Air transportation, one of the most important modes of transportation, is also one of the safest. Nevertheless, the public demands that safety levels continuously improve and that the absolute number of aviation accidents continue to decline, even as air-traffic levels increase. On February 12, 1997, after the tragedy of TWA 800, President William J. Clinton declared, “We will achieve a national goal of reducing the fatal aircraft accident rate by 80% within 10 years.” In response to this presidential declaration, the administrator of NASA announced that NASA would undertake a new program in aviation safety in support of this objective. NASA quickly formed the Aviation Safety Investment Strategy Team (ASIST) in collaboration with the Federal Aviation Administration (FAA) and the National Transportation Safety Board (NTSB), which organized a series of five workshops to examine the options and recommend an approach for NASA to develop the enabling technologies that address the president's goal. The exceptional and dedicated participation from all sectors of the aviation industry in the development of NASA’s strategy was remarkable.

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.

A proactive approach to identifying and alleviating life-threatening conditions in the aviation system entails a well-defined process of identifying threats, evaluating causes, assessing risks, and implementing appropriate solutions. This process is not a trivial undertaking. It requires continuous monitoring of system performance in a non-punitive culture; learning from normal operational experience; comparing actual performance to expected performance; identifying the precursor events and conditions that foreshadow most accidents; designing appropriate interventions to minimize the risk of their occurrence; and having a system in place to monitor the efficacy of the interventions.

Modern aircraft are producing data at an unprecedented rate with hundreds of parameters being recorded on a second by second basis. The data can be used for studying the condition of the hardware systems of the aircraft and also for studying the complex interactions between the pilot and the aircraft. NASA is developing novel data mining algorithms to detect precursors to aviation safety incidents from these data sources. This talk will cover the theoretical aspects of the algorithms and practical aspects of implementing these techniques to study one of the most complex dynamical systems in the world: the national airspace.

The worldwide civilian aviation system is one of the most complex dynamical systems created. Most modern commercial aircraft have onboard flight data recorders that record several hundred discrete and continuous parameters at approximately 1Hz for the entire duration of the flight. These data contain information about the flight control systems, actuators, engines, landing gear, avionics, and pilot commands. In this paper, recent advances in the development of a novel knowledge discovery process consisting of a suite of data mining techniques for identifying precursors to aviation safety incidents are discussed. The data mining techniques include scalable multiple-kernel learning for large-scale distributed anomaly detection. A novel multivariate time-series search algorithm is used to search for signatures of discovered anomalies on massive datasets. The process can identify operationally significant events due to environmental, mechanical, and human factors issues in the high-dimensional flight operations quality assurance data. All discovered anomalies are validated by a team of independent domain experts. This novel automated knowledge discovery process is aimed at complementing the state-of-the-art human-generated exceedance-based analysis that fails to discover previously unknown aviation safety incidents. In this paper, the discovery pipeline, the methods used, and some of the significant anomalies detected on real-world commercial aviation data are discussed.

The world-wide aviation system is one of the most complex dynamical systems ever developed and is generating data at an extremely rapid rate. Most modern commercial aircraft record several hundred flight parameters including information from the guidance, navigation, and control systems, the avionics and propulsion systems, and the pilot inputs into the aircraft. These parameters may be continuous measurements or binary or categorical measurements recorded in one second intervals for the duration of the flight. Currently, most approaches to aviation safety are reactive, meaning that they are designed to react to an aviation safety incident or accident. In this paper, we discuss a novel approach based on the theory of multiple kernel learning to detect potential safety anomalies in very large data bases of discrete and continuous data from world-wide operations of commercial fleets. We pose a general anomaly detection problem which includes both discrete and continuous data streams, where we assume that the discrete streams have a causal influence on the continuous streams. We also assume that atypical sequences of events in the discrete streams can lead to off-nominal system performance. We discuss the application domain, novel algorithms, and also discuss results on real-world data sets. Our algorithm uncovers operationally significant events in high dimensional data streams in the aviation industry which are not detectable using state of the art methods.

The world-wide aviation system is one of the most complex dynamical systems ever developed and is generating data at an extremely rapid rate. Most modern commercial aircraft record several hundred flight parameters including information from the guidance, navigation, and control systems, the avionics and propulsion systems, and the pilot inputs into the aircraft. These parameters may be continuous measurements or binary or categorical measurements recorded in one second intervals for the duration of the flight. Currently, most approaches to aviation safety are reactive, meaning that they are designed to react to an aviation safety incident or accident. Here, we discuss a novel approach based on the theory of multiple kernel learning to detect potential safety anomalies in very large data bases of discrete and continuous data from world-wide operations of commercial fleets. We pose a general anomaly detection problem which includes both discrete and continuous data streams, where we assume that the discrete streams have a causal influence on the continuous streams. We also assume that atypical sequence of events in the discrete streams can lead to off-nominal system performance. We discuss the application domain, novel algorithms, and also briefly discuss results on synthetic and real-world data sets. Our algorithm uncovers operationally significant events in high dimensional data streams in the aviation industry which are not detectable using state of the art methods.

A prognostic system makes it possible to anticipate loss of functionality before it occurs with sufficient lead time to take actions that mitigate the impact of this loss. We focus on the forms of mitigation within the flight vehicle that influence the operational dynamics but do not directly amend the mission plan. Thus, we focus upon the reconfiguration of the feedback control strategy for the flight system. The high degree of complexity in the design and dynamics of modern aircraft is typically handled using a hierarchical control scheme in which there are several levels of control at increasing levels of responsibility: the component level, the subsystem level, and the system level. Our reconfiguration strategy involves mitigating problems that are detected at the component level at both the level in which the fault is detected and higher levels as well. There are, thus, two subproblems to the reconfiguration: (a) an adaptive control problem at the lower level to extend component life and derive new component performance limits, and (b) a supervisory control problem at the higher level to adapt the system controller to maximize system capability while respecting the performance limitations. Since our reconfiguration occurs in the context of a dynamic system, we need to respect the stability implications of the reconfiguration. To address this, we apply bandwidth analyses at the component level and the systems level in a robust performance context. A conservative criterion for stability is to impose rate limits for reconfiguration that insure that undesired, and possibly unmodeled, modes of behavior are not driven by reconfiguration activities. For specific hardware, extensions beyond this conservative approach may be warranted (e.g. to catch faulty behavior) and validated on a case-by-case basis, essentially by extending the component modeling to include a model of behavior under certain types of reconfiguration.

As fault diagnosis and prognosis systems in aerospace applications become more capable, the ability to utilize information supplied by them becomes increasingly important. While certain types of vehicle health data can be effectively processed and acted upon by crew or support personnel, others, due to their complexity or time constraints, require either automated or semi-automated reasoning. Prognostics-enabled Decision Making (PDM) is an emerging research area that aims to integrate prognostic health information and knowledge about the future operating conditions into the process of selecting subsequent actions for the system. The newly developed PDM algorithms require suitable software and hardware platforms for testing under realistic fault scenarios. The paper describes the development of such a platform, based on the K11 planetary rover prototype. A variety of injectable fault modes are being investigated for electrical, mechanical, and power subsystems of the testbed, along with methods for data collection and processing. In addition to the hardware platform, a software simulator with matching capabilities has been developed. The simulator allows for prototyping and initial validation of the algorithms prior to their deployment on the K11. The simulator is also available to the PDM algorithms to assist with the reasoning process. A reference set of diagnostic, prognostic, and decision making algorithms is also described, followed by an overview of the current test scenarios and the results of their execution on the simulator.

Failure prognosis - as a natural extension to the fault detection and isolation (FDI) problem - has become a key issue in a world where the economic impact of system reliability and cost-effective operation of critical assets is steadily increasing. Failure prognostic algorithms aim to characterize the evolution of incipient fault conditions in complex dynamic processes, thus allowing to estimate of the remaining useful life (RUL) of subsystems and components. Several examples can be used here to illustrate the range of possible applications for these algorithms: electro-mechanical systems, continuous-time manufacturing processes, structural damage analysis, and even fault tolerant software architectures. Most of them have in common the fact that they are highly complex, nonlinear, and affected by large-grain uncertainty. We introduce in this chapter an integrated failure prognosis architecture that is applicable to a variety of aircraft systems and industrial processes. We are targeting a specific rotorcraft system as a prototypical testbed for proof-of-concept. The overall architecture consists of an on-board and an off-board module for eventual on-platformimplementation purposes.