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 721 records · Page 40
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Automatic identification of edge localized modes in the DIII-D tokamak

Fusion power production in tokamaks uses discharge configurations that risk producing strong type I edge localized modes. The largest of these modes will likely increase impurities in the plasma and potentially damage plasma facing components, such as the protective heat and particle divertor. Machine learning-based prediction and control may provide for the automatic detection and mitigation of these damaging modes before they grow too large to suppress. To that end, large labeled datasets are required for the supervised training of machine learning models. We present an algorithm that achieves 97.7% precision when automatically labeling edge localized modes in the large DIII-D tokamak discharge database. The algorithm has no user controlled parameters and is largely robust to tokamak and plasma configuration changes. This automatically labeled database of events can subsequently feed future training of machine learning models aimed at autonomous edge localized mode control and suppression.

O’Shea, Finn H. (ORCID:0000000323987381)↗
DOE OSTI2022

Empirical relationships between environmental factors and soil organic carbon produce comparable prediction accuracy as the Machine Learning

Accurate representation of environmental controllers of soil organic carbon (SOC) stocks in Earth System Model (ESM) land models could reduce uncertainties in future carbon-climate feedback projections. Using empirical relationships between environmental factors and SOC stocks to evaluate land models can help modelers understand prediction biases beyond what can be achieved with the observed SOC stocks alone. In this study, we used 31 observed environmental factors, field SOC observations (n = 6,213) from the continental US, and two Machine Learning approaches [Random Forest (RF) and Generalized Additive Modeling (GAM)] to (1) select important environmental predictors of SOC stocks, (2) derive empirical relationships between environmental factors and SOC stocks, and (3) use the derived relationships to predict SOC stocks and compare the prediction accuracy of simpler model developed with the machine learning predictions. Out of the 31 environmental factors we investigated, 12 were identified as important predictors of SOC stocks by the RF approach. In contrast, the GAM approach identified six (of those 12) environmental factors as important controllers of SOC stocks: potential evapotranspiration, normalized difference vegetation index, soil drainage condition, precipitation, elevation, and net primary productivity. The GAM approach showed minimal SOC predictive importance of the remaining six environmental factors identified by the RF approach. Our derived empirical relations produced comparable prediction accuracy as the GAM and RF approach using only a subset of environmental factors. The empirical relationships we derived using the GAM approach can serve as important benchmarks to evaluate environmental control representations of SOC stocks in ESMs, which could reduce uncertainty in predicting future carbon-climate feedbacks.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

ML based control systems for nuclear physics experiments

The Experimental Physics Software and Computing Infrastructure (EPSCI) group at Jefferson Lab is leading the use of machine learning (ML) to enhance control systems in nuclear physics experiments. Collaborating closely with domain experts and data scientists, we have developed an ML-based control system that uses a Gaussian process to dynamically adjust the high voltage of the GlueX Central Drift Chamber. This results in stable detector performance by adapting to environmental changes, thereby reducing the offline calibration effort. Furthermore, we are developing ML-driven systems for optimizing the polarization of photon beams and polarized cryotargets. These systems will maintain the optimal microwave frequency in cryogenic targets and make real-time adjustments to diamond radiators for polarized photon sources, tasks traditionally handled by human operators. By automating these functions, we aim to optimize the polarization, reduce downtime, and minimize human error. This talk will highlight the development of reliable ML-based control systems and the policies to ensure they are both effective and trustworthy.

Jeske, Torri↗
DOE OSTI2018

Decomposition of Nonlinear Dynamical Systems Using Koopman Gramians

In this paper we propose a new Koopman operator approach for nonlinear model decomposition using Koopman gramians. We introduce Koopman operators and discuss the notion of a input-Koopman operator. We show how input-Koopman operators can be used to cast a nonlinear system into the classical state-space form, as well as conditions under which input and state observable functions are well separated. We extend an existing method of dynamic mode decomposition for learning Koopman operators from data known as deep dynamic mode decomposition, for systems with control or disturbances. We illustrate the accuracy of the method on learning an input-state separable Koopman operator for an example system, even when the underlying system exhibits mixed state-input terms. Finally, we introduce a nonlinear decomposition algorithm, based on Koopman gramians, that maximizes internal subsystem observability and disturbance rejection from unwanted noise in other subsystems. To relieve the NP-hardness of the decomposition problem, we derive a relaxation based on Koopman gramians and multi-way partitioning. We illustrate our algorithm on a swing dynamics model for a IEEE 39 bus and discuss our findings.

Learning, Control, Distributed Control, koopman op↗
NASA NTRS2003

Integration of Online Parameter Identification and Neural Network for In-Flight Adaptive Control

An indirect adaptive system has been constructed for robust control of an aircraft with uncertain aerodynamic characteristics. This system consists of a multilayer perceptron pre-trained neural network, online stability and control derivative identification, a dynamic cell structure online learning neural network, and a model following control system based on the stochastic optimal feedforward and feedback technique. The pre-trained neural network and model following control system have been flight-tested, but the online parameter identification and online learning neural network are new additions used for in-flight adaptation of the control system model. A description of the modification and integration of these two stand-alone software packages into the complete system in preparation for initial flight tests is presented. Open-loop results using both simulation and flight data, as well as closed-loop performance of the complete system in a nonlinear, six-degree-of-freedom, flight validated simulation, are analyzed. Results show that this online learning system, in contrast to the nonlearning system, has the ability to adapt to changes in aerodynamic characteristics in a real-time, closed-loop, piloted simulation, resulting in improved flying qualities.

Hageman, Jacob↗
NASA NTRS2003

Integration of Online Parameter Identification and Neural Network for In-Flight Adaptive Control

An indirect adaptive system has been constructed for robust control of an aircraft with uncertain aerodynamic characteristics. This system consists of a multilayer perceptron pre-trained neural network, online stability and control derivative identification, a dynamic cell structure online learning neural network, and a model following control system based on the stochastic optimal feedforward and feedback technique. The pre-trained neural network and model following control system have been flight-tested, but the online parameter identification and online learning neural network are new additions used for in-flight adaptation of the control system model. A description of the modification and integration of these two stand-alone software packages into the complete system in preparation for initial flight tests is presented. Open-loop results using both simulation and flight data, as well as closed-loop performance of the complete system in a nonlinear, six-degree-of-freedom, flight validated simulation, are analyzed. Results show that this online learning system, in contrast to the nonlearning system, has the ability to adapt to changes in aerodynamic characteristics in a real-time, closed-loop, piloted simulation, resulting in improved flying qualities.

Hageman, Jacob J.↗
NASA NTRS1993

Synthesis of Optimal Nonlinear Feedback Laws for Dynamic Systems Using Neural Networks

Open-loop solutions of dynamical optimization problems can be numerically computed usingexisting software packages. The computed time histories of the state and control variables, formultiple sets of end conditions can then be used to train a neural network to 'recognize' the optimal,nonlinear feedback relation between the states and controls of the system. The 'learned' network canthen be used to output an approximate optimal control given a full set (or a partial set) of measuredsystem states. With simple neural networks, we have successfully demonstrated the efficacy of theproposed approach using a minimum-time orbit injection problem. The usefulness and limitations ofthis novel approach on real-life optimal guidance and control problems, with many state and control variables as well as path inequality constraints, remain to be seen.

Orbit injection problem↗
NASA NTRS2012

The Impact of Incentivizing the Use of Feedback on Learning and Performance in Educational Videogames

Educational videogames can be designed to provide instructional feedback responsive to specific actions. However, existing research indicates that students tend to ignore the feedback provided. That is, students often use ineffective help-seeking strategies. Research on the topic of help-seeking in learning environments have primarily focused on the role of cognitive factors, the nature of the help, or issues of timing and frequency. There is a noticeable gap in understanding how to motivate the use provided feedback. This study examined the relation between incentivizing the use of feedback and providing an explanation of the game's scoring rules on math learning in a pre-algebra videogame. A randomized-control design was used, comparing learning outcomes of students who received the incentive with those who did not. Results indicated that students given the incentive to use feedback had significantly higher normalized change scores on math items (d = .53), with stronger effects for students with low academic intrinsic motivation (d = .88 - 1.17).

Delacruz, Girlie C.↗
DOE OSTI2026

Signal Whisperers: Enhancing Wireless Reception Using DRL-Guided Reflector Arrays

This paper presents a multi-agent reinforcement learning (MARL) approach for controlling adjustable metallic reflector arrays to enhance wireless signal reception in non-line-of-sight (NLOS) scenarios. Unlike conventional reconfigurable intelligent surfaces (RIS) that require complex channel estimation, our system employs a centralized training with decentralized execution (CTDE) paradigm where individual agents corresponding to reflector segments autonomously optimize reflector element orientation in three-dimensional space using spatial intelligence based on user location information. Through extensive ray-tracing simulations with dynamic user mobility, the proposed multi-agent beam-focusing framework demonstrates substantial performance improvements over single-agent reinforcement learning baselines, while maintaining rapid adaptation to user movement within one simulation step. Comprehensive evaluation across varying user densities and reflector configurations validates system scalability and robustness. The results demonstrate the potential of learning-based approaches for adaptive wireless propagation control.

deep reinforcement learning↗
DOE OSTI2023

Stream Temperature Prediction in a Shifting Environment: Explaining the Influence of Deep Learning Architecture

Stream temperature is a fundamental control on ecosystem health. Recent efforts incorporating process guidance into deep learning models for predicting stream temperature have been shown to outperform existing statistical and physical models. This performance is in part because deep learning architectures can actively learn spatiotemporal relationships that govern how water and energy propagate through a river network. However, exploration of how spatiotemporal awareness and process guidance influence a model's generalizability under shifting environmental conditions such as climate change is limited. Here, we use Explainable Artificial Intelligence (XAI) to interrogate how differing deep learning architectures affect a model's learned spatial and temporal dependencies, and how those learned dependencies affect a model's ability to maintain high accuracy when applied to unseen environmental conditions. Using the Delaware River Basin in the northeastern United States as a test case, we compare two spatiotemporally aware process–guided deep learning models for predicting stream temperature (a recurrent graph convolution network—RGCN, and a temporal convolution graph model—Graph WaveNet). Both models achieve equally high predictive performance when testing data are well represented in the training data (test root mean squared errors of 1.64°C and 1.65°C); however, Graph WaveNet significantly outperforms RGCN in 4 out of 5 experiments where test partitions represent different types of unseen environmental conditions. XAI results show that the architecture of Graph WaveNet leads to learned spatial relationships with greater fidelity to physical processes, and that this fidelity improves the generalizability of the model when applied to shifting and/or unseen environmental conditions.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2017

A self-learning disturbance observer for nonlinear systems in feedback-error learning scheme

Here this paper represents a novel online self-learning disturbance observer (SLDO) by benefiting from the combination of a type-2 neuro-fuzzy structure (T2NFS), feedback-error learning scheme and sliding mode control (SMC) theory. The SLDO is developed within a framework of feedback-error learning scheme in which a conventional estimation law and a T2NFS work in parallel. In this scheme, the latter learns uncertainties and becomes the leading estimator whereas the former provides the learning error to the T2NFS for learning system dynamics. A learning algorithm established on SMC theory is derived for an interval type-2 fuzzy logic system. In addition to the stability of the learning algorithm, the stability of the SLDO and the stability of the overall system are proven in the presence of time-varying disturbances. Thanks to learning process by the T2NFS, the simulation results show that the SLDO is able to estimate time-varying disturbances precisely as distinct from the basic nonlinear disturbance observer (BNDO) so that the controller based on the SLDO ensures robust control performance for systems with time-varying uncertainties, and maintains nominal performance in the absence of uncertainties.

42 ENGINEERING↗
DOE OSTI2025

Self-consistent equilibrium and transport simulations for NSTX-U plasmas enhanced via machine learning surrogate models

The Control-Oriented Transport SIMulator (COTSIM) is an advanced equilibrium and transport code designed for simulating tokamak discharges at computational speeds suitable for control applications. COTSIM’s modular framework enables users to select models that balance accuracy with speed according to specific needs, allowing the code to operate from fast to faster-than-real-time performance levels. This work presents recent enhancements to COTSIM’s predictive accuracy for NSTX-U scenarios, achieved by integrating neural-network-based surrogate models and self-consistent equilibrium calculations. To improve source deposition predictions, a surrogate model for NUBEAM has been incorporated. Additionally, a surrogate model for the Multi-Mode Module (MMM) now supports predictions of anomalous thermal, momentum, and particle diffusivities—key factors for modeling the evolution of temperature and rotation. Each surrogate model was specifically trained for the NSTX-U operational regime to enhance COTSIM’s accuracy while maintaining computational efficiency. Moreover, COTSIM now couples fixed-boundary equilibrium solvers with its transport solvers, enabling self-consistent predictions of plasma profiles and equilibrium evolution over the discharge. Simulation results demonstrate strong agreement between COTSIM and TRANSP predictions for NSTX-U discharges. These substantial advancements expand COTSIM’s utility in model-based control applications for NSTX-U. Potential applications include simultaneous optimization of equilibrium and transport scenarios, integration into digital twins, real-time profile estimation (e.g., temperature and rotation) from limited or noisy measurements, and advanced feedback-based scenario control.

Equilibrium and transport modeling↗
NASA NTRS1993

Attitude control of spacecraft using neural networks

This paper investigates the use of radial basis function neural networks for adaptive attitude control and momentum management of spacecraft. In the first part of the paper, neural networks are trained to learn from a family of open-loop optimal controls parameterized by the initial states and times-to-go. The trained is then used for closed-loop control. In the second part of the paper, neural networks are used for direct adaptive control in the presence of unmodeled effects and parameter uncertainty. The control and learning laws are derived using the method of Lyapunov.

Vadali, Srinivas R.↗
NASA NTRS1994

Intelligent Control Systems Research

Results of a three phase research program into intelligent control systems are presented. The first phase looked at implementing the lowest or direct level of a hierarchical control scheme using a reinforcement learning approach assuming no a priori information about the system under control. The second phase involved the design of an adaptive/optimizing level of the hierarchy and its interaction with the direct control level. The third and final phase of the research was aimed at combining the results of the previous phases with some a priori information about the controlled system.

Loparo, Kenneth A.↗
NASA NTRS2010

Hybrid Decompositional Verification for Discovering Failures in Adaptive Flight Control Systems

Adaptive flight control systems hold tremendous promise for maintaining the safety of a damaged aircraft and its passengers. However, most currently proposed adaptive control methodologies rely on online learning neural networks (OLNNs), which necessarily have the property that the controller is changing during the flight. These changes tend to be highly nonlinear, and difficult or impossible to analyze using standard techniques. In this paper, we approach the problem with a variant of compositional verification. The overall system is broken into components. Undesirable behavior is fed backwards through the system. Components which can be solved using formal methods techniques explicitly for the ranges of safe and unsafe input bounds are treated as white box components. The remaining black box components are analyzed with heuristic techniques that try to predict a range of component inputs that may lead to unsafe behavior. The composition of these component inputs throughout the system leads to overall system test vectors that may elucidate the undesirable behavior

Thompson, Sarah↗
NASA NTRS2016

Designing the Next Generation of Human Spacecraft

Lunar Space Station Common Module: A new concept for a module for a lunar space station attempts to reduce the module's mass by abandoning the traditional rack structure currently used on the ISS for the mounting of internal hardware and replacing it with a core structure. By using this design, the pressure shell will not have to carry the loads resulting from the internal mass. I worked with another intern to create the initial design for the module, with him focusing on the core and myself focusing on the pressure shell. To start, I was given the shell overall dimensions and material and tasked with sizing the wall thickness and placing stiffeners such that the shell could withstand the required loads. At the same time, I had to keep the mass to a minimum to keep the overall module within the allowable launch mass. Once I had done initial sizing based on pressure loads, I combined the pressure shell with the inner core to perform optimization of the design. Currently, the design involves circumferential stiffeners along the entire length of the pressure shell with longitudinal stiffeners on either end. In addition, extra wall thickness was added around each of the hatches. At this stage, the design shows a comparable mass to a more traditional design, but we are hopeful that, through optimization, we will be able to reduce the mass even further. There is currently a patent pending for the module design, for which I am listed as a co-inventor. ALON Material Testing: I was given samples of aluminum oxynitride (ALON) that had been impacted by a previous intern on which to perform residual strength tests as part of a plan to approve them for space use. Before testing, I measured the pucks and their damages using a ruler and optical micrometer in order to verify that the puck dimensions were within the tolerances set by the test guidelines and that the damages had not grown when the pucks were thinned. The test was a ring-ring test, which used two concentric rings to place the ring in axisymmetric bending, with the puck set up so that the damaged side was always in tension. Though I was unable to do the setup of the test or run the load machine due to a period of changing test procedures, I was able to observe the testing and perform the data collection. The pucks behaved as expected, breaking at the damage, as did the strengths calculated from the data, being lower than for the unimpacted pucks and having less scatter between the puck values. The attached image is of myself during the ALON strength testing. Over the course of my internship, I was able to learn much more about real-life structural analysis and about the behavior of materials, and it confirmed my previous interest in structural analysis. At the same time, due to the opportunities offered to interns, I was able to learn a lot about mission control, and, in doing so, I developed a second interest in working in mission control. In addition, being able to meet the people here and learn about the type of work NASA does made me want to come back to work for NASA full time.

Simmons, Emily↗
NASA NTRS1994

A neural network controller for automated composite manufacturing

At McDonnell Douglas Aerospace (MDA), an artificial neural network based control system has been developed and implemented to control laser heating for the fiber placement composite manufacturing process. This neurocontroller learns an approximate inverse model of the process on-line to provide performance that improves with experience and exceeds that of conventional feedback control techniques. When untrained, the control system behaves as a proportional plus integral (PI) controller. However after learning from experience, the neural network feedforward control module provides control signals that greatly improve temperature tracking performance. Faster convergence to new temperature set points and reduced temperature deviation due to changing feed rate have been demonstrated on the machine. A Cerebellar Model Articulation Controller (CMAC) network is used for inverse modeling because of its rapid learning performance. This control system is implemented in an IBM compatible 386 PC with an A/D board interface to the machine.

Lichtenwalner, Peter F.↗