Browsing by Author "Nichanian, Arthur"

Now showing 1 - 6 of 6
  • Thumbnail Image
    ItemOpen Access
    Evaluating cause-effect relationships in accident investigation using HFACS-DEMATEL
    (Springer, 2024-07-01) Chan, Wesley Tsz-Kin; Li, Wen-Chin; Nichanian, Arthur; Manikath, Elizabeth
    This paper addresses the ‘routes to failure’ in the causal chain of events as categorized using the Human Factors Analysis and Classification System (HFACS) framework. By using the Decision-Making Trial and Evaluation Laboratory (DEMATEL) method to evaluate the comparative influence of each HFACS category on other categories, the present research aims to classify each HFACS category as either an overall ‘cause’ or an overall ‘effect’ factor, and to give each HFACS category a comparable statistical value of their overall level of influence. Analysis of N = 30 responses from aviation safety experts identified that frontline perception faults had the potential to influence higher-level preconditions, and that ‘Environmental Factors’ were found to have the highest overall influence amongst HFACS categories at levels 1 and 2. The findings support the use of the DEMATEL method in the selection and direction of safety interventions. Safety remedies focusing on ‘cause’ factors are likely to have additional second-order benefits on associated ‘effects’, and more influential categories are likely to be more effective in influencing overall system safety. The methodology can assist safety managers in selecting and prioritizing safety initiatives, especially when faced with issues such as monetary or time constraints in the industrial context.
  • Thumbnail Image
    ItemOpen Access
    Future flight safety monitoring: comparison of different computational methods for predicting pilot performance under time series during descent by flight data and eye-tracking data
    (Springer, 2024-06-01) Wang, Yifan; Li, Wen-Chin; Nichanian, Arthur; Korek, Wojciech Tomasz; Chan, Wesley Tsz-Kin
    Introduction. Effective and real-time analysis of pilot performance is important for improving flight safety and enabling remote flight safety control. The use of flight data and pilot physiological data to analyse and predict pilot performance is an effective means of achieving this monitoring. Research question. This research aims to compare two forecasting methods (XGBoost and Transformer) in evaluating and predicting pilot performance using flight data and eye tracking data. Method. Twenty participants were invited to fly an approach using Instrument Landing System (ILS) guidance in the Future Systems Simulator (FSS) while wearing Pupil-Lab eye tracker. The deviation to the desired route, the pupil diameter and the gaze positions were selected for forecasting the flight performance indicator: the difference between the aircraft altitude and the reference altitude corresponding to the ideal 3-degree glide path. Utilize XGBoost and the Transformer forecasting technique to develop a forecasting model using the data from this research, and conduct a comparative analysis of the accuracy and convenience of both models. Results & Discussion. The result demonstrates that using XGBoost regression model had a higher prediction accuracy, (RMSEXGBoots = 42.29, RMSETransformer = 102.10) and its easier to achieve a high prediction accuracy than Transformer as Transformer forecasting method placed a high demand on debugging model and computing equipment. The deviation to desired route and the pupil diameter were more important in the XGBoost model. Conclusion. The use of machine learning and deep learning methods enables the monitoring and prediction of flight performance using flight data and pilot physiological data. The comparison of the two methods shows that it is not necessarily the newer and more complex technology that can build more accurate and faster prediction models, but building the right model based on the data is important for real-time flight data monitoring and prediction in the future.
  • Thumbnail Image
    ItemOpen Access
    Investigating the impacts of COVID-19 on aviation safety based on occurrences captured through flight data monitoring
    (Taylor & Francis, 2022-12-19) Li, Wen-Chin; Nichanian, Arthur; Lin, John; Braithwaite, Graham
    The COVID-19 pandemic led to growing concerns about pilots’ proficiency due to the significant decrease in flight operations. The objective of this research is to provide a proactive approach to mitigate potential risks in flight operations associated with the impact of the COVID-19 pandemic using flight data monitoring (FDM). The results demonstrated significant associations between the pandemic impacts and FDM exceedance categories, flight phases and fleets. Manual flying skill decay, lack of practice effects on use of standard operating procedures and knowledge of flight deck automation should be considered by airlines when preparing for the return to normal operations. An FDM Programme allows prediction of the probability and severity of occurrences for developing an effective SMS within an airline. To mitigate the impacts of the pandemic, tailored training sessions must be implemented, and airlines should strive to avoid additional optional procedures where practicable.
  • Thumbnail Image
    ItemOpen Access
    Self-organising maps for comparing flying performance using different inceptors
    (Springer, 2024-06-01) Nichanian, Arthur; Li, Wen-Chin; Korek, Wojciech Tomasz; Wang, Yifan; Chan, Wesley Tsz-Kin
    This paper addresses a new data analysis method which is suitable to cluster flight data and complement current exceedance-based flight data monitoring programmes within an airline. The data used for this study consists of 296 simulated approaches from 4.5 NM to 1 NM to the runway threshold, flown by 74 participants (both pilots and non-pilots) with either a conventional sidestick or a gamepad in the future flight simulator at Cranfield University. It was clustered and analysed with the use of Kohonen’s Self-Organising Maps (SOM) algorithm. The results demonstrate that SOM can be a meaningful indicator for safety analysts to accurately cluster both optimal and less-optimal flying performance. This methodology can therefore complement current deviation-based flight data analyses by highlighting day-to-day as well as exceptionally good performance, bridging the cap of current analyses with safety-II principles.
  • Thumbnail Image
    ItemOpen Access
    What can we learn from severity index on flight data monitoring? analysis of safety resilience in flight operations during COVID-19 disruptions
    (Taylor & Francis, 2023-11-22) Li, Wen-Chin; Nichanian, Arthur; Lin, John; Braithwaite, Graham
    The unexpected spread of the pandemic raised concerns regarding pilots’ skill decay resulting from the significant drops in the frequency of flights by about 70%. This research retrieved 4761 Flight Data Monitoring (FDM) occurrences based on the FDM programme containing 123,140 flights operated by an international airline between June 2019 and May 2021. The FDM severity index was analysed by event category, aircraft type, and flight phase. The results demonstrate an increase in severity score from the pre-pandemic level to the pandemic onset on events that occurred on different flight phases. This trend is not present in the third stage, which indicates that pilots and the safety management system of the airline demonstrated resilience to cope with the flight disruptions during the pandemic. Through the analysis of event severity, FDM enables safety managers to recommend measures to increase safety resilience and self-monitoring capabilities of both operators and regulators.
  • No Thumbnail Available
    ItemOpen Access
    What can we learn from Severity Index on Flight Data Monitoring? Investigating the impacts of COVID-19 disrupting pilots' proficiency
    (Cranfield University, 2023-02-28 09:06) Li, Wen-Chin; Nichanian, Arthur; Braithwaite, Graham; Lin, John
    FDM data containing 4,761 FDM exceedance events retrieved from 123,140 flights on both Airbus and Boeing aircraft, operated in an international airline was collected from June 2019 to May 2021 for 24 months and was classified under three eight-month stages. The severity index on FDM was analyzed by event category, aircraft type, and flight phase.