Search NASA⌕ Search

SEARCH · Search NASA

Results for “adaptive learning”

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 757 records · Page 42

Tuning Phase Lock Loop Controller of Grid Following Inverters by Reinforcement Learning to Support Networked Microgrid Operations

The dynamic operation of networked microgrids leads to varying topological configurations and generator commitments and dispatches. These variations correspond to systems with different electrical characteristics. The fixed control gains of high-speed power electronic devices may result in undesirable system performance when the electrical characteristics change significantly. As such, it is necessary to tune the control gains of power electronics devices to adapt to the changing system characteristics. This paper uses observer-based reinforcement learning to automatically tune the proportional-integral (PI) gains of phase lock loop (PLL) controller of grid-following (GFL) inverters to adapt to the changing system strengths, that would be seen in networked microgrid operations. Simulation results using an operational electric distribution system, modeled as networked microgrids, are presented to demonstrate the need and effectiveness of the proposed adaptive controls.

networked microgrids, reinforcement learning, grid↗

Domain Aware Deep-learning Algorithms Integrated with Scientific-computing Technologies (DADAIST)

This technical report summarized the contribution of the DADAIST project funded by the Data Model Convergence Initiative via the Laboratory Directed Research and Development (LDRD) investments at Pacific Northwest National Laboratory (PNNL). Specifically, we report the development of the NeuroMANCER (Neural Modules with Adaptive Nonlinear Constraints and Efficient Regularizations), a new open-source Scientific Machine Learning library for formulating and solving parametric constrained optimization problems, physics-informed system identification, and parametric optimal control problems. NeuroMANCER is using differentiable programming to combine modern data-driven models and optimization modeling language into a coherent algorithmic and software framework. NeuroMANCER is a Pytorch-based framework and adopts much of its philosophy focused on research and development, rapid prototyping, and streamlined deployment. Strong emphasis is given to extensibility, interoperability with the PyTorch ecosystem, and quick adaptability to custom domain problems. Neuromancer repository contains a comprehensive library of differentiable modules, including custom activation functions, matrix factorizations, deep learning architectures, neural differential equations, differential equation solvers, implicit layers such as iterative solvers, high-level API for symbolic expressions, API for modeling and control of dynamical systems, and extensive set of tutorial code examples in the form of python scripts and jupyter notebooks.

97 MATHEMATICS AND COMPUTING↗

Recent developments in learning control and system identification for robots and structures

This paper reviews recent results in learning control and learning system identification, with particular emphasis on discrete-time formulation, and their relation to adaptive theory. Related continuous-time results are also discussed. Among the topics presented are proportional, derivative, and integral learning controllers, time-domain formulation of discrete learning algorithms. Newly developed techniques are described including the concept of the repetition domain, and the repetition domain formulation of learning control by linear feedback, model reference learning control, indirect learning control with parameter estimation, as well as related basic concepts, recursive and non-recursive methods for learning identification.

Phan, M.↗

Automated Threat Recognition For Aviation Security Applications

We have developed a framework for automated threat recognition (ATR) of explosive threat materials for both single-energy and dual-energy X-ray CT systems. Under this framework, two different types of ATR have been developed. The first type of ATR employs supervised machine learning with statistical characterization of target materials for threat identification training. The reliance only on statistical characterization information for threat training uniquely enables this style of ATR to adapt quickly to evolving threats. The second type of ATR employs deep learning through convolutional neural networks. Convolutional neural networks are attractive due to their human-like capacity for learning and strong ability to identify trends and patterns. Although this method is more powerful than the first type, it requires large amounts of training data and therefore is less agile. Each ATR performs threat characterization at the voxel neighborhood level. This approach avoids the use of threat shape as a detection criterion, which is prohibited by DHS and TSA guidelines.

97 MATHEMATICS AND COMPUTING↗

Energy flow networks: deep sets for particle jets

A key question for machine learning approaches in particle physics is how to best represent and learn from collider events. As an event is intrinsically a variable-length unordered set of particles, we build upon recent machine learning efforts to learn directly from sets of features or “point clouds”. Adapting and specializing the “Deep Sets” framework to particle physics, we introduce Energy Flow Networks, which respect infrared and collinear safety by construction. We also develop Particle Flow Networks, which allow for general energy dependence and the inclusion of additional particle-level information such as charge and flavor. These networks feature a per-particle internal (latent) representation, and summing over all particles yields an overall event-level latent representation. We show how this latent space decomposition unifies existing event representations based on detector images and radiation moments. To demonstrate the power and simplicity of this set-based approach, we apply these networks to the collider task of discriminating quark jets from gluon jets, finding similar or improved performance compared to existing methods. We also show how the learned event representation can be directly visualized, providing insight into the inner workings of the model. These architectures lend themselves to efficiently processing and analyzing events for a wide variety of tasks at the Large Hadron Collider. Implementations and examples of our architectures are available online in our EnergyFlow package.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

PCOR Partnership Best Practices Manual for Subsurface Technical Risk Assessment of Geologic CO 2 Storage Projects

In 2003, the U.S. Department of Energy established the Regional Carbon Sequestration Partnerships (RCSP) Initiative to help develop technology, infrastructure, and regulations needed to facilitate large-scale carbon dioxide (CO 2 ) geologic storage (herein “storage”) and support deployment of commercial carbon capture and storage projects. The Plains CO 2 Reduction (PCOR) Partnership, led by the Energy & Environmental Research Center (EERC), is one of seven partnerships created by this program. The PCOR Partnership is publishing a series of best practices manuals for each of the four PCOR Partnership-defined primary technical elements of a storage site: site characterization; modeling and simulation; risk assessment; and monitoring, verification, and accounting. This document describes the risk assessment process for evaluating subsurface technical risks associated with a CO 2 storage project. This best practices manual identifies the key elements comprising a risk assessment for a CO 2 storage complex and defines important risk management terminology and technical factors that are unique to the geologic storage of CO 2 . It also provides best practices for implementing a risk assessment based on lessons learned from conducting risk assessments for storage complexes within the PCOR Partnership region. Case studies of these real-world examples, which highlight key aspects of applying the risk assessment process to storage projects, are provided to support the proposed best practices. The development of a best practice requires the execution of multiple projects where the knowledge gained and lessons learned are accumulated over time and integrated to yield a best practice. This development progression is an adaptive management process whereby best practices constantly evolve over time in response to knowledge gained and lessons learned. This document encompasses the current body-of-knowledge and best practices for applying a standardized risk assessment approach within risk management for storage projects. Application of these best practices will provide reliable and consistent standards for identifying project-related risks, analyzing the probabilities and potential impacts of these risks, evaluating which risks require treatment, and determining priority for treatment implementation. These best practices will continue to evolve and be refined over time as commercialization of the CO 2 storage industry proceeds.

54 ENVIRONMENTAL SCIENCES↗

TU-C-BRE-07: Quantifying the Clinical Impact of VMAT Delivery Errors Relative to Prior Patients’ Plans and Adjusted for Anatomical Differences

Purpose: There is increased interest in the Radiation Oncology Physics community regarding sensitivity of pre-treatment IMRT/VMAT QA to delivery errors. Consequently, tools mapping pre-treatment QA to the patient DVH have been developed. However, the quantity of plan degradation that is acceptable remains uncertain. Using DVHs adapted from prior patients’ plans, we developed a technique to determine the magnitude of various delivery errors required to degrade a treatment plan to outside the clinically accepted range. Methods: DVHs for relevant organs at risk were adapted from a population of prior patients’ plans using a machine learning algorithm to establish the clinically acceptable DVH range specific to the patient’s anatomy. We applied this technique to six low-risk prostate cancer patients treated with single-arc VMAT and compared error-induced DVH changes to the adapted DVHs to determine the magnitude of error required to push the plan outside of the acceptable range. The procedure follows: (1) Errors (systematic ' random shift of MLCs, gantry-MLC desynchronization, dose rate fluctuations, etc.) were simulated and degraded DVHs calculated using the Varian Eclipse TPS. (2) Adapted DVHs and acceptable ranges for DVHs were established. (3) Relevant dosimetric indices and corresponding acceptable ranges were calculated from the DVHs. Key indices included NTCP (Lyman-Kutcher-Burman Model) and QUANTEC’s dose-volume Objectives: s of V75Gy≤0.15 for the rectum and V75Gy≤0.25 for the bladder. Results: Degradations to the clinical plan became “unacceptable” for 19±29mm and 1.9±2.0mm systematic outward shifts of a single leaf and leaf bank, respectively. All other simulated errors fell within the acceptable range. Conclusion: Utilizing machine learning and prior patients’ plans one can predict a clinically acceptable range of DVH degradation for a specific patient. Comparing error-induced DVH degradations to this range, it is shown that single-arc VMAT plans for low-risk prostate are relatively insensitive to many potential delivery errors.

60 APPLIED LIFE SCIENCES↗

The Importance of Being Adaptable: An Exploration of the Power and Limitations of Domain Adaptation for Simulation-Based Inference with Galaxy Clusters

The application of deep machine learning methods in astronomy has exploded in the last decade, with new models showing remarkably improved performance on benchmark tasks. Not nearly enough attention is given to understanding the models' robustness, especially when the test data are systematically different from the training data, or "out of domain." Domain shift poses a significant challenge for simulation-based inference, where models are trained on simulated data but applied to real observational data. In this paper, we explore domain shift and test domain adaptation methods for a specific scientific case: simulation-based inference for estimating galaxy cluster masses from X-ray profiles. We build datasets to mimic simulation-based inference: a training set from the Magneticum simulation, a scatter-augmented training set to capture uncertainties in scaling relations, and a test set derived from the IllustrisTNG simulation. We demonstrate that the Test Set is out of domain in subtle ways that would be difficult to detect without careful analysis. We apply three deep learning methods: a standard neural network (NN), a neural network trained on the scatter-augmented input catalogs, and a Deep Reconstruction-Regression Network (DRRN), a semi-supervised deep model engineered to address domain shift. Although the NN improves results by 17% in the Training Data, it performs 40% worse on the out-of-domain Test Set. Surprisingly, the Scatter-Augmented Neural Network (SANN) performs similarly. While the DRRN is successful in mapping the training and Test Data onto the same latent space, it consistently underperforms compared to a straightforward Yx scaling relation. These results serve as a warning that simulation-based inference must be handled with extreme care, as subtle differences between training simulations and observational data can lead to unforeseen biases creeping into the results.

Ntampaka, Michelle [Baltimore, Space Telescope Sci↗

MO-E-BRD-01: Adapt-A-Thon - Texas Hold’em Invitational

Software tools for image-based adaptive radiotherapy such as deformable image registration, contour propagation and dose mapping have progressed beyond the research setting and are now commercial products available as part of both treatment planning systems and stand-alone applications. These software tools are used together to create clinical workflows to detect, track and evaluate changes in the patient and to accumulate dose. Deviations uncovered in this process are used to guide decisions about replanning/adaptation with the goal of keeping the delivery of prescribed dose “on target” throughout the entire course of radiotherapy. Since the output from one step of the adaptive process is used as an input for another, it is essential to understand and document the uncertainty associated with each of the step and how these uncertainties are propagated. This in turn requires an understanding how the underlying tools work. Unfortunately, important details about the algorithms used to implement these tools are scarce or incomplete, too often for competitive reasons. This is in contrast to the situation involving other basic treatment planning algorithms such as dose calculations, where the medical physics community essentially requires vendors to provide physically important details about their underlying theory and clinical implementation. Vendors should adopt this same level of information sharing when it comes to the tools and techniques for image guided adaptive radiotherapy. The goal of this session is to start this process by inviting vendors and medical physicists to discuss and demonstrate the available tools and describe how they are intended to be used in clinical practice. The format of the session will involve a combination of formal presentations, interactive demonstrations, audience participation and some friendly “Texas style” competition. Learning Objectives: Understand the components of the image-based adaptive radiotherapy process. Understand the how these components are implemented in various commercial systems. Understand the different use cases and workflows currently supported these tools.

60 APPLIED LIFE SCIENCES↗

Adaptive fuzzy system for 3-D vision

An adaptive fuzzy system using the concept of the Adaptive Resonance Theory (ART) type neural network architecture and incorporating fuzzy c-means (FCM) system equations for reclassification of cluster centers was developed. The Adaptive Fuzzy Leader Clustering (AFLC) architecture is a hybrid neural-fuzzy system which learns on-line in a stable and efficient manner. The system uses a control structure similar to that found in the Adaptive Resonance Theory (ART-1) network to identify the cluster centers initially. The initial classification of an input takes place in a two stage process; a simple competitive stage and a distance metric comparison stage. The cluster prototypes are then incrementally updated by relocating the centroid positions from Fuzzy c-Means (FCM) system equations for the centroids and the membership values. The operational characteristics of AFLC and the critical parameters involved in its operation are discussed. The performance of the AFLC algorithm is presented through application of the algorithm to the Anderson Iris data, and laser-luminescent fingerprint image data. The AFLC algorithm successfully classifies features extracted from real data, discrete or continuous, indicating the potential strength of this new clustering algorithm in analyzing complex data sets. The hybrid neuro-fuzzy AFLC algorithm will enhance analysis of a number of difficult recognition and control problems involved with Tethered Satellite Systems and on-orbit space shuttle attitude controller.

Mitra, Sunanda↗

Adaptive process control using fuzzy logic and genetic algorithms

Researchers at the U.S. Bureau of Mines have developed adaptive process control systems in which genetic algorithms (GA's) are used to augment fuzzy logic controllers (FLC's). GA's are search algorithms that rapidly locate near-optimum solutions to a wide spectrum of problems by modeling the search procedures of natural genetics. FLC's are rule based systems that efficiently manipulate a problem environment by modeling the 'rule-of-thumb' strategy used in human decision making. Together, GA's and FLC's possess the capabilities necessary to produce powerful, efficient, and robust adaptive control systems. To perform efficiently, such control systems require a control element to manipulate the problem environment, and a learning element to adjust to the changes in the problem environment. Details of an overall adaptive control system are discussed. A specific laboratory acid-base pH system is used to demonstrate the ideas presented.

Karr, C. L.↗

Mitigating Catastrophic Forgetting in Deep Learning in a Streaming Setting Using Historical Summary

Recent advancements in scientific equipment and the adaptation of electronics and the Internet of Things (IoT) in our everyday lives resulted in large and complex data production at a high rate. Making meaningful and timely knowledge discovery at a modest cost from this big data is difficult for computing power and storage limitations. Training deep learning models incrementally in a streaming setting can help us with overcoming these limitations. However, in a well-known phenomenon named catastrophic forgetting, incrementally trained models increasingly perform poorly on the past data. To mitigate catastrophic forgetting in training in a streaming setting, we propose constructing a historical summary over time and use the summary with newly arrived data during incremental training. We propose various data summarization techniques such as random sampling, micro clustering, coreset computation, and Auto Encoders to counteract catastrophic forgetting. We built a pipeline for incremental training with a historical summary for training deep learning models for streaming data. We demonstrate the effectiveness of historical summary in mitigating catastrophic forgetting using three case studies involving three different deep learning applications: an Artificial Neural Network (ANN) for classification task on MNIST dataset, a language model (RNN-LM) on the WikiText2 dataset, and a Convolutional Neural Network (CNN), ResNet50 to classify the ImageNet dataset. Through the training of the models, we observe that catastrophic forgetting is evident in ANN and CNN but not in an RNN. For the first task, our method recovers up to 47.9% lost accuracy due to catastrophic forgetting. For the third task, the historical summary recovers classification accuracy by up to 25%. For the second task, though there is not proof of catastrophic forgetting, the training performance (PPL) improves by up to 26% with historical summary.

Dash, Sajal↗

Training Modalities to Increase Sensorimotor Adaptability

During the acute phase of adaptation to novel gravitational environments, sensorimotor disturbances have the potential to disrupt the ability of astronauts to perform required mission tasks. The goal of our current series of studies is develop a sensorimotor adaptability (SA) training program designed to facilitate recovery of functional capabilities when astronauts transition to different gravitational environments. The project has conducted a series of studies investigating the efficacy of treadmill training combined with a variety of sensory challenges (incongruent visual input, support surface instability) designed to increase adaptability. SA training using a treadmill combined with exposure to altered visual input was effective in producing increased adaptability in a more complex over-ground ambulatory task on an obstacle course. This confirms that for a complex task like walking, treadmill training contains enough of the critical features of overground walking to be an effective training modality. SA training can be optimized by using a periodized training schedule. Test sessions that each contain short-duration exposures to multiple perturbation stimuli allows subjects to acquire a greater ability to rapidly reorganize appropriate response strategies when encountering a novel sensory environment. Using a treadmill mounted on top of a six degree-of-freedom motion base platform we investigated locomotor training responses produced by subjects introduced to a dynamic walking surface combined with alterations in visual flow. Subjects who received this training had improved locomotor performance and faster reaction times when exposed to the novel sensory stimuli compared to control subjects. Results also demonstrate that individual sensory biases (i.e. increased visual dependency) can predict adaptive responses to novel sensory environments suggesting that individual training prescription can be developed to enhance adaptability. These data indicate that SA training can be effectively integrated with treadmill exercise and optimized to provide a unique system that combines multiple training requirements in a single countermeasure system. Learning Objectives: The development of a new countermeasure approach that enhances sensorimotor adaptability will be discussed.

Bloomberg, J. J.↗

Learning control for minimizing a quadratic cost during repetitions of a task

In many applications, control systems are asked to perform the same task repeatedly. Learning control laws have been developed over the last few years that allow the controller to improve its performance each repetition, and to converge to zero error in tracking a desired trajectory. This paper generates a new type of learning control law that learns to minimize a quadratic cost function for tracking. Besides being of interest in its own right, this objective alleviates the need to specify a desired trajectory that can actually be performed by the system. The approach used here is to adapt appropriate methods from numerical optimization theory in order to produce learning control algorithms that adjust the system command from repetition to repetition in order to converge to the quadratic cost optimal trajectory.

Longman, Richard W.↗

Inductive Approaches to Improving Diagnosis and Design for Diagnosability

The first research area under this grant addresses the problem of classifying time series according to their morphological features in the time domain. A supervised learning system called CALCHAS, which induces a classification procedure for signatures from preclassified examples, was developed. For each of several signature classes, the system infers a model that captures the class's morphological features using Bayesian model induction and the minimum message length approach to assign priors. After induction, a time series (signature) is classified in one of the classes when there is enough evidence to support that decision. Time series with sufficiently novel features, belonging to classes not present in the training set, are recognized as such. A second area of research assumes two sources of information about a system: a model or domain theory that encodes aspects of the system under study and data from actual system operations over time. A model, when it exists, represents strong prior expectations about how a system will perform. Our work with a diagnostic model of the RCS (Reaction Control System) of the Space Shuttle motivated the development of SIG, a system which combines information from a model (or domain theory) and data. As it tracks RCS behavior, the model computes quantitative and qualitative values. Induction is then performed over the data represented by both the 'raw' features and the model-computed high-level features. Finally, work on clustering for operating mode discovery motivated some important extensions to the clustering strategy we had used. One modification appends an iterative optimization technique onto the clustering system; this optimization strategy appears to be novel in the clustering literature. A second modification improves the noise tolerance of the clustering system. In particular, we adapt resampling-based pruning strategies used by supervised learning systems to the task of simplifying hierarchical clusterings, thus making post-clustering analysis easier.

Fisher, Douglas H.↗

Deep Reinforcement Learning for Distribution System Operations: A Tutorial and Survey

Here, the rapid evolution of modern electric power distribution systems into complex networks of interconnected active devices, distributed generation (DG), and storage poses increasing difficulties for system operators. The large-scale integration of distributed energy resources (DERs) and the rapid exchange of measurement data via communication networks present major opportunities for advancing grid operations but also introduce greater uncertainty, higher data dimensionality, more complex network and device models, and challenging control and optimization problems. Deep reinforcement learning (DRL) algorithms are promising in addressing these challenges. However, they have not been effectively adapted for power systems applications, requiring extensive customization for implementation and evaluation. This has resulted in reproducibility challenges and a steep learning curve for researchers new to applying DRL algorithms to the power systems domain. To bridge these gaps, this tutorial aims to serve as a valuable resource for researchers interested in exploring learning-based algorithms to operate active power distribution networks. Specifically, this work presents a generalized process for translating sequential decision-making problems in power distribution systems into Markov decision process (MDP) formulations, illustrated through concrete grid service examples. Additionally, we introduce a simple environment design strategy to develop and evaluate example DRL algorithms for distribution system applications, complete with an included code repository to guide users through environment construction.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Fast Adaptive Neural Control of Resonant Extraction at Fermilab

We present the development of a machine learning (ML) based regulation system for third-order resonant beam extraction in the Mu2e experiment at Fermilab. Classical and ML-based controllers have been optimized using semi-analytic simulations and evaluated in terms of regulation performance and training efficiency. We compare several controller architectures and discuss the integration of neural control into an adaptive framework. We also present progress on surrogate models that predict the controller response given a spill intensity and controller action history. To enable real-time deployment, we report progress on implementing low-latency, edge-based inference suitable for hardware-constrained environments. Our results demonstrate the feasibility and advantages of ML-based control in managing complex, time-varying physical systems, with broader implications for accelerator operations and other domains requiring fast, adaptive regulation.

Berlioz, Jose Rene [Fermilab]↗