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 847 records · Page 47
All sourcesNASA NTRSDOE OSTI
NASA NTRS2000

X-38 Vehicle 131R Free Flights 1 and 2

The X-38 program is using a modern flight control system (FCS) architecture originally developed by Honeywell called MACH. During last year's SAE G&C subcommittee meeting, we outlined the design, implementation and testing of MACH in X-38 Vehicles 132, 131R & 201. During this year's SAE meeting, I'll focus upon the first two free flights of V131R, describing what caused the roll-over in FF1 and how we fixed it for FF2. I only have 30 minutes, so it will be a quick summary including VHS video. X-38 is a NASA JSC/DFRC experimental flight test program developing a series of prototypes for an International Space Station (ISS) Crew Return Vehicle (CRV), often described as an ISS "lifeboat." X-38 Vehicle 132 Free Flight 3 was the first flight test of a modern FCS architecture called Multi-Application ControlH (MACH), developed by the Honeywell Technology Center in Minneapolis and Honeywell's Houston Engineering Center. MACH wraps classical Proportional+integral (P+I) outer attitude loops around modern dynamic inversion attitude rate loops. The presentation at last year's SAE Aerospace Meeting No. 85 focused upon the design and testing of the FCS algorithm and Vehicle 132 Free Flight 3. This presentation will summarize flight control and aerodynamics lessons learned during Free Flights 1 and 2 of Vehicle 131R, a subsonic test vehicle laying the groundwork for the orbital/entry test of Vehicle 201 in 2003.

Munday, Steve↗
NASA NTRS2016

UAV Research at NASA Langley: Towards Safe, Reliable, and Autonomous Operations

Unmanned Aerial Vehicles (UAV) are fundamental components in several aspects of research at NASA Langley, such as flight dynamics, mission-driven airframe design, airspace integration demonstrations, atmospheric science projects, and more. In particular, NASA Langley Research Center (Langley) is using UAVs to develop and demonstrate innovative capabilities that meet the autonomy and robotics challenges that are anticipated in science, space exploration, and aeronautics. These capabilities will enable new NASA missions such as asteroid rendezvous and retrieval (ARRM), Mars exploration, in-situ resource utilization (ISRU), pollution measurements in historically inaccessible areas, and the integration of UAVs into our everyday lives all missions of increasing complexity, distance, pace, and/or accessibility. Building on decades of NASA experience and success in the design, fabrication, and integration of robust and reliable automated systems for space and aeronautics, Langley Autonomy Incubator seeks to bridge the gap between automation and autonomy by enabling safe autonomous operations via onboard sensing and perception systems in both data-rich and data-deprived environments. The Autonomy Incubator is focused on the challenge of mobility and manipulation in dynamic and unstructured environments by integrating technologies such as computer vision, visual odometry, real-time mapping, path planning, object detection and avoidance, object classification, adaptive control, sensor fusion, machine learning, and natural human-machine teaming. These technologies are implemented in an architectural framework developed in-house for easy integration and interoperability of cutting-edge hardware and software.

Davila, Carlos G.↗
NASA NTRS2018

Learn to Fly Test Setup and Concept of Operations

The NASA Learn-to-Fly (L2F) project recently completed a series of flight demonstrations of its learning algorithm for flight control at Fort A. P. Hill in Virginia. This paper discusses the test setup and concept of operations (ConOps) used by the L2F team. Unmanned airframe demonstrators for testing the research algorithms included a modified commercial off-the-shelf subscale powered airplane, plus four gliders – two of which had an unconventional configuration and were fabricated using a “rapid” prototyping technique. Avionics system similarities and differences between the test aircraft are described, as well as ground testing in preparation for flight. The ConOps discussion includes the development of a tethered helium balloon drop launch technique for the glider demonstrators. This launch method was chosen for its potential to be inexpensive and allow for rapid turn-around for multiple glider launches – but it also presented challenges, such as balloon tether avoidance, high angle of attack, low dynamic pressure initial conditions, and susceptibility to winds. A remotely piloted approach employing high-end hobbyist radio controlled (R/C) hardware was used for the powered demonstrator. This approach accommodated the interaction between the R/C flight system and the research flight control computer, engaging the L2F algorithm at varying initial conditions and artificially reducing the aircraft stability to stress the algorithm.

Riddick, Stephen E↗
DOE OSTI2020

Physics-constrained Deep Recurrent Neural Models of Building Thermal Dynamics

We develop physics-constrained and control-oriented predictive deep learning models for the thermal dynamics of a real-world commercial office building. The proposed method is based on the systematic encoding of physics-based prior knowledge into a structured recurrent neural architecture. Specifically, our model mimics the structure of the building thermal dynamics model and leverages penalty methods to model inequality constraints. Additionally, we use constrained matrix parameterization based on the Perron-Frobenius theorem to bound the eigenvalues of the learned network weights. We interpret the stable eigenvalues as dissipativeness of the learned building thermal model. We demonstrate the effectiveness of the proposed approach on a dataset obtained from an office building with $20$ thermal zones.

Building Energy, structured neural networks↗
DOE OSTI2021

Constrained Block Nonlinear Neural Dynamical Models

Neural network modules conditioned by known priors can be effectively trained and combined to represent systems with nonlinear dynamics. This work explores a novel formulation for data-efficient learning of deep control-oriented nonlinear dynamical models by embedding local model structure and constraints. The proposed method consists of neural network blocks that represent input, state, and output dynamics with constraints placed on the network weights and system variables. For handling partially observable dynamical systems, we utilize a state observer neural network to estimate the states of the system's latent dynamics. We evaluate the performance of the proposed architecture and training methods on system identification tasks for three nonlinear systems: a continuous stirred tank reactor, a two tank interacting system, and an aerodynamics body. Models optimized with a few thousand system state observations accurately represent system dynamics in open loop simulation over thousands of time steps from a single set of initial conditions. Experimental results demonstrate an order of magnitude reduction in open-loop simulation mean squared error for our constrained, block-structured neural models when compared to traditional unstructured and unconstrained neural network models.

Skomski, Elliott↗
DOE OSTI2022

Sensitivity Study of Mini-Batch Size on a Long Short-Term Memory Network for In-situ Sensing of Core-to-shell Ratio of Microencapsulated Phase Change Materials

Microencapsulated phase change materials are being studied for applications for thermal energy storage in concentrated solar fields. During fabrication, the thickness of the encapsulation cannot be readily measured for real-time control. Therefore, a machine learning network, specifically a Long Short-Term Memory network, is being developed to estimate the ratio of the shell radius to core radius based on a one second temperature history. The mini-batch size determines how often the algorithm weights are updated during network training, and shuffle indicates whether the training data is shuffled during training. A general factorial design is used to analyze the effects of varying mini-batch size and shuffle, along with the core-to-shell ratio, on the RMSE of the response from the Long Short-Term Memory network. It was found that the network performed better for smaller core to shell ratios (less than 0.6) and had the lowest RMSE when the minibatch size was 128. The minimum RMSE found was 0.00501.

Shannon, Rebecca↗
DOE OSTI2019

Data-driven cyber attack detection and mitigation for decentralized wide-area protection and control in smart grids

Modern power systems have already evolved into complicated cyber physical systems (CPS), often referred to as smart grids, due to the continuous expansion of the electrical infrastructure, the augmentation of the number of heterogeneous system components and players, and the consequential application of a diversity of information and telecommunication technologies to facilitate the Wide Area Monitoring, Protection and Control (WAMPAC) of the day-to-day power system operation. Because of the reliance on cyber technologies, WAMPAC, among other critical functions, is prone to various malicious cyber attacks. Successful cyber attacks, especially those sabotage the operation of Bulk Electric System (BES), can cause great financial losses and social panics. Application of conventional IT security solutions is indispensable, but it often turns out to be insufficient to mitigate sophisticated attacks that deploy zero-day vulnerabilities or social engineering tactics. To further improve the resilience of the operation of smart grids when facing cyber attacks, it is desirable to make the WAMPAC functions per se capable of detecting various anomalies automatically, carrying out adaptive activity adjustments in time and thus staying unimpaired even under attack. Most of the existing research efforts attempt to achieve this by adding novel functional modules, such as model-based anomaly detectors, to the legacy centralized WAMPAC functions. In contrast, this dissertation investigates the application of data-driven algorithms in cyber attack detection and mitigation within a decentralized architecture aiming at improving the situational awareness and self-adaptiveness of WAMPAC. First part of the research focuses on the decentralization of System Integrity Protection Scheme (SIPS) with Multi-Agent System (MAS), within which the data-driven anomaly detection and optimal adaptive load shedding are further explored. An algorithm named as Support Vector Machine embedded Layered Decision Tree (SVMLDT) is proposed for the anomaly detection, which provides satisfactory detection accuracy as well as decision-making interpretability. The adaptive load shedding is carried out by every agent individually with dynamic programming. The load shedding relies on the load profile propagation among peer agents and the attack adaptiveness is accomplished by maintaining the historical mean of load shedding proportion. Load shedding only takes place after the consensus pertaining to the anomaly detection is achieved among all interconnected agents and it serves the purpose of mitigating certain cyber attacks. The attack resilience of the decentralized SIPS is evaluated using IEEE 39 bus model. It is shown that, unlike the traditional centralized SIPS, the proposed solution is able to carry out the remedial actions under most Denial of Service (DoS) attacks. The second part investigates the clustering based anomalous behavior detection and peer-assisted mitigation for power system generation control. To reduce the dimensionality of the data, three metrics are designed to interpret the behavior conformity of generator within the same balancing area. Semi-supervised K-means clustering and a density sensitive clustering algorithm based on Hierarchical DBSCAN (HDBSCAN) are both applied in clustering in the 3D feature space. Aiming to mitigate the cyber attacks targeting the generation control commands, a peer-assisted strategy is proposed. When the control commands from control center is detected as anomalous, i.e. either missing or the payload of which have been manipulated, the generating unit utilizes the peer data to infer and estimate a new generation adjustment value as replacement. Linear regression is utilized to obtain the relation of control values received by different generating units, Moving Target Defense (MTD) is adopted during the peer selection and 1-dimensional clustering is performed with the inferred control values, which are followed by the final control value estimation. The mitigation strategy proposed requires that generating units can communicate with each other in a peer-to-peer manner. Evaluation results suggest the efficacy of the proposed solution in counteracting data availability and data integrity attacks targeting the generation controls. However, the strategy stays effective only if less than half of the generating units are compromised and it is not able to mitigate cyber attacks targeting the measurements involved in the generation control.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

Development of Predictive Models for Advanced Reactor Autonomous Control

Advanced reactor designs including microreactors and small modular reactors will contribute to the clean production of cheap energy, and autonomous control for advanced reactors is an appealing option for reducing cost. However, there is a lack of industry experience applying autonomous control for advanced nuclear reactors. To accelerate the development and industry acceptance of autonomous control software for nuclear reactors, we aim to demonstrate autonomous control of the Purdue University research reactor (PUR-1) using INL-developed model predictive control (MPC) methods. To prepare for this demonstration, data-driven predictive models based on process data collected from PUR-1 have been developed and integrated with MPC and used to control a physics-based model of PUR-1. A data-driven dynamics model and a gated recurrent unit (GRU) network were both trained on process data from PUR-1. The dynamics model was shown to effectively control the reactor model with MPC when provided reactivity as a control variable but failed to control the model through the control rod positions. The GRU network produced more accurate predictions than the dynamics model when evaluated on operational data, and future work will include the evaluation of the GRU network in the controller.

22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2020

TensorFlow Quantum: A Software Framework for Quantum Machine Learning

We introduce TensorFlow Quantum (TFQ), an open source library for the rapid prototyping of hybrid quantum-classical models for classical or quantum data. This framework offers high-level abstractions for the design and training of both discriminative and generative quantum models under TensorFlow and supports high-performance quantum circuit simulators. We provide an overview of the software architecture and building blocks through several examples and review the theory of hybrid quantum-classical neural networks. We illustrate TFQ functionalities via several basic applications including supervised learning for quantum classification, quantum control, simulating noisy quantum circuits, and quantum approximate optimization. Moreover, we demonstrate how one can apply TFQ to tackle advanced quantum learning tasks including meta-learning, layerwise learning, Hamiltonian learning, sampling thermal states, variational quantum eigensolvers, classification of quantum phase transitions, generative adversarial networks, and reinforcement learning. We hope this framework provides the necessary tools for the quantum computing and machine learning research communities to explore models of both natural and artificial quantum systems, and ultimately discover new quantum algorithms which could potentially yield a quantum advantage.

Broughton, Michael↗
DOE OSTI2022

A Hybrid Reinforcement Learning-MPC Approach for Distribution System Critical Load Restoration: Preprint

This paper proposes a hybrid control approach for distribution system critical load restoration, combining deep reinforcement learning (RL) and model predictive control (MPC) aiming at maximizing total restored load following an extreme event. RL determines a policy for quantifying operating reserve requirements, thereby hedging against uncertainty, while MPC models grid operations incorporating RL policy actions, i.e., the reserve requirement, renewable (wind and solar) power predictions, and load demand forecasts. We formulate the reserve requirement determination problem as a sequential decision making problem based on the Markov Decision Process (MDP) and design an RL learning environment based on the OpenAI Gym framework and MPC. The RL agent reward and MPC objective function aim to maximize and monotonically increase total restored load and minimize load shedding and renewable power curtailment. The RL algorithm is trained off-line using historical forecast of renewable generation and load demand. The method is tested using a modified IEEE 13-bus distribution test feeder containing wind turbine, photovoltaic, microturbine and battery. Case studies demonstrated that the proposed method outperforms other operating reserve determination methods.

distribution system↗
DOE OSTI2023

Measurement of Beam Energy in the Fermilab's Linac taken at the Transfer Line

Linac is the first machine in the accelerator chain at Fermilab where H$^{-}$ ions are accelerated from 35 keV to 401.5\,MeV and then injected into a synchronton known as Booster where they are stripped of their electrons to become protons. One of the tools used during tuning of the Linac extraction energy is two beam pickups known as Griffin Detectors. Our goal is to control the output energy using machine learning techniques to increase the reliability and quality of the beam delivered from Linac. The first step is to understand the data from the diagnostics to develop reliable and accurate energy measurement, and control methods before implementing machine learning techniques. Two methods of energy measurement were studied, and their results are compared. The first method was the time of flight measurement using Beam Position Monitors that provide beam phase measurement. The second method used the relation between beam transverse positions and dispersion values to calculate momentum variation. The results of these two measurement methods are found to be consistent.

43 PARTICLE ACCELERATORS↗
NASA NTRS1993

Application of fuzzy logic-neural network based reinforcement learning to proximity and docking operations: Special approach/docking testcase results

As part of the RICIS project, the reinforcement learning techniques developed at Ames Research Center are being applied to proximity and docking operations using the Shuttle and Solar Maximum Mission (SMM) satellite simulation. In utilizing these fuzzy learning techniques, we use the Approximate Reasoning based Intelligent Control (ARIC) architecture, and so we use these two terms interchangeably to imply the same. This activity is carried out in the Software Technology Laboratory utilizing the Orbital Operations Simulator (OOS) and programming/testing support from other contractor personnel. This report is the final deliverable D4 in our milestones and project activity. It provides the test results for the special testcase of approach/docking scenario for the shuttle and SMM satellite. Based on our experience and analysis with the attitude and translational controllers, we have modified the basic configuration of the reinforcement learning algorithm in ARIC. The shuttle translational controller and its implementation in ARIC is described in our deliverable D3. In order to simulate the final approach and docking operations, we have set-up this special testcase as described in section 2. The ARIC performance results for these operations are discussed in section 3 and conclusions are provided in section 4 along with the summary for the project.

Jani, Yashvant↗
NASA NTRS2009

Evaluation of Learning Associated with Multiple Exposures to Computerized Dynamic Posturography

Computerized dynamic posturography has been used to quantitatively assess the time course of functional sensorimotor recovery after exposure to spaceflight or to groundbased analogs such as head-down bed rest. An assessment of balance recovery may be confounded as subjects develop new strategies through repeated exposures to test paradigms. The purpose of this control study was to characterize the learning effects of sensory organization and motor control tests across multiple sessions. METHODS: Twenty-eight healthy subjects were tested over four sessions. To examine the effects of between-session interval, subjects were assigned to one of four groups in which the interval between the 1 st and 2nd sessions was 7 (+/- 1) days, 14 (+/-1) days, 28 (+/-2) days, or 56 (+/-3) days. The interval between remaining sessions was 28 (+/-4) days. Peak-to-peak anterior-posterior sway was measured during standard Sensory Organization Tests (SOTs) using either fixed or unstable sway-referenced support with eyes open, eyes closed, or sway-referenced vision. Sway was also measured during modified SOTs using eyes-closed conditions with either static or dynamic head tilts. Postural recovery to unexpected support surface perturbations (translations or rotations) was measured during Motor Control Tests. The test order was block randomized across subjects. RESULTS: The learning effects varied with test condition. There were no measurable differences with a stable support surface. The more challenging conditions (unstable support surface with and without head tilts) led to greater differences and took more trials to stabilize. The effect of time interval between the first two sessions was negligible across conditions. Evidence suggested that learning carried across similar conditions (such as unstable support SOTs). DISCUSSION: Familiarization session and/or trials are recommended to minimize learning effects when characterizing functional recovery after exposure to altered sensory environments. The number of practice trials required depends on task difficulty and similarity across conditions. Learning statement: This presentation will review the learning effects of computerized d

Dean, S. Lance↗
DOE OSTI2023

DAISY Complement Protein ML-Ready Data

A total of 172 children from the DAISY study with multiple plasma samples collected over time, with up to 23 years of follow-up, were characterized via proteomics analysis. Of the children there were 40 controls and 132 cases. All 132 cases had measurements across time relative to IA. Sampling was not consistent for all children. There were 47 of the children who had samples taken and evaluated prior to IA (Pre-IA), and 131 children had measurements at or after IA, but prior to diagnosis of clinical T1D (Post-IA). The control children were frequency matched on HLA genotypes and age and sex with an observed lower frequency of first degree relatives within the control group versus the cases For machine learning the children that will develop islet autoantibodies the 40 control and 47 Pre-IA children were down-selected to a single sample time point. For the 40 control children this was the earliest sample collected and for the 47 Pre-IA children it was a random selection of the first or second time point prior to the detection of autoantibodies to assure the age distributions were not significantly different.

machine learning, proteomics, Type 1 Diabetes, com↗
DOE OSTI2024

Dynamic Multiplexed Control and Modeling of Optogenetic Systems Using the High-Throughput Optogenetic Platform, Lustro

The ability to control cellular processes using optogenetics is inducer-limited, with most optogenetic systems responding to blue light. To address this limitation, we leverage an integrated framework combining Lustro, a powerful high-throughput optogenetics platform, and machine learning tools to enable multiplexed control over blue light-sensitive optogenetic systems. Specifically, we identify light induction conditions for sequential activation as well as preferential activation and switching between pairs of light-sensitive split transcription factors in the budding yeast, Saccharomyces cerevisiae. We use the high-throughput data generated from Lustro to build a Bayesian optimization framework that incorporates data-driven learning, uncertainty quantification, and experimental design to enable the prediction of system behavior and the identification of optimal conditions for multiplexed control. This work lays the foundation for designing more advanced synthetic biological circuits incorporating optogenetics, where multiple circuit components can be controlled using designer light induction programs, with broad implications for biotechnology and bioengineering.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

Contrastive learning for robust representations of neutrino data

In neutrino physics, analyses often depend on large simulated datasets, making it essential for models to generalize effectively to real-world detector data. Contrastive learning, a well-established technique in deep learning, offers a promising solution to this challenge. By applying controlled data augmentations to simulated data, contrastive learning enables the extraction of robust and transferable features. This improves the ability of models trained on simulations to adapt to real experimental data distributions. In this paper, we investigate the application of contrastive learning methods in the context of neutrino physics. Through a combination of empirical evaluations and theoretical insights, we demonstrate how contrastive learning enhances model performance and adaptability. Additionally, we compare it to other domain adaptation techniques, highlighting the unique advantages of contrastive learning for this field. Published by the American Physical Society 2025

Wilkinson, Alex (ORCID:0000000253404506)↗
DOE OSTI2023

DAISY Complement Protein ML-Ready Data

A total of 172 children from the DAISY study with multiple plasma samples collected over time, with up to 23 years of follow-up, were characterized via proteomics analysis. Of the children there were 40 controls and 132 cases. All 132 cases had measurements across time relative to IA. Sampling was not consistent for all children. There were 47 of the children who had samples taken and evaluated prior to IA (Pre-IA), and 131 children had measurements at or after IA, but prior to diagnosis of clinical T1D (Post-IA). The control children were frequency matched on HLA genotypes and age and sex with an observed lower frequency of first degree relatives within the control group versus the cases For machine learning the children that will develop islet autoantibodies the 40 control and 47 Pre-IA children were down-selected to a single sample time point. For the 40 control children this was the earliest sample collected and for the 47 Pre-IA children it was a random selection of the first or second time point prior to the detection of autoantibodies to assure the age distributions were not significantly different.

Webb-Robertson, Bobbie-Jo M↗