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 775 records · Page 43

Ad-Mat: Adaptations of Mature Manufacturing Strategies for Accelerated Redox Flow Battery Deployment

The concept of the Ad-Mat approach is to leverage existing adjacent markets across a broad scope of technologies in order to reduce the manufacturing learning curve and ultimately accelerate redox flow battery (RFB) deployment at scale. Lithium-ion batteries (LIBs) are currently the dominant energy storage technology, and they came to technological maturity under unique market conditions when there was no meaningful competition in the consumer electronic and electric vehicle (EV) space. Today, alternative chemistries that may be technologically better-suited for long-duration storage applications are experiencing a high barrier to entry. This is in large part due to the substantial bias towards the scaled-up production and supply chain that now exists for LIBs. In the case of RFBs in particular, numerous analyses have suggested that RFBs should theoretically have a much lower system cost than LIBs - however, this relies on a mature and competitive manufacturing landscape, which has been extremely challenging to achieve for both flow batteries and other LIB competitors. At the moment, LIB alternatives tend to have isolated small-scale manufacturing pathways, which preclude the economies of scale that would be required to compete with the mature LIB industry. In the present state of the industry, niche manufacturing tools and approaches have evolved to support each alternative technology, such that there is substantial replication and duplication in effort. Continuing to pursue a strategy of isolated manufacturing processes/approaches for each LIB-alternative may never allow for at-scale deployment. In order for RFBs to meaningfully compete with LIBs in the realm of LDES, a new disruptive approach based on cross-industry learning and coordination is needed - and this is exactly what our Ad-Mat concept aims to tackle. In this re-envisioned manufacturing landscape, tools and processes from mature industries can be adapted and deployed across the range of alternative energy storage technologies. Adapting tools, equipment, processes, and industrial learning from mature industries to meet the technological requirements of RFBs would open new markets for existing OEMs in adjacent industries, would prevent unnecessary duplication and re-development, would improve efficiency across the manufacturing chain, and would ultimately support reduced costs and accelerated deployment of RFBs at scale.

adaptive manufacturing↗

Telerobotic control of a mobile coordinated robotic server, executive summary

This interim report continues with the research effort on advanced adaptive controls for space robotics systems. In particular, previous results developed by the principle investigator and his research team centered around fuzzy logic control (FLC) in which the lack of knowledge of the robotic system as well as the uncertainties of the environment are compensated for by a rule base structure which interacts with varying degrees of belief of control action using system measurements. An on-line adaptive algorithm was developed using a single parameter tuning scheme. In the effort presented, the methodology is further developed to include on-line scaling factor tuning and self-learning control as well as extended to the multi-input, multi-output (MIMO) case. Classical fuzzy logic control requires tuning input scale factors off-line through trial and error techniques. This is time-consuming and cannot adapt to new changes in the process. The new adaptive FLC includes a self-tuning scheme for choosing the scaling factors on-line. Further the rule base in classical FLC is usually produced by soliciting knowledge from human operators as to what is good control action for given circumstances. This usually requires full knowledge and experience of the process and operating conditions, which limits applicability. A self-learning scheme is developed which adaptively forms the rule base with very limited knowledge of the process. Finally, a MIMO method is presented employing optimization techniques. This is required for application to space robotics in which several degrees-of-freedom links are commonly used. Simulation examples are presented for terminal control - typical of robotic problems in which a desired terminal point is to be reached for each link. Future activities will be to implement the MIMO adaptive FLC on an INTEL microcontroller-based circuit and to test the algorithm on a robotic system at the Mars Mission Research Center at North Carolina State University.

Lee, Gordon↗

Accelerate microstructure evolution simulation using graph neural networks with adaptive spatiotemporal resolution

Abstract Surrogate models driven by sizeable datasets and scientific machine-learning methods have emerged as an attractive microstructure simulation tool with the potential to deliver predictive microstructure evolution dynamics with huge savings in computational costs. Taking 2D and 3D grain growth simulations as an example, we present a completely overhauled computational framework based on graph neural networks with not only excellent agreement to both the ground truth phase-field methods and theoretical predictions, but enhanced accuracy and efficiency compared to previous works based on convolutional neural networks. These improvements can be attributed to the graph representation, both improved predictive power and a more flexible data structure amenable to adaptive mesh refinement. As the simulated microstructures coarsen, our method can adaptively adopt remeshed grids and larger timesteps to achieve further speedup. The data-to-model pipeline with training procedures together with the source codes are provided.

36 MATERIALS SCIENCE↗

Adaptation and readaptation medical concerns of a Mars trip

The ability of the human body to adapt to microgravity environments and to later readapt to a gravity environment was examined. Issues specifically relating to the effects of long duration space flight on the adaptation/readaptation process are discussed. The need for better health prediction techniques is stressed in order to be able to better anticipate crew health problems and to perform corrective actions. Several specific examples are discussed of latent diseases which could occur during a long duration space mission, even after having subjected the crew to thorough premission checkups. The need for learning how to prevent or ameliorate such problems as space adaptation syndrome, bone and muscle (and possibly tissue) atrophy, immune system atrophy, and heart arrythmias is also discussed. The implications of the age of the crew, the influence of an onboard low level gravity field, and drugs are briefly addressed as factors in the adaptation/readaptation process.

Johnson, Philip C.↗

Dial

A key step in almost all scientific endeavors is answering the question: Given this data I already collected, what new data do I expect will yield the most useful information toward my scientific objective? The area of (sequential) experimental design has long been investigating answers to this question, but in recent years techniques from the machine learning subfield of active learning are increasingly applied. Researchers need a simple software tool for active learning applied to experimental design that can easily integrate into their existing workflows. This computer code, Dial, provides a microservice in ORNL's INTERSECT ecosystem for active learning applied to experimental design. By being part of the INTERSECT ecosystem, Dial is simple to integrate into any INTERSECT-based workflow. Dial provides multiple backend options, where a backend is an implementation of a specific active learning method. Users can select the backend that performs best for their application. Developers can also add new backends as needed. At its core, Dial receives a set of pre-existing measurements and input parameter bounds and then recommends one or more new sets of parameters to measure. Dial also includes interfaces to other microservices in the INTERSECT ecosystem so that it can be incorporated into INTERSECT campaigns. Dial provides a simple, yet powerful interface to convert automated INTERSECT workflows into autonomous workflows that adapt based on the results that are obtained. A shared microservice for active learning prevents duplicated effort by each application team implementing its own adaptive design of experiments tool.

Drane, Lance [Oak Ridge National Laboratory (ORNL)↗

DEVELOPMENT OF AN INFLIGHT COUNTERMEASURE TO MITIGATE POSTFLIGHT GAIT DYSFUNCTION

Following spaceflight crewmembers experience gait and postural instabilities due to inflight adaptive alterations in sensorimotor function. These changes can pose a risk to crew safety if nominal or emergency vehicle egress is required immediately following long-duration spaceflight. At present, no operational countermeasure is available to mitigate postflight locomotor disturbances. Therefore, the goal of this study is to develop an inflight training regimen that facilitates the recovery of locomotor function after long-duration spaceflight. The countermeasure we are developing is based on the concept of variable practice. During this type of training the subject gains experience producing the appropriate adaptive motor behavior under a variety of sensory conditions and response constraints. This countermeasure is built around current ISS treadmill exercise activities. Crewmembers will conduct their nominal inflight treadmill exercise while being exposed to variations in visual flow patterns. These variations will challenge the postural and locomotor systems repeatedly, thereby promoting adaptive reorganization in locomotor behavior. As a result of this training a subject learns to solve a class of motor problems, rather than a specific motor solution to one problem, Le., the subject learns response generalizability or the ability to "learn to learn" under a variety of environmental constraints. We anticipate that this training will accelerate recovery of postural and locomotor function during readaptation to gravitational environments following spaceflight facilitating neural adaptation to unit (Earth) and partial (Mars) gravity after long-duration spaceflight. The study calls for one group of subjects to perform the inflight treadmill training regimen while a control group of subjects performs only the nominal exercise procedures. Locomotor function in both groups is assessed before and after spaceflight using two tests of gait function: The Integrated Treadmill Locomotion Test (ITLT) and the Functional Mobility Test (FMT). The ITLT characterizes alterations in the integrated function of multiple sensorimotor subsystems responsible for the control of locomotion. This test calls for subjects to walk on a motorized treadmill while we assess changes in dynamic postural stability, head-trunk coordination, short-latency head stabilization responses, dynamic visual acuity, lower limb coordination strategies and gait cycle timing. To make these assessments we measure the following parameters while subjects walk on the treadmill: 1) full body 3-dimensional kinematics using a motion capture system (Motion Analysis Corp., Santa Rosa, CA); 2) the shock-wave transmitted from heel-strike to the head using triaxial accelerometers placed on the tibia and head (Entran, Fairfield, NJ); 3) vertical forces using an instrumented treadmill (Kistler Instrument Corp., Amherst, NY); 4) Dynamic visual acuity using Landolt Cs presented on a laptop computer located 4m from the eyes and 5) Gait cycle timing using foot-switches (Motion Lab Systems, Inc., Baton Rouge, LA) attached to the plantar surface of each shoe at the heel and toe. The FMT evaluates a subject's ability to perform challenging locomotor maneuvers similar to those encountered during an egress from a space vehicle. Subjects step over and duck under obstacles along with negotiating a series of pylons set up on a base of 10 cm thick medium density foam. The dependent measures for the FMT are time to complete the course and the number of obstacles touched. To date, we have collected pre and postflight locomotion data from Expeditions 5-9 who will serve as part of the control group for this study. Preliminary results comparing the recovery rates in gait control sub-systems obtained from the ITLT and FMT performance showed two recovery patterns: 1) a concordant recovery trend between gait control parameters and FMT performance indicating a restitution pattern of recovery and 2) gait controecovery that lagged recovery in FMT performance suggesting that improvement in locomotor function was attained through a pattern of substitution. These data suggest that recovery of postflight locomotor function may occur through adaptive mechanisms that lead to either restitution or substitution of function. Understanding the modes of postflight readaptation has implications for countermeasure development and testing and in astronaut postflight rehabilitation.

Bloomberg, J. J.↗

Development of an Inflight Countermeasure to Mitigate Postflight Gait Dysfunction

Following spaceflight crewmembers experience gait and postural instabilities due to inflight adaptive alterations in sensorimotor function. These changes can pose a risk to crew safety if nominal or emergency vehicle egress is required immediately following long-duration spaceflight. At present, no operational countermeasure is available to mitigate postflight locomotor disturbances. Therefore, the goal of this study is to develop an inflight training regimen that facilitates the recovery of locomotor function after long-duration spaceflight. The countermeasure we are developing is based on the concept of variable practice. During this type of training the subject gains experience producing the appropriate adaptive motor behavior under a variety of sensory conditions and response constraints. This countermeasure is built around current ISS treadmill exercise activities. Crewmembers will conduct their nominal inflight treadmill exercise while being exposed to variations in visual flow patterns. These variations will challenge the postural and locomotor systems repeatedly, thereby promoting adaptive reorganization in locomotor behavior. As a result of this training a subject learns to solve a class of motor problems, rather than a specific motor solution to one problem, Le., the subject learns response generalizability or the ability to "learn to learn" under a variety of environmental constraints. We anticipate that this training will accelerate recovery of postural and locomotor function during readaptation to gravitational environments following spaceflight facilitating neural adaptation to unit (Earth) and partial (Mars) gravity after long-duration spaceflight. The study calls for one group of subjects to perform the inflight treadmill training regimen while a control group of subjects performs only the nominal exercise procedures. Locomotor function in both groups is assessed before and after spaceflight using two tests of gait function: The Integrated Treadmill Locomotion Test (ITLT) and the Functional Mobility Test (FMT). The ITLT characterizes alterations in the integrated function of multiple sensorimotor subsystems responsible for the control of locomotion. This test calls for subjects to walk on a motorized treadmill while we assess changes in dynamic postural stability, head-trunk coordination, short-latency head stabilization responses, dynamic visual acuity, lower limb coordination strategies and gait cycle timing. To make these assessments we measure the following parameters while subjects walk on the treadmill: 1) full body 3-dimensional kinematics using a motion capture system (Motion Analysis Corp., Santa Rosa, CA); 2) the shock-wave transmitted from heel-strike to the head using triaxial accelerometers placed on the tibia and head (Entran, Fairfield, NJ); 3) vertical forces using an instumented treadmill (Kistler Instrument Corp., Amherst, NY); 4) Dynamic visual acuity using Landolt Cs presented on a laptop computer located 4m from the eyes and 5) Gait cycle timing using foot-switches (Motion Lab Systems, Inc., Baton Rouge, LA) attached to the plantar surface of each shoe at the heel and toe. The FMT evaluates s. subject's ability to perform challenging locomotor maneuvers similar to those encountered during an egress from a space vehicle. Subjects step over and duck under obstacles along with negotiating a series of pylons set up on a base of 10 cm thick medium density foam. The dependent measures for the FMT are time to complete the course and the number of obstacles touched. To date, we have collected pre and postflight locomotion data from Expeditions 5-9 who will serve as part of the control group for this study. Preliminary results comparing the recovery rates in gait control sub-systems obtained from the ITLT and FMT performance showed two recovery patterns: 1) a concordant recovery trend between gait control parameters and FMT performance indicating a restitution pattern of recovery and 2) gait controecovery that lagged recovery in FMT performance suggesting that improvement in locomotor function was attained through a pattern of substitution. These data suggest that recovery of postflight locomotor function may occur through adaptive mechanisms that lead to either restitution or substitution of function. Understanding the modes of postflight readaptation has implications for countermeasure development and testing and in astronaut postflight rehabilitation.

Bloomberg, J. J.↗

Evaluating the causes of cost reduction in photovoltaic modules

Photovoltaic (PV) module costs have declined rapidly over forty years but the reasons remain elusive. Here we advance a conceptual framework and quantitative method for quantifying the causes of cost changes in a technology, and apply it to PV modules. Our method begins with a cost model that breaks down cost into variables that changed over time. Cost change equations are then derived to quantify each variable's contribution. We distinguish between changes observed in variables of the cost model – which we term low-level mechanisms of cost reduction – and research and development, learning-by-doing, and scale economies, which we refer to as high-level mechanisms. We find that increased module efficiency was the leading low-level cause of cost reduction in 1980–2012, contributing almost 25% of the decline. Government-funded and private R&D was the most important high-level mechanism over this period. After 2001, however, scale economies became a more significant cause of cost reduction, approaching R&D in importance. Policies that stimulate market growth have played a key role in enabling PV's cost reduction, through privately-funded R&D and scale economies, and to a lesser extent learning-by-doing. The method presented here can be adapted to retrospectively or prospectively study many technologies, and performance metrics besides cost.

14 SOLAR ENERGY↗

Accelerating phase field simulations through a hybrid adaptive Fourier neural operator with U-net backbone

Prolonged contact between a corrosive liquid and metal alloys can cause progressive dealloying. For one such process as liquid-metal dealloying (LMD), phase field models have been developed to understand the mechanisms leading to complex morphologies. However, the LMD governing equations in these models often involve coupled non-linear partial differential equations (PDE), which are challenging to solve numerically. In particular, numerical stiffness in the PDEs requires an extremely refined time step size (on the order of 10 -12 s or smaller). This computational bottleneck is especially problematic when running LMD simulation until a late time horizon is required. This motivates the development of surrogate models capable of leaping forward in time, by skipping several consecutive time steps at-once. In this paper, we propose a U-shaped adaptive Fourier neural operator (U-AFNO), a machine learning (ML) based model inspired by recent advances in neural operator learning. U-AFNO employs U-Nets for extracting and reconstructing local features within the physical fields, and passes the latent space through a vision transformer (ViT) implemented in the Fourier space (AFNO). We use U-AFNOs to learn the dynamics of mapping the field at a current time step into a later time step. We also identify global quantities of interest (QoI) describing the corrosion process (e.g., the deformation of the liquid-metal interface, lost metal, etc.) and show that our proposed U-AFNO model is able to accurately predict the field dynamics, in spite of the chaotic nature of LMD. Most notably, our model reproduces the key microstructure statistics and QoIs with a level of accuracy on par with the high-fidelity numerical solver, while achieving a significant 11, 200 × speed-up on a high-resolution grid when comparing the computational expense per time step. Finally, we also investigate the opportunity of using hybrid simulations, in which we alternate forward leaps in time using the U-AFNO with high-fidelity time stepping. We demonstrate that while advantageous for some surrogate model design choices, our proposed U-AFNO model in fully auto-regressive settings consistently outperforms hybrid schemes.

36 MATERIALS SCIENCE↗

A Neural Optimizer With Decision-Focused Learning for Optimal Energy Storage Operation

Here, this article introduces a neural optimizer-based framework for optimizing battery energy storage system (BESS) control for grid services, including demand charge and energy cost reduction. By leveraging decision-focused learning (DFL), the proposed framework ensures seamless integration and adaptation, significantly enhancing control performance. A patch time-series transformer is employed for peak load forecasting, incorporating aleatoric uncertainty quantification to account for forecasting uncertainties within the decision-making process. The framework utilizes a solver-in-the-loop approach to generate optimal BESS actions, which are then used to train the neural optimizer-based agent. By co-optimizing both BESS operational modes and output power within the NN, the system achieves improved performance and robustness. After initial training, the forecasting and control models are jointly fine-tuned to account for forecasting errors, further improving decision precision and efficiency through DFL. Case studies are performed to validate the performance of the framework using multiple real-world datasets, demonstrating superior performance in monthly peak load forecasting compared to state-of-the-art models. In addition, the results are compared against existing decision-making approaches. The results demonstrate a reduction in monthly peak forecasting error by approximately 15% across various performance measures and achieve an optimization gap for BESS operation that is about three times smaller compared to existing methods.

Kim, Hyeonjin [Pacific Northwest National Laborato↗

Deep Reinforcement Scheduling of Energy Storage Systems for Real-time Voltage Regulation in Unbalanced LV Networks with High PV Penetration

The ever-growing higher penetration of distributed energy resources (DERs) in low-voltage (LV) distribution systems brings both opportunities and challenges to voltage support and regulation. This paper proposes a deep reinforcement learning (DRL)-based scheduling scheme of energy storage systems (ESSs) to mitigate system voltage deviations in unbalanced LV distribution networks. The ESS-based voltage regulation problem is formulated as a multi-stage quadratic stochastic program, with the objective of minimizing the expected total daily voltage regulation cost while satisfying operational constraints. While existing voltage regulation methods are mostly focused on onetime- step control, this paper explores a day-horizon systemwide voltage regulation problem. In other words, the size of action and state spaces are extremely high-dimensional and need to be delicately handled. Furthermore, in order to overcome the difficulty of modeling uncertainties and develop a realtime solution, a learn-to-schedule feedback control framework is proposed by adapting the problem to a model-free DRL setting. The proposed algorithm is tested on a customized 6-bus system and a modified IEEE 34-bus system. Simulation results validate the effectiveness and near-optimality of voltage regulation by ESS in comparison with a deterministic quadratic program solution.

Wang, Shengyi↗

Lessons learned on the Skylab program

Lessons learned in the Skylab program and their application and adaptation to other space programs are summarized. Recommendations and action taken on particular problems are described. The use of Skylab recommendations to identify potential problems of future space programs is discussed.

Source record↗

Distributed memory approaches for robotic neural controllers

The suitability is explored of two varieties of distributed memory neutral networks as trainable controllers for a simulated robotics task. The task requires that two cameras observe an arbitrary target point in space. Coordinates of the target on the camera image planes are passed to a neural controller which must learn to solve the inverse kinematics of a manipulator with one revolute and two prismatic joints. Two new network designs are evaluated. The first, radial basis sparse distributed memory (RBSDM), approximates functional mappings as sums of multivariate gaussians centered around previously learned patterns. The second network types involved variations of Adaptive Vector Quantizers or Self Organizing Maps. In these networks, random N dimensional points are given local connectivities. They are then exposed to training patterns and readjust their locations based on a nearest neighbor rule. Both approaches are tested based on their ability to interpolate manipulator joint coordinates for simulated arm movement while simultaneously performing stereo fusion of the camera data. Comparisons are made with classical k-nearest neighbor pattern recognition techniques.

Jorgensen, Charles C.↗

Towards a Self-Configuring Optimization System for Spacecraft Design

In this paper, we propose the use of a set of generic, metaheuristic optimization algorithms, which is configured for a particular optimization problem by an adaptive problem solver based on artificial intelligence and machine learning techniques. We describe work in progress on these principles.

Metaheuristic Optimization Algorithm OASIS↗

Cascade Error Projection: An Efficient Hardware Learning Algorithm

A new learning algorithm termed cascade error projection (CEP) is presented. CEP is an adaption of a constructive architecture from cascade correlation and the dynamical stepsize of A/D conversion from the cascade back propagation algorithm.

learning algorithm pattern recognition cascade err↗

Space Telecommunications Radio System STRS Cognitive Radio

Radios today are evolving from awareness toward cognition. A software defined radio (SDR) provides the most capability for integrating autonomic decision making ability and allows the incremental evolution toward a cognitive radio. This cognitive radio technology will impact NASA space communications in areas such as spectrum utilization, interoperability, network operations, and radio resource management over a wide range of operating conditions. NASAs cognitive radio will build upon the infrastructure being developed by Space Telecommunication Radio System (STRS) SDR technology. This paper explores the feasibility of inserting cognitive capabilities in the NASA STRS architecture and the interfaces between the cognitive engine and the STRS radio. The STRS architecture defines methods that can inform the cognitive engine about the radio environment so that the cognitive engine can learn autonomously from experience, and take appropriate actions to adapt the radio operating characteristics and optimize performance.

Briones, Janette C.↗

FJET Database Project: Extract, Transform, and Load

The Data Mining & Knowledge Management team at Kennedy Space Center is providing data management services to the Frangible Joint Empirical Test (FJET) project at Langley Research Center (LARC). FJET is a project under the NASA Engineering and Safety Center (NESC). The purpose of FJET is to conduct an assessment of mild detonating fuse (MDF) frangible joints (FJs) for human spacecraft separation tasks in support of the NASA Commercial Crew Program. The Data Mining & Knowledge Management team has been tasked with creating and managing a database for the efficient storage and retrieval of FJET test data. This paper details the Extract, Transform, and Load (ETL) process as it is related to gathering FJET test data into a Microsoft SQL relational database, and making that data available to the data users. Lessons learned, procedures implemented, and programming code samples are discussed to help detail the learning experienced as the Data Mining & Knowledge Management team adapted to changing requirements and new technology while maintaining flexibility of design in various aspects of the data management project.

excel vba↗