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.

Sample report in support of "Discovering Anomalous Aviation Safety Events Using Scalable Data Mining Algorithms" manuscript.

This is a report on a continuing study of automated analyses of experiential textual reports to gain insight into the causal factors of human errors in aviation operations. The intent of this research is to better understand the quantitative and qualitative attributes of an aviation incident, and to identify the respective contributions of their interaction to incident occurrence.

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.

This paper provides a review of three different advanced machine learning algorithms for anomaly detection in continuous data streams from a ground-test firing of a subscale Solid Rocket Motor (SRM). This study compares Orca, one-class support vector machines, and the Inductive Monitoring System (IMS) for anomaly detection on the data streams. We measure the performance of the algorithm with respect to the detection horizon for situations where fault information is available. These algorithms have been also studied by the present authors (and other co-authors) as applied to liquid propulsion systems. The trade space will be explored between these algorithms for both types of propulsion systems.

Published at 12th AIAA Aviation Technology, Integration, and Operations (ATIO) Conference and 14th AIAA/ISSM 17 - 19 September 2012, Indianapolis, Indiana

We discuss a statistical framework that underlies envelope detection schemes as well as dynamical models based on Hidden Markov Models (HMM) that can encompass both discrete and continuous sensor measurements for use in Integrated System Health Management (ISHM) applications. The HMM allows for the rapid assimilation, analysis, and discovery of system anomalies. We motivate our work with a discussion of an aviation problem where the identification of anomalous sequences is essential for safety reasons. The data in this application are discrete and continuous sensor measurements and can be dealt with seamlessly using the methods described here to discover anomalous flights. We specifically treat the problem of discovering anomalous features in the time series that may be hidden from the sensor suite and compare those methods to standard envelope detection methods on test data designed to accentuate the differences between the two methods. Identification of these hidden anomalies is crucial to building stable, reusable, and cost-efficient systems. We also discuss a data mining framework for the analysis and discovery of anomalies in high-dimensional time series of sensor measurements that would be found in an ISHM system. We conclude with recommendations that describe the tradeoffs in building an integrated scalable platform for robust anomaly detection in ISHM applications.

Several different unsupervised anomaly detection algorithms have been applied to Space Shuttle Main Engine (SSME) data to serve the purpose of developing a comprehensive suite of Integrated Systems Health Management (ISHM) tools. As the theoretical bases for these methods vary considerably, it is reasonable to conjecture that the resulting anomalies detected by them may differ quite significantly as well. As such, it would be useful to apply a common metric with which to compare the results. However, for such a quantitative analysis to be statistically significant, a sufficient number of examples of both nominally categorized and anomalous data must be available. Due to the lack of sufficient examples of anomalous data, use of any statistics that rely upon a statistically significant sample of anomalous data is infeasible. Therefore, the main focus of this paper will be to compare actual examples of anomalies detected by the algorithms via the sensors in which they appear, as well the times at which they appear. We find that there is enough overlap in detection of the anomalies among all of the different algorithms tested in order for them to corroborate the severity of these anomalies. In certain cases, the severity of these anomalies is supported by their categorization as failures by experts, with realistic physical explanations. For those anomalies that can not be corroborated by at least one other method, this overlap says less about the severity of the anomaly, and more about their technical nuances, which will also be discussed.