Development of a Metric Concept that Differentiates Between Normal and Abnormal Operational Aviation Data
| Autor: | Daniele Baranzini, Matthew Stogsdill, Pernilla Ulfvengren |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
0211 other engineering and technologies 02 engineering and technology 010501 environmental sciences computer.software_genre Maskinteknik 01 natural sciences Physiology (medical) Safety Risk Reliability and Quality Set (psychology) 0105 earth and related environmental sciences Complement (set theory) Production Engineering Human Work Science and Ergonomics 021110 strategic defence & security studies Mechanical Engineering Aggregate (data warehouse) Produktionsteknik arbetsvetenskap och ergonomi Touchdown Data set Variable (computer science) Accidents Aviation Metric (unit) Performance indicator Data mining Aviation computer |
| Zdroj: | Risk Analysis. 42:1815-1833 |
| ISSN: | 1539-6924 0272-4332 |
| DOI: | 10.1111/risa.13680 |
| Popis: | There is a strong and growing interest in using the large amount of high-quality operationaldata available within an airline. One reason for this is the push by regulators to use data todemonstrate safety performance by monitoring the outputs of Safety P erformance Indicatorsrelative to targeted goals. However, the current exceedance-based approaches alone do notprovide sufficient operational risk information to support managers and operators makingproximate real-time data-driven decisions. The purpose of this study was to develop and testa set of metrics which can complement the current exceedance-based methods. The approachwas to develop two construct variables that were designed with the aim to: (1) create anaggregate construct variable that can differentiate between normal and abnormal landings(row_mean); and (2) determine if temporal sequence patterns can be detected within thedata set that can differentiate between the two landing groups (row_sequence). To assessthe differentiation ability of the aggregate constructs, a set of both statistical and visual testswere run in order to detect quantitative and qualitative differences between the data seriesrepresenting two landing groups prior to touchdown. The result, verified with a time series k-means cluster analysis, show that the composite constructs seem to differentiate normal andabnormal landings by capturing time-varying importance of individual variables in the final300 seconds before touchdown. Together the approaches discussed in this article present aninteresting and complementary way forward that should be further pursued. QC 20210527 PROSPERO |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text