events; and (7) the use of a common comparison language to “translate” the results of different HRA methods. These seven lessons learned highlight how the present study can serve as a useful template for future benchmarking studies.

99 GENERAL AND MISCELLANEOUS↗

SSD-optimized workload placement with adaptive learning and classification in HPC environments

In recent years, non-volatile memory devices such as SSD drives have emerged as a viable storage solution due to their increasing capacity and decreasing cost. Due to the unique capability and capacity requirements in large scale HPC (High Performance Computing) storage environment, a hybrid configuration (SSD and HDD) may represent one of the most available and balanced solutions considering the cost and performance. Under this setting, effective data placement as well as movement with controlled overhead become a pressing challenge. In this paper, we propose an integrated object placement and movement framework and adaptive learning algorithms to address these issues. Specifically, we present a method that shuffle data objects across storage tiers to optimize the data access performance. The method also integrates an adaptive learning algorithm where realtime classification is employed to predict the popularity of data object accesses, so that they can be placed on, or migrate between SSD or HDD drives in the most efficient manner. We discuss preliminary results based on this approach using a simulator we developed to show that the proposed methods can dynamically adapt storage placements and access pattern as workloads evolve to achieve the best system level performance such as throughput.

Wan, Lipeng↗

Development and assessment of prognosis digital twin in a NAMAC system

The nearly autonomous management and control (NAMAC) system is a comprehensive control system to assist plant operations by furnishing control recommendations to operators. Prognosis digital twin (DT-P) is a critical component in NAMAC for predicting action effects and supporting NAMAC decision-making during normal and accident scenarios. To quantifying and reducing uncertainty of machine-learning-based DT-Ps in multi-step predictions, this work investigates and derives insights from the application of three techniques for optimizing the performance of DT-P by long short-term memory recurrent neural networks, including manual search, sequential model-based optimization, and physics-guided machine learning. Finally, sequential model-based optimization and physics-guide machine learning result in smallest errors when the predicting transients are similar to the training data.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

Fused Sensor Analysis and Advanced Control of Industrial Field Devices for Security: Cymbiote Multi-Source Sensor Fusion Platform

Embedded field devices that sense and control physical processes in critical infrastructure are soft targets for cyber-attack because they lack the fundamental features for existing cyber security monitoring and control. In this paper we present a new platform to collect and fuse data across multiple cyber and physical streams from these field devices to enable the host based attack detection and security control capabilities that have become common within IT environments. Experiments of different attack behaviors are discussed and initial machine learning detection approach analysis is presented.

Data fusion, Fied Control Device, Cyber Security, ↗

The Second Skin: A Wearable Sensor Suite that Enables Real-Time Human Biomechanics Tracking Through Deep Learning

Objective: Real-time determination of human kinematics and kinetics could advance biomechanics research and enable valuable applications of biofeedback and generalizable exoskeleton control. Here, this work aims to investigate a taskindependent, user-independent method for obtaining precise realtime joint state estimation across lower-body joints during a wide variety of tasks. Methods: We developed a generalizable sensing approach using a suit comprised of inertial measurement units (IMUs) and pressure insoles. With the suit, we collected a dataset of 33 tasks commonly performed during construction and hazardous waste cleanup (N = 10). We then trained deep learning user-independent, task-agnostic models to estimate joint lowerbody kinematics and dynamics using only worn sensor data. We likewise computed joint kinematics and dynamics analytically from sensor data to serve as a comparison tool for model results. Results: Our models achieved overall angle estimation root-meansquared-errors (RMSE) of 6.56±.92°, 8.60±1.01°, 7.58±.89°, and 6.00±.73° compared to 13.9±.1.3°, 15.31±1.0°, 10.76±.70°, and 7.56±.48° via analytical methods at the lower back, hip, knee, and ankle, respectively. Likewise, our models achieved overall normalized moment estimation RMSEs of .207±.069 Nm/kg, .242±.044 Nm/kg, .202±.038 Nm/kg, and .193±.034 Nm/kg compared to .306±.036 Nm/kg, .407±.021 Nm/kg, 1.18 ±.022 Nm/kg, and 1.73±.071 Nm/kg via analytical methods at the lower back, hip, knee, and ankle, respectively. Conclusion: These results are comparable to other state-of-the-art wearable sensing systems, establishing deep learning as a viable sensing approach that generalizes to new users and tasks. Significance: This work shows promise for enabling accurate real-world biomechanical data collection and enhancement of biofeedback systems and wearable robot control.

Casey, Ryan T. F. [Georgia Institute of Technology↗

Predicting lake surface water phosphorus dynamics using process-guided machine learning

Phosphorus (P) loading to lakes is degrading the quality and usability of water globally. Accurate predictions of lake P dynamics are needed to understand whole-ecosystem P budgets, as well as the consequences of changing lake P concentrations for water quality. However, complex biophysical processes within lakes, along with limited observational data, challenge our capacity to reproduce short-term lake dynamics needed for water quality predictions, as well as long-term dynamics needed to understand broad scale controls over lake P. Here we use an emerging paradigm in modeling, process-guided machine learning (PGML), to produce a phosphorus budget for Lake Mendota (Wisconsin, USA) and to accurately predict epilimnetic phosphorus over a time range of days to decades. In our implementation of PGML, which we term a Process-Guided Recurrent Neural Network (PGRNN), we combine a process-based model for lake P with a recurrent neural network, and then constrain the predictions with ecological principles. We test independently the process-based model, the recurrent neural network, and the PGRNN to evaluate the overall approach. The process-based model accounted for most of the observed pattern in lake P; however it missed the long-term trend in lake P and had the worst performance in predicting winter and summer P in surface waters. The root mean square error (RMSE) for the process-based model, the recurrent neural network, and the PGRNN was 33.0 μg P L -1 , 22.7 μg P L -1 , and 20.7 μg P L -1 , respectively. All models performed better during summer, with RMSE values for the three models (same order) equal to 14.3 μg P L -1 , 10.9 μg P L -1 , and 10.7 μg P L -1 . Although the PGRNN had only marginally better RMSE during summer, it had lower bias and reproduced long-term decreases in lake P missed by the other two models. For all seasons and all years, the recurrent neural network had better predictions than process alone, with root mean square error (RMSE) of 23.8 μg P L -1 and 28.0 μg P L -1 , respectively. The output of PGRNN indicated that new processes related to water temperature, thermal stratification, and long term changes in external loads are needed to improve the process model. By using ecological knowledge, as well as the information content of complex data, PGML shows promise as a technique for accurate prediction in messy, real-world ecological dynamics, while providing valuable information that can improve our understanding of process.

54 ENVIRONMENTAL SCIENCES↗

U.S. Nuclear Regulatory Commission Historical Perspectives of Very Low-Level Radioactive Waste - 18367

The United States Nuclear Regulatory Commission (NRC), in Title 10 of the Code of Federal Regulations Part 61 (10 CFR Part 61), 'Licensing Requirements for Land Disposal of Radioactive Waste', provides licensing procedures, performance objectives, and technical requirements for the issuance of licenses for the land disposal of low-level radioactive waste. Low-level radioactive waste is divided into four categories based on its potential risk and need for isolation. Class A is the lowest category of low-level radioactive waste and poses the least risk. A large percentage of Class A low-level waste contains very low radionuclide concentrations and does not pose a significant health and safety risk. In the current regulatory framework, this waste, referred to as low-activity or very low-level waste, is managed in the same manner as much more hazardous waste. In 1986 and 1990, as a result of the Low-Level Radioactive Waste Policy Amendments Act of 1985, the NRC issued the Below Regulatory Concern (BRC) policy statement. This policy statement established an implementation plan regarding the expeditious handling of rulemaking petitions 'to exempt specific radioactive waste streams from regulation due to the presence of radionuclides in sufficiently low concentrations or quantities as to be below regulatory concern.' The BRC policy statement provided a consistent risk framework when considering regulatory exemption decisions, such as: (1) the release for unrestricted public use of lands and structures containing residual radioactivity; (2) the distribution of consumer products containing small amounts of radioactive material; (3) the disposal of very low-level radioactive waste at other than licensed disposal sites; and (4) the recycling of slightly contaminated equipment and materials. Due to concerns with the BRC policy that were raised by Congress, the States, the public, and others, Congress enacted the Energy Policy Act of 1992, which revoked the NRC's 1986 and 1990 BRC policy statements and led to the NRC's formal withdrawal of the BRC policy in 1993. Stakeholders raised concerns on NRC's potential deregulation of radioactive material. Additionally, in March 2005, the NRC staff proposed a rule to amend 10 CFR Part 20, 'Standards for Protection Against Radiation,' to include radiological criteria for controlling the disposition of solid materials with very small amounts of residual radioactivity. The NRC staff also proposed a limited disposition approach for the disposition of solid material, limiting the release of solid material meeting a 0.01 milli-Sievert per year (mSv/yr) [1 milli-rem (mrem/yr)] dose criterion, from licensed control. In June 2005, the Commission disapproved publication of the proposed rule and deferred the rulemaking until a later time, stating that the NRC's existing approach of reviewing specific cases on an individual basis was fully protective of public health and safety. This rulemaking effort was discontinued by the Commission in 2016. Recently, several nuclear power plant licensees have announced early decommissioning of their facilities. Some stakeholders have expressed concerns about the capacity and disposal costs associated with using the four existing low-level waste disposal sites for very low levels of radioactive waste (i.e., waste at the low end of the Class A category). A more risk-informed, performance based approach to waste disposal would allow more flexibility in managing this waste commensurate with its risk and hazard. A new approach would also allow the NRC to align with international standards for this type of waste. The NRC is presently conducting a scoping study to identify the actions the agency should take to strengthen its regulatory framework for very low-level waste disposal. The Very Low-Level Waste (VLLW) scoping study will consider divergent stakeholder comments; lessons learned from the BRC policy statements and the proposed rule on radiological criteria for controlling the disposition of solid materials; and best practices of other countries with respect to VLLW disposal. The NRC will also engage other government agencies to discuss regulatory options for VLLW. This paper offers a historical overview of past NRC initiatives to manage the lower end of Class A waste in a manner that is risk informed and performance based. It examines previous endeavors and discusses the regulatory challenges that arose. It also addresses lessons learned and introduces NRC's current effort regarding very low-level radioactive waste disposal. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Emerging Technologies for Improved Plug Load Management Systems: Learning Behavior Algorithms and Automatic and Dynamic Load Detection

Plug loads are responsible for a significant portion of the energy consumed in commercial buildings, yet their distributed and ever-changing nature makes them one of the most challenging building end uses to manage. Plug load management systems exist today that utilize smart plugs to meter and control devices at the outlet level, however, their uptake has been relatively slow in part due to the significant labor required for installation and maintenance. Learning behavior algorithms and automatic and dynamic load detection have been identified as two technology areas that could accelerate the adoption of plug load management systems by reducing these labor demands and providing additional energy efficiency and non-energy benefits. Learning behavior algorithms learn occupant behavior and adjust plug load management systems accordingly, allowing for the automatic creation of optimized control schedules. Automatic and dynamic load detection allows a plug load management system to identify devices as they are plugged in to a building and keeps the system up to date as devices are moved throughout a building. In this paper, we present our findings with respect to the current state of these two technologies based on a review of existing research and patents, as well as a series of interviews with companies working in the plug load space. We have found that, as of now, no commercialized solutions exist for these plug load technologies and that more work is needed to bring them to market. In addition, we summarize our findings related to the technology challenges, market barriers, drivers, and opportunities for these technologies moving forward.

30 DIRECT ENERGY CONVERSION↗

Tuning water dissociation at oxide–electrolyte interfaces with electric fields

Understanding how electric fields influence water dissociation at heterogeneous interfaces is crucial for controlling interfacial chemical reactions and advancing next-generation energy technologies. Herein, ab initio–based machine learning simulations show that even small electric field changes can significantly alter the water dissociation fraction at planar TiO 2 –electrolyte interfaces. The resulting free energy difference between undissociated and dissociated interfacial water exhibits a linear dependence on the field change with a slope of 1.97 eÅ, which far exceeds the dissociation-induced dipole change of a water molecule. Employing a machine-learned collective variable to investigate the reaction statistics of thousands of water dissociation/recombination events, we find that small electric field changes exert minor effects on individual reaction energy barriers but significantly influence the populations of local configurations associated with initial states that are most favorable for reactions. These findings elucidate the pronounced impact of electric fields on interfacial water dissociation and reveal a mechanism for electric-field-controlled chemical reactions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

PHYSICAL FIDELITY CONSIDERATIONS FOR NRC ADVANCED REACTOR CONTROL ROOM TRAINING SIMULATORS USED FOR INSPECTOR/EXAMINER TRAINING

This paper describes research into the physical fidelity requirements of control room simulators to train U.S. Nuclear Regulatory Commission (NRC) staff for their duties as inspectors and license examiners for next-generation nuclear power plants. The control rooms of these power plants are expected to utilize digital instrumentation and controls to a much greater extent than do current plants. The NRC is assessing training facility needs, particularly for control room simulators, which play a central role in NRC training. Simulator fidelity affects both training effectiveness and cost. Research has shown high simulation fidelity sometimes positively affects transfer to the operational environment but sometimes makes no significant difference or actually impedes learning. The conditions in which these different effects occur are often unclear, especially for regulators (as opposed to operators) about whom research is particularly sparse. This project developed an inventory of the tasks and knowledges, skills, and abilities that NRC regulators need to fulfill job duties and used expert panels to characterize the inventory items by type and level of cognitive/behavioral capability needed, difficulty to perform, importance to safety, frequency of performance, and the importance of simulator training for learning these capabilities. A survey of current NRC staff provides information about the physical fidelity of the simulator on which the student trained to the control room to which the student was assigned and the effect lack of fidelity had on learning and job performance. The study concludes that a high level of physical fidelity is not required for effective training of NRC staff.

man-machine interface↗

Memristors learn to play

A hybrid analogue–digital computing system built upon memristive devices is capable of solving classic control problems with potentially a lower energy consumption and higher speed than fully digital systems.

97 MATHEMATICS AND COMPUTING↗

A Machine Learning-Based Method to Estimate Transformer Primary-Side Voltages with Limited Customer-Side AMI Measurements

Distribution control applications such as volt/var optimization, network reconfiguration, and distribution automation require accurate knowledge of the distribution system state. The lack of sufficient sensors on the primary side of distribution networks often limits the accuracy of the control decisions by these applications. The deployment of advanced metering infrastructure (AMI) provides utilities an opportunity to translate the AMI data on the secondary onto the primary so that it can be used as pseudo-measurements to augment the limited existing measurements on the primary. This paper develops an approach for estimating service transformer primary-side voltages by using limited secondary-side AMI measurements. The estimated primary-side voltages can be used by utilities as pseudo-measurements for distribution control applications. The detailed secondary model topology, which is an essential input data for many existing algorithms, is not required for the proposed method. The performance of the proposed method is validated by using AMI measurements from the field and an actual distribution feeder model of San Diego Gas & Electric Company.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

Synaptic potentiation onto habenula neurons in the learned helplessness model of depression

The cellular basis of depressive disorders is poorly understood. Recent studies in monkeys indicate that neurons in the lateral habenula (LHb), a nucleus that mediates communication between forebrain and midbrain structures, can increase their activity when an animal fails to receive an expected positive reward or receives a stimulus that predicts aversive conditions (that is, disappointment or anticipation of a negative outcome). LHb neurons project to, and modulate, dopamine-rich regions, such as the ventral tegmental area (VTA), that control reward-seeking behaviour and participate in depressive disorders. Here we show that in two learned helplessness models of depression, excitatory synapses onto LHb neurons projecting to the VTA are potentiated. Synaptic potentiation correlates with an animal's helplessness behaviour and is due to an enhanced presynaptic release probability. Depleting transmitter release by repeated electrical stimulation of LHb afferents, using a protocol that can be effective for patients who are depressed, markedly suppresses synaptic drive onto VTA-projecting LHb neurons in brain slices and can significantly reduce learned helplessness behaviour in rats. Our results indicate that increased presynaptic action onto LHb neurons contributes to the rodent learned helplessness model of depression.

38 RADIATION CHEMISTRY, RADIOCHEMISTRY, AND NUCLEA↗

Anomaly Detection, Localization and Classification using Drifting Synchrophasor Data Streams

With ongoing automation and digitization of the electric power system, several Phasor Measurement Units(PMUs) have been deployed for monitoring and control. PMU data can have multiple anomalies, and many of the researchers in the past have concentrated on training machine/deep learning algorithms offline for anomaly detection over PMU data (i.e., not in real time). These machine/deep learning algorithms, when trained offline on a sample rather than a population of the dataset, fail to consider the dynamic behavior of the power grid in real-time, resulting in low accuracy. Considering the dynamic behavior of the power grid (e.g., change in load, generation, distributed energy resources (DERs) switching, network, controls), the definition of data anomalies varies in time and requires online training. A fundamental challenge is to enable online (i.e., real-time) training of machine/deep learning algorithms for anomaly detection over streaming PMU data. While machine/deep learning is often desirable to manage data streams, training a deep learning algorithm over streaming PMU data is nontrivial due to changes in data statistics caused by dynamic streaming data. This paper proposes PMUNET: a novel device-level deep learning-based data-driven approach for anomaly detection, localization, and classification over streaming PMU data, using online learning and multivariate data-drift detection algorithm .Two variants of PMUNET, Dynamic data Change Driven Learning (DCDL) and Continuity Driven Learning (CDL), are proposed and compared. DCDL aims to train the deep learning algorithm whenever the definition of anomaly changes due to the power grid dynamics. On the other hand, CDL continuously trains the deep learning algorithm over the PMU data-stream. The experimental results verify that DCDL outperforms CDL and other efficient anomaly detection methods over multiple events such as faults and load/ generator/capacitor/DERs variations/switching for IEEE 14 and 39 Bus test system as well as real PMU industrial data. The result verifies that DCDL variant of PMUNET improves over existing approach with a gain of 2% - 10% in terms of accuracy, false-positive rate, and false-negative rate.

adversarial deep learning↗

Layer-Parallel Training of Deep Residual Neural Networks

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be interpreted as forward Euler discretizations of a nonlinear initial value problem whose time-dependent control variables represent the weights of the neural network. Hence, training a ResNet can be cast as an optimal control problem of the associated dynamical system. For similar time-dependent optimal control problems arising in engineering applications, parallel-in-time methods have shown notable improvements in scalability. This paper demonstrates the use of those techniques for efficient and effective training of ResNets. The proposed algorithms replace the classical (sequential) forward and backward propagation through the network layers with a parallel nonlinear multigrid iteration applied to the layer domain. This adds a new dimension of parallelism across layers that is attractive when training very deep networks. From this basic idea, we derive multiple layer-parallel methods. The most efficient version employs a simultaneous optimization approach where updates to the network parameters are based on inexact gradient information in order to speed up the training process. Finally, using numerical examples from supervised classification, we demonstrate that the new approach achieves a training performance similar to that of traditional methods, but enables layer-parallelism and thus provides speedup over layer-serial methods through greater concurrency.

97 MATHEMATICS AND COMPUTING↗

Building thermal model development of typical house in U.S. for virtual storage control of aggregated building loads based on limited available information

A building thermal model is an essential component for achieving optimal control of a building’s heating, ventilation, and air conditioning (HVAC). A self-learning grey-box model has been developed by implementing data-driven techniques and utilizing limited available information about the building. In previous research, detailed foreknown knowledge/information, e.g. physical and thermal properties of building materials, as well as sufficient number of observation points, e.g. indoor temperature sensors in different zones, are available for making the decision of model structure and parameters searching range easier. The availability of measured data and a narrowed searching range of model parameters, e.g. resistance and capacity for each wall, made the adopted algorithms quickly achieve near optimal values, which closely approximate the actual heat transfer of a building. Meanwhile, the details of pre-processing of the key inputs were seldom explained. Compared to the previous research, in this study, the available information is assumed to be limited which can fill the requirement for large scale virtual storage control of real residential community in near future, where it may be impractically or over time-consuming to acquire the detailed information for each single house. The developed model is validated by comparing the results to measured data in a recently-built home typical of the southeastern United States.

Cui, Borui↗