An Adaptive Expert System for the Autonomous Detection of Aviation Mishap Leading Indicators
52nd Aerospace Sciences Meeting(2014)
Abstract
Risk mitigation and mishap prevention have remained significant challenges for Naval Aviation since the first Naval Aviation fatality in June 1913. Since that time various programmatic initiatives, organizational changes, and technological advances have been implemented to reduce flight related risks. One program recently established to help reduce the Naval Aviation mishap rate is Military Flight Operations Quality Assurance (MFOQA). MFOQA, derived from a comparable commercial aviation initiative, utilizes the collection, download, analysis, and visualization of data from aircraft onboard data collection systems to provide objective information that can be used to improve safety and operational readiness. One of the challenges to implementing MFOQA in Naval Aviation, however, is the ability to effectively and objectively analyze the huge volume of data collected. Since an impractical number of subject matter experts would be required to accomplish detailed analyses of the thousands of flight files generated by Naval aircraft, automated methods are needed to exploit the information that exists. An Adaptive Expert System (AES) was developed to replicate analyses that could otherwise only be performed by human analysts. The AES autonomously analyzes aircraft data and identifies anomalous events and trends. It presents objective results to aid the identification of aircrew performance that is outside statistical or prescribed norms and may be indicative of mishap precursors or leading indicators. The AES includes functionalities for rotary wing and fixed wing aircraft, and both single flight and aggregated analyses. This paper provides an overview of the evolution of MFOQA in Naval Aviation and the development of the AES including various analytical and presentation techniques employed. It also addresses how the AES supports the implementation of a robust MFOQA program by aiding the identification of potential mishap leading indicators.
MoreTranslated text
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined