Anomaly Detection in General-Aviation Operations Using Energy Metrics and Flight-Data Records

Abstract

Among operations in the General Aviation community, one of the most important objectives is to improve safety across all flight regimes. Flight data monitoring or Flight Operations Quality Assurance programs have percolated in the General Aviation sector with the aim of improving safety by analyzing and evaluating flight data. Energy-based metrics provide measurable indications of the energy state of the aircraft and can be viewed as an objective currency to evaluate various safety-critical conditions. The use of data mining techniques for safety analysis, incident examination, and fault detection is gaining traction in the aviation community. In this paper, a generic methodology is presented for identifying anomalous flight data records from General Aviation operations in the approach and landing phase. Energybased metrics, identified in previous work, are used to generate feature vectors for each flight data record. Density-based clustering and one-class classification are then used together for anomaly detection using energy-based metrics. A demonstration of this methodology on a set of actual flight data records from routine operations as well as simulated flight data is presented highlighting its potential for retrospective safety analysis. Anomaly detection using energy metrics, specifically, is a novel application presented here.

Recent Advances in Anomaly Detection Methods Applied to Aviation

“…Abnormal approaches with MKAD: [104] (2011) GA approach and landing anomalies with OC-SVM: [105] (2017)…”

“…With the aim of improving the safety of General Aviation operations, Puranik et al [105] propose a framework to identify anomalies based on a OC-SVM model. After a classical preprocessing phase to clean the raw multivariate time series data, a set of feature vectors corresponding to the energy metrics detailed in [112] are computed, such as the Specific Total Energy (STE) or the Specific Potential Energy (SPE).…”

“…TempAD is able to generate for each cluster STL predicates defining the bounds of normal flights as a function of time, distance to touchdown or aircraft state vectors (including latitude, longitude, altitude, ground speed). The representative features to find anomalies include some of the energy features used in [105]. The method is evaluated on real surveillance data from the terminal airspace at New York La Guardia airport, covering several thousands of arrival flights.…”

Critical Parameter Identification for Safety Events in Commercial Aviation Using Machine Learning

“…For example, Hegde and Rokseth [9] have conducted a survey of ML applications to engineering risk assessment. However, prior studies have mostly used machine learning techniques to perform retrospective analyses of flight data records to detect anomalies during routine operations [10][11][12][13][14][15][16][17]. In all these anomaly detection approaches, identification of precursors or causal factors is conducted a-posteriori by SME analysis.…”

Recent Advances in Anomaly Detection Methods applied to Aviation

“…[104] (2011) GA approach and landing anomalies with OC-SVM:[105] (2017) Distance-based Anomalous pilot switching with SequenceMiner:[18] (2009) Anomalous take-off and approach operations:[19] (2011),[20](2015) Anomalous safety events with LoOP:[16] (2019) Anomalous taxi paths with hierarchical clustering: [22] (2019) Anomalous radiotelephony readbacks with kNN: [106] (2018) Reconstruction-based Atypical aviation safety data with KPCA: [107] (2017) Atypical approaches and landings with FPCA: [52] (2018) Anomalous trajectories in TMA and en-route: [108] (2018), [109] (2019) Anomalous transitions between sector configurations: [110] (2018) Anomalous ADS-B messages with ConvLSTM-AE: [86] (2019) Statistical-based Anomalous flights with VARX: [38] (2016), Anomalous flight switches with VAR: [39] (2016) Abnormal flight data with GMM: [21] (2016) Anomalous air traffic congestion with ICA: [37] (2019) Temporal-logic based Anomalous trajectories in terminal airspace with TempAD: [103], [111] (2019) Application of anomaly detection models to aviation use cases4.1. Anomaly detection for air traffic operationsOne application area in aviation where anomaly detection techniques have particularly been applied to is in the identification of significant operational events in flight data.…”