Engineering topics

Matthews, Bryan

Publications and source records attributed to Matthews, Bryan.

18 records

NASA NTRS2020

Unsupervised Anomaly Detection in High-Dimensional Flight Data Using Convolutional Variational Auto-Encoder

The modern National Airspace System (NAS) is an extremely safe system and the aviation industry has experienced a steady decrease in fatalities over the years. This can be attributed to both improved flight critical systems with redundant hardware and software protections, as well as an increased focus on active monitoring and response to real time and historically identified vulnerabilities by implementing more resilient procedures and protocols. The main approach for identifying vulnerabilities in operations leverages domain expertise using knowledge about how the system should behave within the expected tolerances to known safety margins. This approach works well when the system has a well-defined operating condition. However, the operations in the NAS can be highly complex with various nuances that render it difficult to clearly pre-define all known safety vulnerabilities. With the advancement of data science and machine learning techniques, the potential to automatically identify emerging vulnerabilities in the observed operations has become more practical in recent years. The state-of-the-art anomaly detection approaches in aerospace data usually rely on supervised or semi-supervised learning. However, in many real-world problems such as flight safety, creating labels for the data requires huge amount of effort and is largely impractical. To address this challenge, we developed a Convolutional Variational Auto-Encoder (CVAE), which is an unsupervised learning approach for anomaly detection in high-dimensional heterogeneous time-series data. We validate performance of CVAE compared to the state-of-the-art supervised learning approach as well as unsupervised clustering-based approach using KMeans++ and kernel-based approach using One-Class Support Vector Machine (OC-SVM) on Yahoo!'s benchmark time series anomaly detection data. Finally, we showcase performance of CVAE on a case study of identifying anomalies in the first 60 seconds of commercial flights' take-offs using Flight Operational Quality Assurance (FOQA) data.

Memarzadeh, Milad↗

NASA NTRS2019

Automatic Anomaly Detection with Machine Learning

This presentation will discuss the following topics: Understanding the benefits of automatic anomaly detection Identifying precursors with algorithms. Overcoming the challenges of data issues in automation.

Data Science↗

NASA NTRS2018

Variables Influencing RNAV STAR Adherence

In this study we investigated how variables in the aviation domain impact adherence levels of aircraft flying area navigation arrivals with optimized profile descents (RNAV OPDs) (RNAV STARs: aRea NAVigation Standard Terminal Arrival Routes). Variable categories were: weather, aircraft, procedure, and traffic. Non-adherence events analyzed were: miss above, miss below, skip before merge, and skip after merge. Miss below and miss above describe when a flight does not comply vertically with a procedure. Skips refer to a flight leaving a procedure, then returning. Findings of this work reveal that vertical events are most impacted by altitude restriction size, steepness of flight paths, and merging routes. Lateral events were impacted by merging flight conflicts, number of speed restrictions, and the flow rate of the arrival traffic. This study helps increase understanding of how the system is functioning and identifies where procedures are not flexible enough to handle the variability in normal operations.major airports, procedure design, and recommendations for future work.

RNAV OPD↗

NASA NTRS2018

Knowledge Discovery Process: Case Study of RNAV Adherence of Radar Track Data

This talk is an introduction to the knowledge discovery process, beginning with: identifying the problem, choosing data sources, matching the appropriate machine learning tools, and reviewing the results. The overview will be given in the context of an ongoing study that is assessing RNAV adherence of commercial aircraft in the national airspace.

Machine Learning↗

NASA NTRS2018

Using ADOPT Algorithm and Operational Data to Discover Precursors to Aviation Adverse Events

The US National Airspace System (NAS) is making its transition to the NextGen system and assuring safety is one of the top priorities in NextGen. At present, safety is managed reactively (correct after occurrence of an unsafe event). While this strategy works for current operations, it may soon become ineffective for future airspace designs and high density operations. There is a need for proactive management of safety risks by identifying hidden and "unknown" risks and evaluating the impacts on future operations. To this end, NASA Ames has developed data mining algorithms that finds anomalies and precursors (high-risk states) to safety issues in the NAS. In this paper, we describe a recently developed algorithm called ADOPT that analyzes large volumes of data and automatically identifies precursors from real world data. Precursors help in detecting safety risks early so that the operator can mitigate the risk in time. In addition, precursors also help identify causal factors and help predict the safety incident. The ADOPT algorithm scales well to large data sets and to multidimensional time series, reduce analyst time significantly, quantify multiple safety risks giving a holistic view of safety among other benefits. This paper details the algorithm and includes several case studies to demonstrate its application to discover the "known" and "unknown" safety precursors in aviation operation.

aviation safet↗

NASA NTRS2017

Ask-the-expert: Active Learning Based Knowledge Discovery Using the Expert

Often the manual review of large data sets, either for purposes of labeling unlabeled instances or for classifying meaningful results from uninteresting (but statistically significant) ones is extremely resource intensive, especially in terms of subject matter expert (SME) time. Use of active learning has been shown to diminish this review time significantly. However, since active learning is an iterative process of learning a classifier based on a small number of SME-provided labels at each iteration, the lack of an enabling tool can hinder the process of adoption of these technologies in real-life, in spite of their labor-saving potential. In this demo we present ASK-the-Expert, an interactive tool that allows SMEs to review instances from a data set and provide labels within a single framework. ASK-the-Expert is powered by an active learning algorithm for training a classifier in the backend. We demonstrate this system in the context of an aviation safety application, but the tool can be adopted to work as a simple review and labeling tool as well, without the use of active learning.

software↗

NASA NTRS2017

Objective Assessment Method for RNAV STAR Adherence

Flight crews and air traffic controllers have reported many safety concerns regarding area navigation standard terminal arrival routes (RNAV STARs). Specifically, optimized profile descents (OPDs). However, our information sources to quantify these issues are limited to subjective reporting and time consuming case-by-case investigations. This work is a preliminary study into the objective performance of instrument procedures and provides a framework to track procedural concepts and assess design specifications. We created a tool and analysis methods for gauging aircraft adherence as it relates to RNAV STARs. This information is vital for comprehensive understanding of how our air traffic behaves. In this study, we mined the performance of 24 major US airports over the preceding three years. Overlaying 4D radar track data onto RNAV STAR routes provided a comparison between aircraft flight paths and the waypoint positions and altitude restrictions. NASA Ames Supercomputing resources were utilized to perform the data mining and processing. We assessed STARs by lateral transition path (full-lateral), vertical restrictions (full-lateral/full-vertical), and skipped waypoints (skips). In addition, we graphed frequencies of aircraft altitudes relative to the altitude restrictions. Full-lateral adherence was always greater than Full-lateral/ full- vertical, as it is a subset, but the difference between the rates was not consistent. Full-lateral/full-vertical adherence medians of the 2016 procedures ranged from 0% in KDEN (Denver) to 21% in KMEM (Memphis). Waypoint skips ranged from 0% to nearly 100% for specific waypoints. Altitudes restrictions were sometimes missed by systematic amounts in 1,000 ft. increments from the restriction, creating multi-modal distributions. Other times, altitude misses looked to be more normally distributed around the restriction. This tool may aid in providing acceptability metrics as well as risk assessment information.

Stewart, Michael↗

NASA NTRS2016

Active Learning with Rationales for Identifying Operationally Significant Anomalies in Aviation

A major focus of the commercial aviation community is discovery of unknown safety events in flight operations data. Data-driven unsupervised anomaly detection methods are better at capturing unknown safety events compared to rule-based methods which only look for known violations. However, not all statistical anomalies that are discovered by these unsupervised anomaly detection methods are operationally significant (e.g., represent a safety concern). Subject Matter Experts (SMEs) have to spend significant time reviewing these statistical anomalies individually to identify a few operationally significant ones. In this paper we propose an active learning algorithm that incorporates SME feedback in the form of rationales to build a classifier that can distinguish between uninteresting and operationally significant anomalies. Experimental evaluation on real aviation data shows that our approach improves detection of operationally significant events by as much as 75% compared to the state-of-the-art. The learnt classifier also generalizes well to additional validation data sets.

anomaly detection↗

NASA NTRS2014

Automated Discovery of Flight Track Anomalies

As new technologies are developed to handle the complexities of the Next Generation Air Transportation System (NextGen), it is increasingly important to address both current and future safety concerns along with the operational, environmental, and efficiency issues within the National Airspace System (NAS). In recent years, the Federal Aviation Administration’s (FAA) safety offices have been researching ways to utilize the many safety databases maintained by the FAA, such as those involving flight recorders, radar tracks, weather, and many other high- volume sensors, in order to monitor this unique and complex system. Although a number of current technologies do monitor the frequency of known safety risks in the NAS, very few methods currently exist that are capable of analyzing large data repositories with the purpose of discovering new and previously unmonitored safety risks. While monitoring the frequency of known events in the NAS enables mitigation of already identified problems, a more proactive approach of finding unidentified issues still needs to be addressed. This is especially important in the proactive identification of new, emergent safety issues that may result from the planned introduction of advanced NextGen air traffic management technologies and procedures. Development of an automated tool that continuously evaluates the NAS to discover both events exhibiting flight characteristics indicative of safety-related concerns as well as operational anomalies will heighten the awareness of such situations in the aviation community and serve to increase the overall safety of the NAS. This paper discusses the extension of previous anomaly detection work to identify operationally significant flights within the highly complex airspace encompassing the New York area of operations, focusing on the major airports of Newark International (EWR), LaGuardia International (LGA), and John F. Kennedy International (JFK). In addition, flight traffic in the vicinity of Denver International (DEN) airport/airspace is also investigated to evaluate the impact on operations due to variances in seasonal weather and airport elevation. From our previous research, subject matter experts determined that some of the identified anomalies were significant, but could not reach conclusive findings without additional supportive data. To advance this research further, causal examination using domain experts is continued along with the integration of air traffic control (ATC) voice data to shed much needed insight into resolving which flight characteristic(s) may be impacting an aircraft's unusual profile. Once a flight characteristic is identified, it could be included in a list of potential safety precursors. This paper also describes a process that has been developed and implemented to automatically identify and produce daily reports on flights of interest from the previous day.

Matthews, Bryan↗

NASA NTRS2010

Propulsion Health Monitoring of a Turbine Engine Disk Using Spin Test Data

This paper considers data collected from an experimental study using high frequency capacitive sensor technology to capture blade tip clearance and tip timing measurements in a rotating turbine engine-like-disk-to predict the disk faults and assess its structural integrity. The experimental results collected at a range of rotational speeds from tests conducted at the NASA Glenn Research Center s Rotordynamics Laboratory are evaluated using multiple data-driven anomaly detection techniques to identify abnormalities in the disk. Further, this study presents a select evaluation of an online health monitoring scheme of a rotating disk using high caliber sensors and test the capability of the in-house spin system.

Abdul-Aziz, Ali↗

NASA NTRS2010

Ares I-X Ground Diagnostic Prototype

The automation of pre-launch diagnostics for launch vehicles offers three potential benefits: improving safety, reducing cost, and reducing launch delays. The Ares I-X Ground Diagnostic Prototype demonstrated anomaly detection, fault detection, fault isolation, and diagnostics for the Ares I-X first-stage Thrust Vector Control and for the associated ground hydraulics while the vehicle was in the Vehicle Assembly Building at Kennedy Space Center (KSC) and while it was on the launch pad. The prototype combines three existing tools. The first tool, TEAMS (Testability Engineering and Maintenance System), is a model-based tool from Qualtech Systems Inc. for fault isolation and diagnostics. The second tool, SHINE (Spacecraft Health Inference Engine), is a rule-based expert system that was developed at the NASA Jet Propulsion Laboratory. We developed SHINE rules for fault detection and mode identification, and used the outputs of SHINE as inputs to TEAMS. The third tool, IMS (Inductive Monitoring System), is an anomaly detection tool that was developed at NASA Ames Research Center. The three tools were integrated and deployed to KSC, where they were interfaced with live data. This paper describes how the prototype performed during the period of time before the launch, including accuracy and computer resource usage. The paper concludes with some of the lessons that we learned from the experience of developing and deploying the prototype.

Schwabacher, Mark A.↗

NASA NTRS2010

Ares I-X Ground Diagnostic Prototype

Automating prelaunch diagnostics for launch vehicles offers three potential benefits. First, it potentially improves safety by detecting faults that might otherwise have been missed so that they can be corrected before launch. Second, it potentially reduces launch delays by more quickly diagnosing the cause of anomalies that occur during prelaunch processing. Reducing launch delays will be critical to the success of NASA's planned future missions that require in-orbit rendezvous. Third, it potentially reduces costs by reducing both launch delays and the number of people needed to monitor the prelaunch process. NASA is currently developing the Ares I launch vehicle to bring the Orion capsule and its crew of four astronauts to low-earth orbit on their way to the moon. Ares I-X will be the first unmanned test flight of Ares I. It is scheduled to launch on October 27, 2009. The Ares I-X Ground Diagnostic Prototype is a prototype ground diagnostic system that will provide anomaly detection, fault detection, fault isolation, and diagnostics for the Ares I-X first-stage thrust vector control (TVC) and for the associated ground hydraulics while it is in the Vehicle Assembly Building (VAB) at John F. Kennedy Space Center (KSC) and on the launch pad. It will serve as a prototype for a future operational ground diagnostic system for Ares I. The prototype combines three existing diagnostic tools. The first tool, TEAMS (Testability Engineering and Maintenance System), is a model-based tool that is commercially produced by Qualtech Systems, Inc. It uses a qualitative model of failure propagation to perform fault isolation and diagnostics. We adapted an existing TEAMS model of the TVC to use for diagnostics and developed a TEAMS model of the ground hydraulics. The second tool, Spacecraft Health Inference Engine (SHINE), is a rule-based expert system developed at the NASA Jet Propulsion Laboratory. We developed SHINE rules for fault detection and mode identification. The prototype uses the outputs of SHINE as inputs to TEAMS. The third tool, the Inductive Monitoring System (IMS), is an anomaly detection tool developed at NASA Ames Research Center and is currently used to monitor the International Space Station Control Moment Gyroscopes. IMS automatically "learns" a model of historical nominal data in the form of a set of clusters and signals an alarm when new data fails to match this model. IMS offers the potential to detect faults that have not been modeled. The three tools have been integrated and deployed to Hangar AE at KSC where they interface with live data from the Ares I-X vehicle and from the ground hydraulics. The outputs of the tools are displayed on a console in Hangar AE, one of the locations from which the Ares I-X launch will be monitored. The full paper will describe how the prototype performed before the launch. It will include an analysis of the prototype's accuracy, including false-positive rates, false-negative rates, and receiver operating characteristics (ROC) curves. It will also include a description of the prototype's computational requirements, including CPU usage, main memory usage, and disk usage. If the prototype detects any faults during the prelaunch period then the paper will include a description of those faults. Similarly, if the prototype has any false alarms then the paper will describe them and will attempt to explain their causes.

Schwabacher, Mark↗

NASA NTRS2008

Algorithms for Spectral Decomposition with Applications to Optical Plume Anomaly Detection

The analysis of spectral signals for features that represent physical phenomenon is ubiquitous in the science and engineering communities. There are two main approaches that can be taken to extract relevant features from these high-dimensional data streams. The first set of approaches relies on extracting features using a physics-based paradigm where the underlying physical mechanism that generates the spectra is used to infer the most important features in the data stream. We focus on a complementary methodology that uses a data-driven technique that is informed by the underlying physics but also has the ability to adapt to unmodeled system attributes and dynamics. We discuss the following four algorithms: Spectral Decomposition Algorithm (SDA), Non-Negative Matrix Factorization (NMF), Independent Component Analysis (ICA) and Principal Components Analysis (PCA) and compare their performance on a spectral emulator which we use to generate artificial data with known statistical properties. This spectral emulator mimics the real-world phenomena arising from the plume of the space shuttle main engine and can be used to validate the results that arise from various spectral decomposition algorithms and is very useful for situations where real-world systems have very low probabilities of fault or failure. Our results indicate that methods like SDA and NMF provide a straightforward way of incorporating prior physical knowledge while NMF with a tuning mechanism can give superior performance on some tests. We demonstrate these algorithms to detect potential system-health issues on data from a spectral emulator with tunable health parameters.

Srivastava, Askok N.↗

NASA NTRS2006

Data Mining for ISHM of Liquid Rocket Propulsion Status Update

This document consists of presentation slides that review the current status of data mining to support the work with the Integrated Systems Health Management (ISHM) for the systems associated with Liquid Rocket Propulsion. The aim of this project is to have test stand data from Rocketdyne to design algorithms that will aid in the early detection of impending failures during operation. These methods will be extended and improved for future platforms (i.e., CEV/CLV).

Srivastava, Ashok↗

NASA NTRS2005

Brain-Computer Interfaces for 1-D and 2-D Cursor Control: Designs Using Volitional Control of the EEG Spectrum or Steady-State Visual Evoked Potentials

We have developed and tested two EEG-based brain-computer interfaces (BCI) for users to control a cursor on a computer display. Our system uses an adaptive algorithm, based on kernel partial least squares classification (KPLS), to associate patterns in multichannel EEG frequency spectra with cursor controls. Our first BCI, Target Practice, is a system for one-dimensional device control, in which participants use biofeedback to learn voluntary control of their EEG spectra. Target Practice uses a KF LS classifier to map power spectra of 30-electrode EEG signals to rightward or leftward position of a moving cursor on a computer display. Three subjects learned to control motion of a cursor on a video display in multiple blocks of 60 trials over periods of up to six weeks. The best subject s average skill in correct selection of the cursor direction grew from 58% to 88% after 13 training sessions. Target Practice also implements online control of two artifact sources: a) removal of ocular artifact by linear subtraction of wavelet-smoothed vertical and horizontal EOG signals, b) control of muscle artifact by inhibition of BCI training during periods of relatively high power in the 40-64 Hz band. The second BCI, Think Pointer, is a system for two-dimensional cursor control. Steady-state visual evoked potentials (SSVEP) are triggered by four flickering checkerboard stimuli located in narrow strips at each edge of the display. The user attends to one of the four beacons to initiate motion in the desired direction. The SSVEP signals are recorded from eight electrodes located over the occipital region. A KPLS classifier is individually calibrated to map multichannel frequency bands of the SSVEP signals to right-left or up-down motion of a cursor on a computer display. The display stops moving when the user attends to a central fixation point. As for Target Practice, Think Pointer also implements wavelet-based online removal of ocular artifact; however, in Think Pointer muscle artifact is controlled via adaptive normalization of the SSVEP. Training of the classifier requires about three minutes. We have tested our system in real-time operation in three human subjects. Across subjects and sessions, control accuracy ranged from 80% to 100% correct with lags of 1-5 seconds for movement initiation and turning.

Trejo, Leonard J.↗

NASA NTRS2004

Measures and Models for Estimating and Predicting Cognitive Fatigue

We analyzed EEG and ERPs in a fatiguing mental task and created statistical models for single subjects. Seventeen subjects (4 F, 18-38 y) viewed 4-digit problems (e.g., 3+5-2+7=15) on a computer, solved the problems, and pressed keys to respond (intertrial interval = 1 s). Subjects performed until either they felt exhausted or three hours had elapsed. Re- and post-task measures of mood (Activation Deactivation Adjective Checklist, Visual Analogue Mood Scale) confirmed that fatigue increased and energy decreased over time. We tested response times (RT); amplitudes of ERP components N1, P2, P300, readiness potentials; and amplitudes of frontal theta and parietal alpha rhythms for change as a function of time. For subjects who completed 3 h (n=9) we analyzed 12 15-min blocks. For subjects who completed at least 1.5 h (n=17), we analyzed the first-, middle-, and last 100 error-free trials. Mean RT rose from 6.7 s to 8.5 s over time. We found no changes in the amplitudes of ERP components. In both analyses, amplitudes of frontal theta and parietal alpha rose by 30% or more over time. We used 30-channel EEG frequency spectra to model the effects of time in single subjects using a kernel partial least squares classifier. We classified 3.5s EEG segments as being from the first 100 or the last 100 trials, using random sub-samples of each class. Test set accuracies ranged from 63.9% to 99.6% correct. Only 2 of 17 subjects had mean accuracies lower than 80%. The results suggest that EEG accurately classifies periods of cognitive fatigue in 90% of subjects.

Trejo, Leonard J.↗

NASA NTRS2003

Multimodal neuroelectric interface development

We are developing electromyographic and electroencephalographic methods, which draw control signals for human-computer interfaces from the human nervous system. We have made progress in four areas: 1) real-time pattern recognition algorithms for decoding sequences of forearm muscle activity associated with control gestures; 2) signal-processing strategies for computer interfaces using electroencephalogram (EEG) signals; 3) a flexible computation framework for neuroelectric interface research; and d) noncontact sensors, which measure electromyogram or EEG signals without resistive contact to the body.

Evaluation Studies↗

NASA NTRS2003

Kernel PLS-SVC for Linear and Nonlinear Discrimination

A new methodology for discrimination is proposed. This is based on kernel orthonormalized partial least squares (PLS) dimensionality reduction of the original data space followed by support vector machines for classification. Close connection of orthonormalized PLS and Fisher's approach to linear discrimination or equivalently with canonical correlation analysis is described. This gives preference to use orthonormalized PLS over principal component analysis. Good behavior of the proposed method is demonstrated on 13 different benchmark data sets and on the real world problem of the classification finger movement periods versus non-movement periods based on electroencephalogram.

Rosipal, Roman↗