SEARCH · Search NASA

Results for “Training Principles”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 235 records · Page 13

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Thermodynamics-informed latent space dynamics identification

This software showcases a latent space dynamics identification method, namely tLaSDI, that embeds the first and second principles of thermodynamics. The latent variables are learned through an autoencoder as a nonlinear dimension reduction model. The latent dynamics are constructed by a neural network-based model that precisely preserves certain structures for the thermodynamic laws through the GENERIC formalism. An abstract error estimate is established, which provides a new loss formulation involving the Jacobian computation of autoencoder. The autoencoder and the latent dynamics are simultaneously trained to minimize the new loss. Computational examples demonstrate the effectiveness of tLaSDI, which exhibits robust generalization ability, even in extrapolation. In addition, an intriguing correlation is empirically observed between a quantity from tLaSDI in the latent space and the behaviors of the full-state solution.

Cheung, Siu Wun↗

NASA NTRSDate not supplied

Crew Performance Support System to Aid in Anomaly Resolution: Concept of Operations

As missions progress into deep space, communication delays and disruptions will disenable the crew’s reliance on Earth experts. There are also limitations in the amount of data that can be downlinked to the ground. It is prudent to assume that critical, complex vehicle or habitat sub-systems will malfunction at a time when a lunar or Mars’ crew cannot rely on the Earth-Support team to detect, diagnose and resolve the problem and it is impractical to expect a small crew to step-in with the same level of expertise as 50+ authorities. The crew will need novel processes and advanced technological support to independently identify and resolve safety- and time-critical anomalies. That a self-reliant crew is unable to respond appropriately to time-critical anomalies is a significant risk to crew safety and mission success. This risk is driven by several factors; novel and unanticipated anomalies would not have been trained pre-flight, the crew could forget their pre-flight training or spaceflight stressors could impair the crew’s problem-solving ability. At last year’s IWS, Beard reported that a single spaceflight stressor (elevated CO2) could undermine the crew’s ability to independently respond to emergencies. Concept of Operations (ConOps) provide a common view of future system functions to all stakeholders. For the current project, a ConOps was developed that describes the operational processes, practices and capabilities needed by a crew of astronauts on deep space missions to autonomously respond to anticipated and unanticipated anomalies. It is crucial to recognize that, as of August 2018 existing technologies are unable to effectively support crew anomaly response to unanticipated events. “Intelligent technology” has not reached a maturity level that permits generalizing a solution to novel situations. For example, to train intelligent technology requires volumes of data that do not exist. The complexities involved in a manned mission to Mars cannot be compared to sending rovers to Mars using scripted software. This ConOps proposes a Crew Performance Support System (CPSS) that will push NASA and its industry partners toward what will be required for a safe and successful manned mission to Mars. Anomaly resolution during a deep space mission will take place within a dynamic, or changing, context. The figure to the left shows five broad contextual variables: the organizational culture, mission context, system characteristics, team characteristics and individual characteristics. The yellow arrow indicates that spaceflight and task-related stressors can affect system, team and individual crewmember characteristics and therefore anomaly response potential. The figure depicts a protective umbrella of Human-System Integration (HSI) principles that should be instituted during CPSS development including a balanced workload, shared situation awareness and building an appropriate level of trust in the automation. The figure also depicts two interrelated and cooperative components, an HSI Data System and other Enabling Capabilities will be required to support crew anomaly response and Earth-Support situation awareness. As we journey from ISS to Gateway to Mars, multiple, simultaneous and integrated research and development efforts (i.e., support systems co-evolution) must be implemented to meet the problem-solving challenges a self-reliant crew will face on a Mars’ mission. The crossovers between the capabilities are just as important as the discrete capabilities themselves. As the capabilities mature, the lines between the support subdomains will blur and an integrated system will emerge. The ConOps summarizes current knowledge about how highly trained people solve anomalies in safety- and time-critical situations, describes a group of capabilities that could help to reduce the extant risk and documents requirements levied on additional systems that provides critical inputs to the CPSS. Scenarios are used to promote a shared understanding of processes, practices and technological goals needed for safe and productive manned missions beyond LEO.

HSIA risk↗

DOE OSTI2025

Functional protein mining with conformal guarantees

Molecular structure prediction and homology detection offer promising paths to discovering protein function and evolutionary relationships. However, current approaches lack statistical reliability assurances, limiting their practical utility for selecting proteins for further experimental and in-silico characterization. To address this challenge, we introduce a statistically principled approach to protein search leveraging principles from conformal prediction, offering a framework that ensures statistical guarantees with user-specified risk and provides calibrated probabilities (rather than raw ML scores) for any protein search model. Our method (1) lets users select many biologically-relevant loss metrics (i.e. false discovery rate) and assigns reliable functional probabilities for annotating genes of unknown function; (2) achieves state-of-the-art performance in enzyme classification without training new models; and (3) robustly and rapidly pre-filters proteins for computationally intensive structural alignment algorithms. Our framework enhances the reliability of protein homology detection and enables the discovery of uncharacterized proteins with likely desirable functional properties.

59 BASIC BIOLOGICAL SCIENCES↗

NASA NTRS1988

Human factors in aviation

The fundamental principles of human-factors (HF) analysis for aviation applications are examined in a collection of reviews by leading experts, with an emphasis on recent developments. The aim is to provide information and guidance to the aviation community outside the HF field itself. Topics addressed include the systems approach to HF, system safety considerations, the human senses in flight, information processing, aviation workloads, group interaction and crew performance, flight training and simulation, human error in aviation operations, and aircrew fatigue and circadian rhythms. Also discussed are pilot control; aviation displays; cockpit automation; HF aspects of software interfaces; the design and integration of cockpit-crew systems; and HF issues for airline pilots, general aviation, helicopters, and ATC.

Wiener, Earl L.↗

NASA NTRS1989

The principle of commonality and its application to the Space Station Freedom Program

The principle of commonality has achieved wide application in the communication, automotive, and aircraft industries. By the use of commonality, component development costs are minimized, logistics are simplified, and the investment costs of spares inventory are reduced. With space systems, which must be maintained and repaired in orbit, the advantages of commonality are compounded. Transportation of spares is expensive, on-board storage volume for spares is limited, and crew training and special tools needed for maintenance and repair are significant considerations. This paper addresses the techniques being formulated to realize the benefits of commonality in the design of the systems and elements of the Space Station Freedom Program, and include the criteria for determining the extent of commonality to be implemented.

Hopson, George D.↗

NASA NTRS1981

Symposium on Aviation Psychology, 1st, Ohio State University, Columbus, OH, April 21, 22, 1981, Proceedings

The impact of modern technology on the role, responsibility, authority, and performance of human operators in modern aircraft and ATC systems was examined in terms of principles defined by Paul Fitts. Research into human factors in aircraft operations and the use of human factors engineering for aircraft safety improvements were discussed, and features of the man-machine interface in computerized cockpit warning systems are examined. The design and operational features of computerized avionics displays and HUDs are described, along with results of investigations into pilot decision-making behavior, aircrew procedural compliance, and aircrew judgment training programs. Experiments in vision and visual perception are detailed, as are behavioral studies of crew workload, coordination, and complement. The effectiveness of pilot selection, screening, and training techniques are assessed, as are methods for evaluating pilot performance.

Source record↗

NASA NTRS2016

DeepSAT: A Deep Learning Approach to Tree-Cover Delineation in 1-m NAIP Imagery for the Continental United States

High resolution tree cover classification maps are needed to increase the accuracy of current land ecosystem and climate model outputs. Limited studies are in place that demonstrates the state-of-the-art in deriving very high resolution (VHR) tree cover products. In addition, most methods heavily rely on commercial softwares that are difficult to scale given the region of study (e.g. continents to globe). Complexities in present approaches relate to (a) scalability of the algorithm, (b) large image data processing (compute and memory intensive), (c) computational cost, (d) massively parallel architecture, and (e) machine learning automation. In addition, VHR satellite datasets are of the order of terabytes and features extracted from these datasets are of the order of petabytes. In our present study, we have acquired the National Agriculture Imagery Program (NAIP) dataset for the Continental United States at a spatial resolution of 1-m. This data comes as image tiles (a total of quarter million image scenes with ~60 million pixels) and has a total size of ~65 terabytes for a single acquisition. Features extracted from the entire dataset would amount to ~8-10 petabytes. In our proposed approach, we have implemented a novel semi-automated machine learning algorithm rooted on the principles of "deep learning" to delineate the percentage of tree cover. Using the NASA Earth Exchange (NEX) initiative, we have developed an end-to-end architecture by integrating a segmentation module based on Statistical Region Merging, a classification algorithm using Deep Belief Network and a structured prediction algorithm using Conditional Random Fields to integrate the results from the segmentation and classification modules to create per-pixel class labels. The training process is scaled up using the power of GPUs and the prediction is scaled to quarter million NAIP tiles spanning the whole of Continental United States using the NEX HPC supercomputing cluster. An initial pilot over the state of California spanning a total of 11,095 NAIP tiles covering a total geographical area of 163,696 sq. miles has produced true positive rates of around 88 percent for fragmented forests and 74 percent for urban tree cover areas, with false positive rates lower than 2 percent for both landscapes.

Imagery↗

DOE OSTI2024

FiberFlex: Real-time FPGA-based Intelligent and Distributed Fiber Sensor System for Pedestrian Recognition

In recent years, security monitoring of public places and critical infrastructure has heavily relied on the widespread use of cameras, raising concerns about personal privacy violations. To balance the need for effective security monitoring with the protection of personal privacy, we explore the potential of optical fiber sensors for this application. This article proposes FiberFlex, an intelligent and distributed fiber sensor system. Ultizing Field Programmable Gate Arrays (FPGA) high-level synthesis (HLS) acceleration, FiberFlex offers real-time pedestrian detection by co-designing the entire pipeline of optical signal acquisition, processing, and recognition networks based on the principles of optical fiber sensing. As a promising alternative to traditional camera-based monitoring systems, FiberFlex achieves pedestrian detection by analyzing the vibration patterns caused by pedestrian footsteps, enabling security monitoring while preserving individual privacy. FiberFlex comprises three modules: First , fiber-optic sensing system: A fiber-optic distributed acoustic sensing (DAS) system is built and used to measure the ground vibration waves generated by people walking. Second , algorithms: We first collect the training data by measuring the ground vibration waves, label the data, and use the data to train the neural network models to perform pedestrian recognition. Third , hardware accelerators: We use HLS tools to design hardware modules on FPGA for data collection and pre-processing and integrate them with the downstream neural network accelerators to perform in-line real-time pedestrian detection. The final detection results are sent back from FPGA to the host CPU. We implement our system FiberFlex with the in-house built DAS system and AMD/Xilinx Kintex7 FPGA KC705 board and verify the whole system using the real-world collected data. We conduct recognition tests on five test subjects of varying ages, heights, and weights in a fixed sensing area. Each subject experienced 20 real-time recognition tests using their daily walking habits, and the subjects were given adequate rest between tests. After 100 tests on five test subjects, the overall real-time recognition accuracy exceeded \(88.0\%\) . The whole system uses 55 W of power, 33 W in the optical DAS system and 22 W in the FPGA. Relying on its end-to-end interdisciplinary design, FiberFlex seamlessly combines fiber-optic sensors with FPGA accelerators to enable low-power real-time security monitoring without compromising privacy, making it a valuable addition to the existing security monitoring network. According to FiberFlex, more valuable research can be conducted in the future, such as fall monitoring for the elderly, migration of identification networks between different application scenarios, and improvement of anti-interference performance in more complex environments. In future perception networks, where the “eyes” are not feasible, let’s use fiber optic touch instead.

Distributed↗

DOE OSTI2026

Machine learning inversion of interatomic force constants from single-crystal inelastic neutron scattering

Atomic vibrations govern many macroscopic properties of materials, but experiments to comprehensively probe them remain challenging. Inelastic neutron scattering (INS) is a powerful technique to map phonon dispersions in crystals, especially when leveraging modern time-of-flight (ToF) spectrometers with large detectors. However, efficiently and robustly extracting interatomic force constants (FCs) parameterizing phonon dynamics from experimental spectra remains a bottleneck due to the complexity and high dimensionality of ToF INS datasets. Here, we present a machine learning approach for the direct inversion of FCs from single-crystal INS measurements. The framework leverages synthetic training data generated using universal machine-learned force fields and an efficient physics-based forward model. We benchmark two neural architectures–one emphasizing structured latent representation learning and the other direct, supervised spectral regression–across simulated datasets for two materials under idealized and noisy conditions. The latent-representation model is subsequently applied to experimental single-crystal INS data on germanium. The model is shown to reproduce FCs derived from both first-principles simulations and from iterative optimization, and furthermore achieves reliable inference even from sparse, single-orientation measurements representing short data acquisitions. Analysis of the learned latent space reveals semantically continuous and physically interpretable encodings that support strong cross-domain generalization. By bridging theoretical and experimental domains, we establish a path toward rapid inversion of experimental spectra and data-driven interpretation of temperature-dependent lattice dynamics.

42 ENGINEERING↗

DOE OSTI2025

The Past, Present and Future of Structural Health Monitoring: An Overview of Three Ages

This paper presents an overview of the discipline of structural health monitoring (SHM), organised in terms of three proposed ages. The first age is delineated by the prehistory of SHM and the period where nondestructing testing methods evolved into an organised set of principles built upon physics-based models; this age ended when the model-based approaches reached an impasse in terms of their ability to properly deal with real-world problems. The second age of SHM began with a transition to data-based methods based on statistical pattern recognition, which provided a holistic approach to SHM problems for the first time. This age arguably ended when the methods foundered in situations where the necessary training data were scarce. It is argued here that the third age began with the development of population-based SHM, which has been designed to overcome the problem of data scarcity. As there is very limited space in a single article to provide a comprehensive overview, an appendix has been provided here that gives a very systematic bibliography of SHM reviews—a meta-bibliography.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2024

Deep learning-based predictive models for laser direct drive at the Omega Laser Facility

The rich and complex physics of inertial confinement fusion provides a unique and challenging space for high-fidelity first-principles modeling. Consequently, simulation codes that are used to design experiments are computationally expensive and lack the predictive capability required for extensive parameter exploration in search of a high-performing design for laser direct drive. In this article, we present two deep-learning-based predictive models intended to address these difficulties. The first model (TL DNN) acts as a fast emulator of simulations as well as experiments at the Omega Laser Facility. This model is trained on a simulation database and subsequently calibrated on experimental data using transfer learning. To facilitate the development of this model, an autoencoder is developed to reduce the dimensionality of the input space by compressing the laser pulse input. The model predicts key experimental scalar observables of Omega experiments with high accuracy and minimal computational cost. This deep neural net enables rapid exploration of a high-dimensional input parameter space for an optimal implosion design. The second model (DNN SM+) aims to extend the statistical modeling work of Lees et al. [Phys. Rev. Lett. 127, 105001 (2021)], by increasing the complexity of the model space and allowing for coupling between degradation terms. Since the model capacity of DNN SM+ is higher than the model of Lees et al., DNN SM+ can potentially provide an improvement in predictive capability, and we use this model to provide insight into complicated degradation dependencies.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

NASA NTRSDate not supplied

Hybrid Model Based Approaches for Systems Health Management and Prognostics

To facilitate and solve the prediction problem, awareness of the current health state of the system is key, since it is necessary to perform condition-based predictions. To accurately predict the future state of any system, it is required to possess knowledge of its current health state and future operational conditions. Latest achievements of data-driven algorithms in regression of complex nonlinear functions and classification tasks have generated a growing interest in artificial intelligence for industrial applications. Complex multi-physics models as well as digital twins, once purely built on physics and corresponding simplified lumped parameter iterations, can now benefit from machine learning algorithms to mitigate the lack of understanding of some complex behavior. Given models of the current and future system behavior, a general approach of model-based prognostics can solve the prediction problem and further decision making. In principle, data driven approaches can replace expensive experimental test-setups as well as reduce the number of simulations needed to explore, e.g., the parametric space of a multi-parameter model. Nonetheless, the limitations of pure data-driven methods came to light rather quickly, at least for some industries. In many industrial applications, data acquisition is costly, and the volume of data that can be collected does not satisfy the requirements for an effective model training and cross-validation. Therefore, some recent works in the area of machine learning is focusing on blending physics with data-driven algorithms, thus mitigating the drawbacks of the two approaches and emphasizing respective advantages. Partial physical knowledge of the problem can aid the learning process by “guiding” the algorithm towards efficient solutions that satisfy the physics driving the system behavior. The result is a hybrid modeling approach combining physical knowledge as well data driven methods to develop a unified hybrid approach. A hybrid framework for fusing information from physics-based performance models along with deep learning algorithms for prognostics of complex safety critical systems is presented. In this framework, physics-based performance models infer unobservable model parameters related to the system's components health solving a calibration problem in the deep learning approach.

Hybrid Modeling↗

NASA NTRSDate not supplied

Hybrid Approaches to Systems Health Management and Prognostics

Systems Health Management↗

NASA NTRS2022

Hybrid Model Based Approaches for Systems Health Management and Prognostics

This is a previously approved and published presentation. To accurately predict the future state of any system, it is required to possess knowledge of its current health state and future operational conditions. Present achievements of data-driven algorithms in regression of complex nonlinear functions and classification tasks have generated a growing interest in artificial intelligence for industrial applications. Complex multi-physics models as well as digital twins, once purely built on physics and corresponding simplified lumped parameter iterations, can now benefit from machine learning algorithms to mitigate the lack of understanding of some complex behavior. Given models of the current and future system behavior, a general approach of model-based prognostics can solve the prediction problem and further decision-making. In principle, data-driven approaches can replace expensive experimental test-setups as well as reduce the number of simulations needed to explore, e.g., the parametric space of a multi-parameter model. Nonetheless, the limitations of pure data-driven methods came to light rather quickly, at least for some industries. In many industrial applications, data acquisition is costly, and the volume of data that can be collected does not satisfy the requirements for effective model training and cross-validation. Therefore, some recent works in the area of machine learning is focusing on blending physics with data-driven algorithms, thus mitigating the drawbacks of the two approaches and emphasizing respective advantages. Partial physical knowledge of the problem can aid the learning process by “guiding” the algorithm towards efficient solutions that satisfy the physics driving the system behavior. The result is a hybrid modeling approach combining physical knowledge as well data-driven methods to develop a unified hybrid approach. A hybrid framework for fusing information from physics-based performance models along with deep learning algorithms for prognostics of complex safety-critical systems is presented. In this framework, physics-based performance models infer unobservable model parameters related to the system's components health solving a calibration problem in the deep learning approach.

Prognostics↗

NASA NTRSDate not supplied

NASA’s Safety, Reliability, and Mission Assurance Digital Future

The evolution from “document-centric” to “data-centric” and “model-centric” information leveraging structured data and model-based approaches is at the heart of digital engineering transformational efforts underway across industry and government. It is these approaches that pave the way for data lakes, Authoritative Sources of Truth (ASOTs), and systems- of-systems interoperability and the corresponding transformational benefits thereof. Such benefits include increased data availability, data access equity, data traceability, real-time analytics, batch analytics, and (most importantly) acceleration of the time-to-value and time-to-insights associated with engineering products and analyses. The longer-term benefits of reusability, customization and traceability are even more promising. For Safety and Mission Assurance (SMA), and Mission Success (SMS) activities; realization of such benefits is essential to provide engineers and analysts alike vital information when needed to support critical decision making throughout the entire life cycle. The SMA community often operate in parallel with engineering activities, for which information exchange with relevant context is paramount. Far too often, such information lags key decision points and/or is absent of the robust, integrated, knowledge needed, given inherent barriers associated with traditional document-centric means to data sharing, analysis, and reporting. This paper provides an overview of how NASA’s Office of Safety and Mission Assurance (OSMA) is evolving its policies, standards, guidance, and training to transform to eliminate such barriers, thus realizing the benefits emerging in this new digital era. A roadmap for achieving this digital future is presented along with key building blocks involving use and implementation of concepts such as: Objectives-Hierarchies, Objective-Driven Requirements, Accepted Standards, Safety and Assurance Cases, data digitization (i.e., ontologies, structured data, and model-centric data), FAIR (Findable, Accessible, Interoperable, & Reusable) and/or FAIRUST (Findable, Accessible, Interoperable, Reusable, Understandable, Secure, and Trusted) principles [1]. This paper also describes how OSMA, leveraging the Agency’s overall commitment to Digital Transformation (DT), is using the power of Policy, “Digital” Domain representation, Product Evolution, and Community Outreach and Engagement as part of a strategic vision and roadmap to evolve and transform its SMA organizations to become better able to serve its stakeholders and customers. Future publications will elaborate on these building blocks and deeper concepts.

Authoritative Source of Truth (ASOT),↗

DOE OSTI2024

BindingDB in 2024: a FAIR knowledgebase of protein-small molecule binding data

Abstract BindingDB (bindingdb.org) is a public, web-accessible database of experimentally measured binding affinities between small molecules and proteins, which supports diverse applications including medicinal chemistry, biochemical pathway annotation, training of artificial intelligence models and computational chemistry methods development. This update reports significant growth and enhancements since our last review in 2016. Of note, the database now contains 2.9 million binding measurements spanning 1.3 million compounds and thousands of protein targets. This growth is largely attributable to our unique focus on curating data from US patents, which has yielded a substantial influx of novel binding data. Recent improvements include a remake of the website following responsive web design principles, enhanced search and filtering capabilities, new data download options and webservices and establishment of a long-term data archive replicated across dispersed sites. We also discuss BindingDB’s positioning relative to related resources, its open data sharing policies, insights gleaned from the dataset and plans for future growth and development.

Liu, Tiqing↗

NASA NTRS1990

Fuzzy logic in control systems: Fuzzy logic controller. I, II

Recent advances in the theory and applications of fuzzy-logic controllers (FLCs) are examined in an analytical review. The fundamental principles of fuzzy sets and fuzzy logic are recalled; the basic FLC components (fuzzification and defuzzification interfaces, knowledge base, and decision-making logic) are described; and the advantages of FLCs for incorporating expert knowledge into a control system are indicated. Particular attention is given to fuzzy implication functions, the interpretation of sentence connectives (and, also), compositional operators, and inference mechanisms. Applications discussed include the FLC-guided automobile developed by Sugeno and Nishida (1985), FLC hardware systems, FLCs for subway trains and ship-loading cranes, fuzzy-logic chips, and fuzzy computers.

Lee, Chuen Chien↗

NASA NTRS1993

Parametric motion control of robotic arms: A biologically based approach using neural networks

A neural network based system is presented which is able to generate point-to-point movements of robotic manipulators. The foundation of this approach is the use of prototypical control torque signals which are defined by a set of parameters. The parameter set is used for scaling and shaping of these prototypical torque signals to effect a desired outcome of the system. This approach is based on neurophysiological findings that the central nervous system stores generalized cognitive representations of movements called synergies, schemas, or motor programs. It has been proposed that these motor programs may be stored as torque-time functions in central pattern generators which can be scaled with appropriate time and magnitude parameters. The central pattern generators use these parameters to generate stereotypical torque-time profiles, which are then sent to the joint actuators. Hence, only a small number of parameters need to be determined for each point-to-point movement instead of the entire torque-time trajectory. This same principle is implemented for controlling the joint torques of robotic manipulators where a neural network is used to identify the relationship between the task requirements and the torque parameters. Movements are specified by the initial robot position in joint coordinates and the desired final end-effector position in Cartesian coordinates. This information is provided to the neural network which calculates six torque parameters for a two-link system. The prototypical torque profiles (one per joint) are then scaled by those parameters. After appropriate training of the network, our parametric control design allowed the reproduction of a trained set of movements with relatively high accuracy, and the production of previously untrained movements with comparable accuracy. We conclude that our approach was successful in discriminating between trained movements and in generalizing to untrained movements.

Bock, O.↗