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 127 records · Page 7

All sources NASA NTRS DOE OSTI

NASA NTRS2012

Optimal Routing and Control of Multiple Agents Moving in a Transportation Network and Subject to an Arrival Schedule and Separation Constraints

We address the problem of navigating a set of moving agents, e.g. automated guided vehicles, through a transportation network so as to bring each agent to its destination at a specified time. Each pair of agents is required to be separated by a minimal distance, generally agent-dependent, at all times. The speed range, initial position, required destination, and required time of arrival at destination for each agent are assumed provided. The movement of each agent is governed by a controlled differential equation (state equation). The problem consists in choosing for each agent a path and a control strategy so as to meet the constraints and reach the destination at the required time. This problem arises in various fields of transportation, including Air Traffic Management and train coordination, and in robotics. The main contribution of the paper is a model that allows to recast this problem as a decoupled collection of problems in classical optimal control and is easily generalized to the case when inertia cannot be neglected. Some qualitative insight into solution behavior is obtained using the Pontryagin Maximum Principle. Sample numerical solutions are computed using a numerical optimal control solver.

Sadovsky, A. V.↗

NASA NTRS1996

Health Monitoring System for Composite Structures

An automated system was developed to monitor the health status of composites. It uses the vibration characteristics of composites to identify a component's damage condition. The vibration responses are characterized by a set of signal features defined in the time, frequency and spatial domains. The identification of these changes in the vibration characteristics corresponding to different health conditions was performed using pattern recognition principles. This allows efficient data reduction and interpretation of vast amounts of information. Test components were manufactured from isogrid panels to evaluate performance of the monitoring system. The components were damaged by impact to simulate different health conditions. Free vibration response was induced by a tap test on the test components. The monitoring system was trained using these free vibration responses to identify three different health conditions. They are undamaged vs. damaged, damage location and damage zone size. High reliability in identifying the correct component health condition was achieved by the monitoring system.

Tang, S. S.↗

NASA NTRS1978

Outline of cost-benefit analysis and a case study

The methodology of cost-benefit analysis is reviewed and a case study involving solar cell technology is presented. Emphasis is placed on simplifying the technique in order to permit a technical person not trained in economics to undertake a cost-benefit study comparing alternative approaches to a given problem. The role of economic analysis in management decision making is discussed. In simplifying the methodology it was necessary to restrict the scope and applicability of this report. Additional considerations and constraints are outlined. Examples are worked out to demonstrate the principles. A computer program which performs the computational aspects appears in the appendix.

Kellizy, A.↗

NASA NTRS1994

Preflight Adaptation Training for Spatial Orientation and Space Motion Sickness

Two part-task preflight adaptation trainers (PATs) are being developed at the NASA Johnson Space Center to preadapt astronauts to novel sensory stimulus conditions similar to those present in microgravity to facilitate adaptation to microgravity and readaptation to Earth. This activity is a major component of a general effort to develop countermeasures aimed at minimizing sensory and sensorimotor disturbances and Space Motion Sickness (SMS) associated with adaptation to microgravity and readaptation to Earth. Design principles for the development of the two trainers are discussed, along with a detailed description of both devices. In addition, a summary of four ground-based investigations using one of the trainers to determine the extent to which various novel sensory stimulus conditions produce changes in compensatory eye movement responses, postural equilibrium, motion sickness symptoms, and electrogastric responses are presented. Finally, a brief description of the general concept of dual-adopted states that underly the development of the PATs, and ongoing and future operational and basic research activities are presented.

Harm, Deborah L.↗

NASA NTRS2016

Neural Network (NN) Retrievals of Stratocumulus Cloud Properties Using Multiangle Polarimetric Observations During ORACLES

The ORACLES (ObseRvations of Aerosols above CLouds and their intEractionS) campaign is taking place in the SouthEast Atlantic during the Austral Spring for three consecutive years from 20162018. The study area encompasses one of the Earths three semipermanent subtropical Stratocumulus (Sc) cloud decks,and experiences very large aerosol optical depths, mainly biomass burning, originating from Africa. Over time, cloud optical depth (COD), lifetime and cloud microphysics (number concentration, effective radii Reff and precipitation) are expected to be influenced by indirect aerosol effects. These changes play a key role in the energetic balance of the region, and are part of the core investigation objectives of the ORACLES campaign, which acquires measurements of clean and polluted scenes of above cloud aerosols (ACA). Simultaneous retrievals of aerosol and cloud optical properties are being developed (e.g. MODIS, OMI), butstill challenging, especially for passive, single viewing angle instruments. By comparison, multiangle polarimetric instruments like RSP (Research Scanning Polarimeter) show promise for detection and quantification of ACA, however, there are no operational retrieval algorithms available yet. Here we describe anew algorithm to retrieve cloud and aerosol optical properties from observations by RSP flown on the ER2and P3 during the 2016 ORACLES campaign. The algorithm is based on training a NN, and is intended to retrieve aerosol and cloud properties simultaneously. However, the first step was to establish the retrievalscheme for low level Sc cloud optical properties. The NN training was based on simulated RSP total and polarized radiances for a range of COD, Reff, and effective variances, spanning 7 wavelength bands and 152 viewing zenith angles. Random and correlated noise were added to the simulations to achieve a morerealistic representation of the signals. Before introducing the input variables to the network, the signals are projected on a principle component plane that retains the maximal signal information but minimizes the noise contribution. We will discuss parameter choices for the network and present preliminary results of cloudretrievals from ORACLES, compared with standard RSP low-levelcloud retrieval method that has been validated against in situ observations.

Cloud-aerosol↗

NASA NTRS1997

Training Manual for Elements of Interface Definition and Control

The primary thrust of this manual is to ensure that the format and information needed to control interfaces between equipment are clear and understandable. The emphasis is on controlling the engineering design of the interface and not on the functional performance requirements of the system or the internal workings of the interfacing equipment. Interface control should take place, with rare exception, at the interfacing elements and no further. There are two essential sections of the manual. Chapter 2, Principles of Interface Control, discusses how interfaces are defined. It describes different types of interfaces to be considered and recommends a format for the documentation necessary for adequate interface control. Chapter 3, The Process: Through the Design Phases, provides tailored guidance for interface definition and control. This manual can be used to improve planned or existing interface control processes during system design and development. It can also be used to refresh and update the corporate knowledge base. The information presented herein will reduce the amount of paper and data required in interface definition and control processes by as much as 50 percent and will shorten the time required to prepare an interface control document. It also highlights the essential technical parameters that ensure that flight subsystems will indeed fit together and function as intended after assembly and checkout.

Lalli, Vincent R.↗

NASA NTRS1986

Towards a general object-oriented software development methodology

Object diagrams were used to design a 5000 statement team training exercise and to design the entire dynamics simulator. The object diagrams are also being used to design another 50,000 statement Ada system and a personal computer based system that will be written in Modula II. The design methodology evolves out of these experiences as well as the limitations of other methods that were studied. Object diagrams, abstraction analysis, and associated principles provide a unified framework which encompasses concepts from Yourdin, Booch, and Cherry. This general object-oriented approach handles high level system design, possibly with concurrency, through object-oriented decomposition down to a completely functional level. How object-oriented concepts can be used in other phases of the software life-cycle, such as specification and testing is being studied concurrently.

Seidewitz, ED↗

NASA NTRSDate not supplied

Hybrid Modeling of Unmanned Aerial Vehicle Electric Powertrain for Fault Detection and Diagnostics

This paper shows the application of hybrid physics-informed machine learning to a representative electric powertrain for unmanned aerial vehicles. The model is composed of physics-derived principles and empirical equations, as well as fully connected networks that are strategically placed within the model to substitute equations that are subject to large uncertainty. Polynomial fit driven by heuristics or empirical observations can be substituted by more flexible networks that can minimize the error between model predictions and observations without being restricted to a predefined functional form. This modeling strategy allows training of networks deep inside the model and unknown parameters in a single learning stage. It has already been applied to Li-ion batteries in the past, and in this work, we extend the applications to other components of an electric powertrain, namely electronic speed controller with pulse-width modulation, and brushless DC motor with connected propeller. Training and testing of the model is carried out using experimental data from Li-ion battery discharge and powertrain testing in a laboratory environment.

Physics-Informed Machine Learning↗

NASA NTRS2019

High-Performance Computing Optimization for Aladyn – Adaptive Neural Network Molecular Dynamics Mini-Application

This report provides a description and performance evaluation of the optimization techniques for high performance computing (HPC) implementation of the open source Computational Materials mini-application Aladyn (https://github.com/nasa/aladyn). Aladyn is a basic molecular dynamics code written in FORTRAN 2003, which is designed to demonstrate the use of adaptive neural networks (ANNs) in atomistic simulations. The role of ANNs is to efficiently reproduce the very complex energy landscape resulting from the atomic interactions in materials with the accuracy of the more expensive quantum mechanics-based calculations. The ANN is trained on a large set of atomic structures calculated using the density functional theory (DFT) method. While achieving orders of magnitude faster computational performance than DFT, the ANN-based approach was still very computationally demanding compared to the conventional approach of using empirically fitted energy functions. After its initial development, Aladyn was evaluated and optimized by experts at the NASA Advanced Supercomputing (NAS) division to exploit modern supercomputer architectures. The code has been optimized for execution on multicore central processing units (CPUs), including Intel® Skylake microarchitecture, and on graphic accelerators, such as Nvidia® V100 graphic processing units (GPUs), using Open Multi-Processing (OpenMP) and Open Accelerators (OpenACC) programming interfaces. The optimization achieved a speedup of 4.7 times the baseline version on CPU performance and an additional 2.4 times on CPU+GPU performance. Atomistic computer simulations are a fundamental tool in materials research to model material properties form physics-based first principles. Atomic interaction, governed by Quantum Mechanics (QM) require sophisticated and highly computationally demanding mathematical models to calculate [1]. Classical methods use approximate functional forms, empirically fitted through a set of variable parameters to emulate atomic energies as direct functions of atomic coordinates [2]. While empirical potentials are computationally much simpler, allowing simulations of large-scale systems of up to a trillion (1012) atoms [3], they are substantially less accurate compared to quantum calculations and applicable only to very specific atomic configurations or predefined crystallographic phases. A recently suggested approach is to use heuristic machine learning methods [4], such as those based on Adaptive Neural Networks (ANNs) to predict atomic energies, after being trained on a sufficiently large database of QM-calculated structures [5,6]. This approach reduces significantly the computational complexity, allowing for simulations of orders of magnitude larger systems compared to QM-based methods without compromising accuracy. Still, compared to classical methods using empirical energy functions, ANN methods remain two- to three orders of magnitude more computationally demanding. Hence, the computational cost of simulations, together with the need for extensive training of ANNs, still makes the practical implementation of ANN-based methods quite challenging. The purpose of the Aladyn mini-application software [7], available as open source at https://github.com/nasa/aladyn, is to be a testbed for exploring possible optimization strategies to develop highly scalable parallel algorithms for ANN-based atomistic simulations. Aladyn is aimed at utilizing the architecture of the high-end modern highperformance computing (HPC) hardware based on multicore central processing units (CPUs) equipped with graphic processing unit (GPU) accelerators. Specifically, the goal is to optimize the performance on a single HPC compute node, before implementing scaling to multi-node parallelization using message passing interface (MPI). At the same time, the open source code of Aladyn can serve as a training model for students and professors in academia.

Yamakov, Vesselin I.↗

NASA NTRS2023

Damage Detection of a Pressure Vessel with Smart Sensing and Deep Learning

Structural Health Monitoring plays a crucial role in ensuring the safety and reliability of critical infrastructure, including pressure vessels involved in various applications. This research reports the damage detection of a pressure box employed in space habitat that operates in harsh environment where both structural failure and bolt joint loosening may occur. These failure modes are extremely hard to model based on first principles. We explore proper sensing mechanism and the associated inverse analysis algorithm that can elucidate the health condition of the pressure box. It is identified that piezoelectric impedance based active interrogation can provide necessary information for damage detection in such a system. Concurrently, deep learning technique leveraging spatial convolutional neural network is synthesized to analyze the raw data acquired and identify different types of damage. By training the deep learning model on a dataset of healthy and various damage scenarios, we can achieve high accuracy in identifying the presence of damage and its type. This research provides a data-driven methodology for structural damage detection using deep learning and has the potential to be extended to various systems with different failure modes.

Yang Zhang↗

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↗

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↗

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↗