Finding Precursors to Anomalous Drop in Airspeed During a Flight's Takeoff

Aerodynamic stall based loss of control in flight is a major cause of fatal flight accidents. In a typical takeoff, a flight's airspeed continues to increase as it gains altitude. However, in some cases, the airspeed may drop immediately after takeoff and when left uncorrected, the flight gets close to a stall condition which is extremely risky. The takeoff is a high workload period for the flight crew involving frequent monitoring, control and communication with the ground control tower. Although there exists secondary safety systems and specialized recovery maneuvers, current technology is reactive; often based on simple threshold detection and does not provide the crew with sufficient lead time. Further, with increasing complexity of automation, the crew may not be aware of the true states of the automation to take corrective actions in time. At NASA, we aim to develop decision support tools by mining historic flight data to proactively identify and manage high risk situations encountered in flight. In this paper, we present our work on finding precursors to the anomalous drop-in-airspeed (ADA) event using the ADOPT (Automatic Discovery of Precursors in Time series) algorithm. ADOPT works by converting the precursor discovery problem into a search for sub-optimal decision making in the time series data, which is modeled using reinforcement learning. We give insights about the flight data, feature selection, ADOPT modeling and results on precursor discovery. Some improvements to ADOPT algorithm are implemented that reduces its computational complexity and enables forecasting of the adverse event. Using ADOPT analysis, we have identified some interesting precursor patterns that were validated to be operationally significant by subject matter experts. The performance of ADOPT is evaluated by using the precursor scores as features to predict the drop in airspeed events.

[1]  C. Granger.  Investigating causal relations by econometric models and cross-spectral methods , 1969 .

[2]  John David Anderson,et al.  Introduction to Flight , 1985 .

[3]  Xin Xu,et al.  Sequential anomaly detection based on temporal-difference learning: Principles, models and case studies , 2010, Appl. Soft Comput..

[4]  Vahram Stepanyan,et al.  Stall Recovery Guidance Algorithms Based on Constrained Control Approaches , 2016 .

[5]  Eamonn J. Keogh,et al.  The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances , 2016, Data Mining and Knowledge Discovery.

[6]  Nikunj C. Oza,et al.  Discovery of Precursors to Adverse Events using Time Series Data , 2016, SDM.

[7]  Andrew Y. Ng,et al.  Pharmacokinetics of a novel formulation of ivermectin after administration to goats , 2000, ICML.

[8]  Thomas S. Donnelly.  An Improved Stall Warning System for General Aviation Aircraft , 1972 .

[9]  Michael S. Selig,et al.  Stall/post-stall modeling of the longitudinal characteristics of a general aviation aircraft , 2016 .

[10]  Ashok N. Srivastava,et al.  Multiple kernel learning for heterogeneous anomaly detection: algorithm and aviation safety case study , 2010, KDD.

[11]  P. S. Sastry,et al.  A survey of temporal data mining , 2006 .

[12]  John V. Foster,et al.  Simulation Study of a Commercial Transport Airplane During Stall and Post-Stall Flight , 2004 .

[13]  Inseok Hwang,et al.  Flight deck human-automation issue detection via intent inference , 2014 .

[14]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[15]  Timothy J. Etherington,et al.  Evaluating Technologies for Improved Airplane State Awareness and Prediction , 2016 .