Results for “training data quality” — Page 11

NASA NTRSDate not supplied

Latest Development in Radiative Transfer Models and Retrieval Algorithms Using Principal Components

The radiative transfer model (RTMs) has a wide range of applications in satellite remote sensing and atmospheric radiation applications. However, millions of line-by-line (LBL) radiative transfer calculations at fine monochromatic frequencies are needed in order to properly calculate spectral contributions of water vapor and trace gases in the atmosphere in infrared and solar spectral regions. Therefore, fast and accurate RTMs are needed to efficiently process large amount of satellite data. A Principal Component-based Radiative Transfer Model (PCRTM) was first developed in 2004 at NASA Langley Research Centre to fulfil this need. By using PC-compression, one can reduce the data dimension significantly while maintaining original information content. The PCRTM can directly compute PC-scores and their derivatives with respect to retrieved parameters. The PCRTM can simulate the top-of-atmosphere (TOA) radiance or reflectance spectra from 0.250 µm (400000 cm-1) to 2000 µm (50 cm-1) with several orders of magnitude faster speed as compared to a LBL RTM. It is also extremely accurate compared to LBL RTM benchmarks (0.03 K RMS error in IR and 0.05% in solar). The PCRTM model has been developed for hyperspectral sensors such as AIRS, CrIS, IASI, NAST-I, SHIS, FIRST, and CLARREO-IR in thermal IR spectral region and CLARREO-Solar, CPF, TEMPO, EMIT, OMI, and SCIAMACHY in solar spectral region. The PCRTM accuracy has been demonstrated via RTM intercomparisons and with real satellite observations from AIRS, CrIS, IASI, SCHIAMACHY, and EMIT etc. In this presentation, we will describe two PCRTM-based inversion algorithms to retrieve atmospheric temperature, water vapor, and trace gas profiles, as well as cloud and surface properties from hyperspectral sounders such as AIRS, CrIS, IASI, and NAST-I. The first one is called Single Fieldof-view Sounder Atmospheric Product (SiFSAP) algorithm. It provides L2 products with 9-times higher area spatial resolution as compared to current cloud-clearing sounder algorithms. The SiFSAP L2 and L3 products are available at NASA's Goddard Earth Sciences Data and Information Services Center (GES DISC) for public access. The second inversion algorithm is called Climate Fingerprinting Atmospheric Product (ClimFiSP) algorithm. It is designed to produce high quality climate products (trends, anomalies, daily, and monthly profiles of temperature, water vapor, traces, clouds, and surface properties) from multiple satellite sensors such AIRS on Aqua and CrIS on multiple satellites. This product will be available at NASA GES DISC later this year. The PCRTMbased high fidelity simulators for CLARREO and CPF have been used for sensor performance trade studies, algorithm development, and inter-satellite calibrations. We have also used PCRTM generated TOA radiance spectra to train an AI-based algorithm and successfully retrieved cloud properties from EMIT solar hyperspectral imagers.

PCRTM↗

NASA NTRS1994

Upward appraisal as a means for improving supervisory performance and promoting process improvement, with long-term implications for organizational change

This study represents the implementation phase of an organizational development project which was initiated last year in the Management Support Division (MSD) at Langley Research Center to diagnose organizational functioning. As a result of MSD survey data from last year's effort, a Quality Action Team was created to address the responses compiled from the MSD Organizational Assessment Questionnaire and Follow-Up Questionnaire. The team was officially named the MSD Employee Relations Improvement Team (MERIT). MERIT's goal was to analyze major concerns generated by the questionnaires and to present feasible solutions to management which would improve supervisory performance, promote process improvement; and ultimately, lead to a better organization. The team met weekly and was very disciplined in following guidelines needed to ensure a fully functioning team. Several TQM tools were used during the team process, including brainstorming and the cause and effect diagram. One of the products produced by MERIT was a 'report card', more formally known as an upward appraisal system, to evaluate supervisory performance in the division office, its three branches, and in teams. Major areas of emphasis on the 47 item report card were those identified by employees through the previously administered questionnaires as needing to be improved; specifically, training, recognition, teamwork, supervision and leadership, and communication. MERIT created an enlarged and modified version of the report card which enabled scores for each individual supervisor to be recorded on a separate form, along with summary results and employee comments. Report card results have been compiled and fed back to the Division Chief and Assistant Division Chief. These individuals will in turn, feed the results back to the remaining supervisors and the team leaders. Although results differ among supervisors, some similarities exist. Communication generally appears to be adequate, which represents an improvement over last year. In contrast, recognition and teamwork are the two major areas where improvement in supervisory performance seems to be most needed. The initial report card results will serve as a baseline against which future performance ratings will be compared. Once supervisors have been presented with their data and given an opportunity to analyze and discus the results, they will be assisted in developing an action plan for improving their performance and work processes. They will be provided with ongoing support from management in following through with the action plan.

Siegfeldt, Denise V.↗

NASA NTRS2016

Geocam Space: Enhancing Handheld Digital Camera Imagery from the International Space Station for Research and Applications

Handheld astronaut photography of the Earth has been collected from the International Space Station (ISS) since 2000, making it the most temporally extensive remotely sensed dataset from this unique Low Earth orbital platform. Exclusive use of digital handheld cameras to perform Earth observations from the ISS began in 2004. Nadir viewing imagery is constrained by the inclined equatorial orbit of the ISS to between 51.6 degrees North and South latitude, however numerous oblique images of land surfaces above these latitudes are included in the dataset. While unmodified commercial off-the-shelf digital cameras provide only visible wavelength, three-band spectral information of limited quality current cameras used with long (400+ mm) lenses can obtain high quality spatial information approaching 2 meters/ground pixel resolution. The dataset is freely available online at the Gateway to Astronaut Photography of Earth site (http://eol.jsc.nasa.gov), and now comprises over 2 million images. Despite this extensive image catalog, use of the data for scientific research, disaster response, commercial applications and visualizations is minimal in comparison to other data collected from free-flying satellite platforms such as Landsat, Worldview, etc. This is due primarily to the lack of fully-georeferenced data products - while current digital cameras typically have integrated GPS, this does not function in the Low Earth Orbit environment. The Earth Science and Remote Sensing (ESRS) Unit at NASA Johnson Space Center provides training in Earth Science topics to ISS crews, performs daily operations and Earth observation target delivery to crews through the Crew Earth Observations (CEO) Facility on board ISS, and also catalogs digital handheld imagery acquired from orbit by manually adding descriptive metadata and determining an image geographic centerpoint using visual feature matching with other georeferenced data, e.g. Landsat, Google Earth, etc. The lack of full geolocation information native to the data makes it difficult to integrate astronaut photographs with other georeferenced data to facilitate quantitative analysis such as urban land cover/land use classification, change detection, or geologic mapping. The manual determination of image centerpoints is both time and labor-intensive, leading to delays in releasing geolocated and cataloged data to the public, such as the timely use of data for disaster response. The GeoCam Space project was funded by the ISS Program in 2015 to develop an on-orbit hardware and ground-based software system for increasing the efficiency of geolocating astronaut photographs from the ISS (Fig. 1). The Intelligent Robotics Group at NASA Ames Research Center leads the development of both the ground and on-orbit systems in collaboration with the ESRS Unit. The hardware component consists of modified smartphone elements including cameras, central processing unit, wireless Ethernet, and an inertial measurement unit (gyroscopes/accelerometers/magnetometers) reconfigured into a compact unit that attaches to the base of the current Nikon D4 camera - and its replacement, the Nikon D5 - and connects using the standard Nikon peripheral connector or USB port. This provides secondary, side and downward facing cameras perpendicular to the primary camera pointing direction. The secondary cameras observe calibration targets with known internal X, Y, and Z position affixed to the interior of the ISS to determine the camera pose corresponding to each image frame. This information is recorded by the GeoCam Space unit and indexed for correlation to the camera time recorded for each image frame. Data - image, EXIF header, and camera pose information - is transmitted to the ground software system (GeoRef) using the established Ku-band USOS downlink system. Following integration on the ground, the camera pose information provides an initial geolocation estimate for the individual film frame. This new capability represents a significant advance in geolocation from the manual feature-matching approach for both nadir and off-nadir viewing imagery. With the initial geolocation estimate, full georeferencing of an image is completed using the rapid tie-pointing interface in GeoRef, and the resulting data is added to the Gateway to Astronaut Photography of Earth online database in both Geotiff and Keyhole Markup Language (kml) formats. The integration of the GeoRef software component of Geocam Space into the CEO image cataloging workflow is complete, and disaster response imagery acquired by the ISS crew is now fully georeferenced as a standard data product. The on-orbit hardware component (GeoSens) is in final prototyping phase, and is on-schedule for launch to the ISS in late 2016. Installation and routine use of the Geocam Space system for handheld digital camera photography from the ISS is expected to significantly improve the usefulness of this unique dataset for a variety of public- and private-sector applications.

Stefanov, William L.↗

NASA NTRSDate not supplied

How Can We Harness the Power of Machine Learning With TEMPO Data?

There are many potential applications of machine learning for TEMPO data that include - Improve retrievals by reducing the effect of random instrument noise - Expand coverage by producing data in moderately cloudy conditions (see also Fasnacht et al. poster) - Help diagnose impacts of instrumental artifacts - Produce value-added products quickly by training on existing products from other sensors (land and ocean) - Speed up processing by training on products produced with full-physics algorithms (e.g., NO 2 slant column fitting may take ~1 hour/orbit but with a neural net it may take only minutes)

NO2↗

NASA NTRS1972

Participation in the Apollo passive seismic experiment

Computer programs which were written to read digital tapes containing lunar seismic data were studied. Interpreting very early parts of the lunar seismogram as seismic body-wave phases enabled the determination of the structure of the outer part of the moon in the Fra Mauro region. The crust in the Fra Mauro region is 60 to 65 km-thick, overlaying a high velocity mantle. The crust is further divided into an upper part, 25 km thick, apparently made of material similar to the surficial basalts, and a lower part of seemingly different composition, possibly an anorthositic gabbro. The generation of the exceedingly long reverberating wave-train observed in lunar seismogram was also studied. This is believed to be due to an intense scattering layer with very high quality coefficient overlying a more homogeneous elastic medium. Titles and abstracts of related published papers are included.

Press, F.↗

NASA NTRS2005

Inductive Learning Approaches for Improving Pilot Awareness of Aircraft Faults

Neural network flight controllers are able to accommodate a variety of aircraft control surface faults without detectable degradation of aircraft handling qualities. Under some faults, however, the effective flight envelope is reduced; this can lead to unexpected behavior if a pilot performs an action that exceeds the remaining control authority of the damaged aircraft. The goal of our work is to increase the pilot s situational awareness by informing him of the type of damage and resulting reduction in flight envelope. Our methodology integrates two inductive learning systems with novel visualization techniques. One learning system, the Inductive Monitoring System (IMS), learns to detect when a simulation includes faulty controls, while two others, Inductive Classification System (INCLASS) and multiple binary decision tree system (utilizing C4.5), determine the type of fault. In off-line training using only non-failure data, IMS constructs a characterization of nominal flight control performance based on control signals issued by the neural net flight controller. This characterization can be used to determine the degree of control augmentation required in the pitch, roll, and yaw command channels to counteract control surface failures. This derived information is typically sufficient to distinguish between the various control surface failures and is used to train both INCLASS and C4.5. Using data from failed control surface flight simulations, INCLASS and C4.5 independently discover and amplify features in IMS results that can be used to differentiate each distinct control surface failure situation. In real-time flight simulations, distinguishing features learned during training are used to classify control surface failures. Knowledge about the type of failure can be used by an additional automated system to alter its approach for planning tactical and strategic maneuvers. The knowledge can also be used directly to increase the pilot s situational awareness and inform manual maneuver decisions. Our multi-modal display of this information provides speech output to issue control surface failure warnings to a lesser-used communication channel and provides graphical displays with pilot-selectable !eve!s of details to issues additional information about the failure. We also describe a potential presentation for flight envelope reduction that can be viewed separately or integrated with an existing attitude indicator instrument. Preliminary results suggest that the inductive approach is capable of detecting that a control surface has failed and determining the type of fault. Furthermore, preliminary evaluations suggest that the interface discloses a concise summary of this information to the pilot.

Spikovska, Lilly↗

NASA NTRS1998

Applications of Artificial Neural Networks in Structural Engineering with Emphasis on Continuum Models

The use of continuum models for the analysis of discrete built-up complex aerospace structures is an attractive idea especially at the conceptual and preliminary design stages. But the diversity of available continuum models and hard-to-use qualities of these models have prevented them from finding wide applications. In this regard, Artificial Neural Networks (ANN or NN) may have a great potential as these networks are universal approximators that can realize any continuous mapping, and can provide general mechanisms for building models from data whose input-output relationship can be highly nonlinear. The ultimate aim of the present work is to be able to build high fidelity continuum models for complex aerospace structures using the ANN. As a first step, the concepts and features of ANN are familiarized through the MATLAB NN Toolbox by simulating some representative mapping examples, including some problems in structural engineering. Then some further aspects and lessons learned about the NN training are discussed, including the performances of Feed-Forward and Radial Basis Function NN when dealing with noise-polluted data and the technique of cross-validation. Finally, as an example of using NN in continuum models, a lattice structure with repeating cells is represented by a continuum beam whose properties are provided by neural networks.

Kapania, Rakesh K.↗

NASA NTRS2002

The Virtual Glovebox (VGX): An Immersive Simulation System for Training Astronauts to Perform Glovebox Experiments in Space

The era of the International Space Station (ISS) has finally arrived, providing researchers on Earth a unique opportunity to study long-term effects of weightlessness and the space environment on structures, materials and living systems. Many of the physical, biological and material science experiments planned for ISS will require significant input and expertise from astronauts who must conduct the research, follow complicated assay procedures and collect data and samples in space. Containment is essential for Much of this work, both to protect astronauts from potentially harmful biological, chemical or material elements in the experiments as well as to protect the experiments from contamination by air-born particles In the Space Station environment. When astronauts must open the hardware containing such experiments, glovebox facilities provide the necessary barrier between astronaut and experiment. On Earth, astronauts are laced with the demanding task of preparing for the many glovebox experiments they will perform in space. Only a short time can be devoted to training for each experimental task and gl ovebox research only accounts for a small portion of overall training and mission objectives on any particular ISS mission. The quality of the research also must remain very high, requiring very detailed experience and knowledge of instrumentation, anatomy and specific scientific objectives for those who will conduct the research. This unique set of needs faced by NASA has stemmed the development of a new computer simulation tool, the Virtual Glovebox (VGB), which is designed to provide astronaut crews and support personnel with a means to quickly and accurately prepare and train for glovebox experiments in space.

Smith, Jeffrey D.↗

NASA NTRS2004

Automated Classification of ROSAT Sources Using Heterogeneous Multiwavelength Source Catalogs

We describe an on-line system for automated classification of X-ray sources, ClassX, and present preliminary results of classification of the three major catalogs of ROSAT sources, RASS BSC, RASS FSC, and WGACAT, into six class categories: stars, white dwarfs, X-ray binaries, galaxies, AGNs, and clusters of galaxies. ClassX is based on a machine learning technology. It represents a system of classifiers, each classifier consisting of a considerable number of oblique decision trees. These trees are built as the classifier is 'trained' to recognize various classes of objects using a training sample of sources of known object types. Each source is characterized by a preselected set of parameters, or attributes; the same set is then used as the classifier conducts classification of sources of unknown identity. The ClassX pipeline features an automatic search for X-ray source counterparts among heterogeneous data sets in on-line data archives using Virtual Observatory protocols; it retrieves from those archives all the attributes required by the selected classifier and inputs them to the classifier. The user input to ClassX is typically a file with target coordinates, optionally complemented with target IDs. The output contains the class name, attributes, and class probabilities for all classified targets. We discuss ways to characterize and assess the classifier quality and performance and present the respective validation procedures. Based on both internal and external validation, we conclude that the ClassX classifiers yield reasonable and reliable classifications for ROSAT sources and have the potential to broaden class representation significantly for rare object types.

McGlynn, Thomas↗

NASA NTRS2016

Tailoring a Human Reliability Analysis to Your Industry Needs

Companies at risk of accidents caused by human error that result in catastrophic consequences include: airline industry mishaps, medical malpractice, medication mistakes, aerospace failures, major oil spills, transportation mishaps, power production failures and manufacturing facility incidents. Human Reliability Assessment (HRA) is used to analyze the inherent risk of human behavior or actions introducing errors into the operation of a system or process. These assessments can be used to identify where errors are most likely to arise and the potential risks involved if they do occur. Using the basic concepts of HRA, an evolving group of methodologies are used to meet various industry needs. Determining which methodology or combination of techniques will provide a quality human reliability assessment is a key element to developing effective strategies for understanding and dealing with risks caused by human errors. There are a number of concerns and difficulties in "tailoring" a Human Reliability Assessment (HRA) for different industries. Although a variety of HRA methodologies are available to analyze human error events, determining the most appropriate tools to provide the most useful results can depend on industry specific cultures and requirements. Methodology selection may be based on a variety of factors that include: 1) how people act and react in different industries, 2) expectations based on industry standards, 3) factors that influence how the human errors could occur such as tasks, tools, environment, workplace, support, training and procedure, 4) type and availability of data, 5) how the industry views risk & reliability, and 6) types of emergencies, contingencies and routine tasks. Other considerations for methodology selection should be based on what information is needed from the assessment. If the principal concern is determination of the primary risk factors contributing to the potential human error, a more detailed analysis method may be employed versus a requirement to provide a numerical value as part of a probabilistic risk assessment. Industries involved with humans operating large equipment or transport systems (ex. railroads or airlines) would have more need to address the man machine interface than medical workers administering medications. Human error occurs in every industry; in most cases the consequences are relatively benign and occasionally beneficial. In cases where the results can have disastrous consequences, the use of Human Reliability techniques to identify and classify the risk of human errors allows a company more opportunities to mitigate or eliminate these types of risks and prevent costly tragedies.

DeMott, D. L.↗

NASA NTRSDate not supplied

An Approach to Identifying Aspects of Positive Pilot Behavior within the Aviation Safety Reporting System

The National Airspace System (NAS) is constantly evolving as air traffic continues to ramp up to pre-pandemic numbers and projected to grow to unprecedented levels in the coming years. As well as increasing demand to the current system, emerging operations such as Unmanned Autonomous Systems are also expected to add to complexity in the airspace. To address these issues, the industry and government agencies supporting the NAS will need to rely upon additional automation and new technologies to address future operational requirements, while continuing to be a world-leading safe transportation system. As these new technologies are implemented, the system continues to rely on human pilots and controllers in the loop to monitor the system and intervene in situations the automation cannot handle. The goal of proactively addressing safety is of foremost concern to ensure passenger confidence. The industry has implemented various Safety Monitoring Systems to identify safety risks and proactively address them before they result in a serious incident or accident. One such program is the Aviation Safety Reporting System (ASRS). ASRS is a long-established system where pilots and controllers voluntarily and anonymously report safety incidents they experienced and observed during line operations by providing rich text narratives describing the events, the environment, and conditions leading to the safety event of concern. These narratives provide insight and context around events of interest and can be used to identify emerging problems. They can trigger investigations within Flight Operational Quality Assurance or Flight Data Monitoring programs. However, this process typically focuses on the adverse events and the unsafe aspects of the operations surrounding the reported or detected events. This perspective of investigating factors that went wrong around an adverse event is commonly referred to as Safety I. Alternatively, characterizing successful actions that operators perform every day under varying conditions that keep the system within safe operating bounds is a concept referred to as Safety II. The benefit of the Safety II view is that the scope is much larger than that of Safety I since a vast majority of the operations result in successful flights. Many of the successful techniques used to manage operational threats are not documented in standard operating procedures or taught during training. They are typically acquired over time by working with experienced pilots during line operations or in many cases after experiencing a problem for the first time and reacting to it in situ, drawing from years of experience to manage the threat. In an attempt to quantify these positive actions, we are proposing an approach to extracting key behaviors within ASRS reports that can support the Safety II concept. Our analysis assumes that ASRS reports contain some descriptions of corrective actions that operators performed to prevent a situation from leading to an accident. Leveraging recent advances in Natural Language Process modeling, we have developed an approach to extract positive sentiment from reports, embed these positive statements in a vector space where they can be numerically analyzed, and clustering these statements into similar contextual categories. From these contextualized categories we can attempt to summarized and distilled aspects of the positive behavior. The goal is to identify categories of behavior that describe consistent operator techniques that supports the Safety II concept. With this information, airlines may enable learning from these positive actions, or address procedures that need to be changed to avoid having pilots implement a workaround. These insights can provide a lens into what is “going right” in the operations that may otherwise not be known widely within the community. It is envisioned that this approach can be extended to other narrative programs such as Line Operation Safety Audit or Learning Improvement Team reports where similar observed behavior can be analyzed to extract positive actions and inform the overall operations.

NLP↗

NASA NTRSDate not supplied

An Approach to Identifying Aspects of Positive Pilot Behavior within the Aviation Safety Reporting System

The National Airspace System (NAS) is constantly evolving as air traffic continues to ramp up to pre-pandemic numbers and projected to grow to unprecedented levels in the coming years. As well as increasing demand to the current system, emerging operations such as Unmanned Autonomous Systems are also expected to add to complexity in the airspace. To address these issues, the industry and government agencies supporting the NAS will need to rely upon additional automation and new technologies to address future operational requirements, while continuing to be a world-leading safe transportation system. As these new technologies are implemented, the system continues to rely on human pilots and controllers in the loop to monitor the system and intervene in situations the automation cannot handle. The goal of proactively addressing safety is of foremost concern to ensure passenger confidence. The industry has implemented various Safety Monitoring Systems to identify safety risks and proactively address them before they result in a serious incident or accident. One such program is the Aviation Safety Reporting System (ASRS). ASRS is a long-established system where pilots and controllers voluntarily and anonymously report safety incidents they experienced and observed during line operations by providing rich text narratives describing the events, the environment, and conditions leading to the safety event of concern. These narratives provide insight and context around events of interest and can be used to identify emerging problems. They can trigger investigations within Flight Operational Quality Assurance or Flight Data Monitoring programs. However, this process typically focuses on the adverse events and the unsafe aspects of the operations surrounding the reported or detected events. This perspective of investigating factors that went wrong around an adverse event is commonly referred to as Safety I. Alternatively, characterizing successful actions that operators perform every day under varying conditions that keep the system within safe operating bounds is a concept referred to as Safety II. The benefit of the Safety II view is that the scope is much larger than that of Safety I since a vast majority of the operations result in successful flights. Many of the successful techniques used to manage operational threats are not documented in standard operating procedures or taught during training. They are typically acquired over time by working with experienced pilots during line operations or in many cases after experiencing a problem for the first time and reacting to it in situ, drawing from years of experience to manage the threat. In an attempt to quantify these positive actions, we are proposing an approach to extracting key behaviors within ASRS reports that can support the Safety II concept. Our analysis assumes that ASRS reports contain some descriptions of corrective actions that operators performed to prevent a situation from leading to an accident. Leveraging recent advances in Natural Language Process modeling, we have developed an approach to extract positive sentiment from reports, embed these positive statements in a vector space where they can be numerically analyzed, and clustering these statements into similar contextual categories. From these contextualized categories we can attempt to summarized and distilled aspects of the positive behavior. The goal is to identify categories of behavior that describe consistent operator techniques that supports the Safety II concept. With this information, airlines may enable learning from these positive actions, or address procedures that need to be changed to avoid having pilots implement a workaround. These insights can provide a lens into what is “going right” in the operations that may otherwise not be known widely within the community. It is envisioned that this approach can be extended to other narrative programs such as Line Operation Safety Audit or Learning Improvement Team reports where similar observed behavior can be analyzed to extract positive actions and inform the overall operations.

NLP↗

NASA NTRSDate not supplied

An Approach to Identifying Aspects of Positive Pilot Behavior within the Aviation Safety Reporting System

The National Airspace System (NAS) is constantly evolving as air traffic continues to ramp up to pre-pandemic numbers and projected to grow to unprecedented levels in the coming years. As well as increasing demand to the current system, emerging operations such as Unmanned Autonomous Systems are also expected to add to complexity in the airspace. To address these issues, the industry and government agencies supporting the NAS will need to rely upon additional automation and new technologies to address future operational requirements, while continuing to be a world-leading safe transportation system. As these new technologies are implemented, the system continues to rely on human pilots and controllers in the loop to monitor the system and intervene in situations the automation cannot handle. The goal of proactively addressing safety is of foremost concern to ensure passenger confidence. The industry has implemented various Safety Monitoring Systems to identify safety risks and proactively address them before they result in a serious incident or accident. One such program is the Aviation Safety Reporting System (ASRS). ASRS is a long-established system where pilots and controllers voluntarily and anonymously report safety incidents they experienced and observed during line operations by providing rich text narratives describing the events, the environment, and conditions leading to the safety event of concern. These narratives provide insight and context around events of interest and can be used to identify emerging problems. They can trigger investigations within Flight Operational Quality Assurance or Flight Data Monitoring programs. However, this process typically focuses on the adverse events and the unsafe aspects of the operations surrounding the reported or detected events. This perspective of investigating factors that went wrong around an adverse event is commonly referred to as Safety I. Alternatively, characterizing successful actions that operators perform every day under varying conditions that keep the system within safe operating bounds is a concept referred to as Safety II. The benefit of the Safety II view is that the scope is much larger than that of Safety I since a vast majority of the operations result in successful flights. Many of the successful techniques used to manage operational threats are not documented in standard operating procedures or taught during training. They are typically acquired over time by working with experienced pilots during line operations or in many cases after experiencing a problem for the first time and reacting to it in situ, drawing from years of experience to manage the threat. In an attempt to quantify these positive actions, we are proposing an approach to extracting key behaviors within ASRS reports that can support the Safety II concept. Our analysis assumes that ASRS reports contain some descriptions of corrective actions that operators performed to prevent a situation from leading to an accident. Leveraging recent advances in Natural Language Process modeling, we have developed an approach to extract positive sentiment from reports, embed these positive statements in a vector space where they can be numerically analyzed, and clustering these statements into similar contextual categories. From these contextualized categories we can attempt to summarized and distilled aspects of the positive behavior. The goal is to identify categories of behavior that describe consistent operator techniques that supports the Safety II concept. With this information, airlines may enable learning from these positive actions, or address procedures that need to be changed to avoid having pilots implement a workaround. These insights can provide a lens into what is “going right” in the operations that may otherwise not be known widely within the community. It is envisioned that this approach can be extended to other narrative programs such as Line Operation Safety Audit or Learning Improvement Team reports where similar observed behavior can be analyzed to extract positive actions and inform the overall operations.

NLP↗

NASA NTRS1990

NASA/DOD Aerospace Knowledge Diffusion Research Project. Paper 6: Aerospace knowledge diffusion in the academic community: A report of phase 3 activities of the NASA/DOD Aerospace Knowledge Diffusion Research Project

Descriptive and analytical data regarding the flow of aerospace-based scientific and technical information (STI) in the academic community are presented. An overview is provided of the Federal Aerospace Knowledge Diffusion Research Project, illustrating a five-year program on aerospace knowledge diffusion. Preliminary results are presented of the project's research concerning the information-seeking habits, practices, and attitudes of U.S. aerospace engineering and science students and faculty. The type and amount of education and training in the use of information sources are examined. The use and importance ascribed to various information products by U.S. aerospace faculty and students including computer and other information technology is assessed. An evaluation of NASA technical reports is presented and it is concluded that NASA technical reports are rated high in terms of quality and comprehensiveness, citing Engineering Index and IAA as the most frequently used materials by faculty and students.

Pinelli, Thomas E.↗

NASA NTRS2011

Space Shuttle Ascent Flight Design Process: Evolution and Lessons Learned

The Space Shuttle Ascent Flight Design team is responsible for defining a launch to orbit trajectory profile that satisfies all programmatic mission objectives and defines the ground and onboard reconfiguration requirements for this high-speed and demanding flight phase. This design, verification and reconfiguration process ensures that all applicable mission scenarios are enveloped within integrated vehicle and spacecraft certification constraints and criteria, and includes the design of the nominal ascent profile and trajectory profiles for both uphill and ground-to-ground aborts. The team also develops a wide array of associated training, avionics flight software verification, onboard crew and operations facility products. These key ground and onboard products provide the ultimate users and operators the necessary insight and situational awareness for trajectory dynamics, performance and event sequences, abort mode boundaries and moding, flight performance and impact predictions for launch vehicle stages for use in range safety, and flight software performance. These products also provide the necessary insight to or reconfiguration of communications and tracking systems, launch collision avoidance requirements, and day of launch crew targeting and onboard guidance, navigation and flight control updates that incorporate the final vehicle configuration and environment conditions for the mission. Over the course of the Space Shuttle Program, ascent trajectory design and mission planning has evolved in order to improve program flexibility and reduce cost, while maintaining outstanding data quality. Along the way, the team has implemented innovative solutions and technologies in order to overcome significant challenges. A number of these solutions may have applicability to future human spaceflight programs.

Picka, Bret A.↗

NASA NTRS2003

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

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

Hageman, Jacob↗

NASA NTRS2003

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

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

Hageman, Jacob J.↗

NASA NTRS2018

Efficient Unsteady Model Estimation Using Computational and Experimental Data

Improving aircraft simulations for pilot training in loss-of-control and stalled conditions is one goal of NASA research in the System Wide Safety Program. One part of this effort is to develop appropriate generic aerodynamic models that provide representative responses in simulation for a given class of aircraft. In this part of the flight envelope nonlinear unsteady responses are often present and may require an extended aerodynamic model compared to that used in the conventional flight envelope. In this preliminary study, two objectives are addressed. First, to obtain a representative model for a NASA generic aircraft at an unsteady condition in the flight envelope and second, to evaluate the techniques involved. To meet these objectives, two different generic aircraft configurations are modeled using both experimental and analytical data. With these results, an initial assessment of the efficiency and quality of the tools and test techniques are evaluated to develop guidance for analytical and experimental approaches to unsteady modeling.

Murphy, Patrick C.↗