Logarithmic multivariate Gaussian models are trained to evaluate the performance of aircrafts at different flight phases (takeoff, ascent, cruise, etc.) separately. For demonstration and validation, the developed model is applied to analyze performance anomalies associated with the mechanical system and pilot operation in a historical flight dataset. Applications include assisting transportation management systems by handling large amounts of historical flight datasets to analyze mechanical and operational anomalies, which may potentially improve future aeronautical system design and pilot training.
That model has been developed to evaluate the performance of aircrafts through sensor information from completed commercial scheduled flights. Such a model overcomes the difficulties associated with large size and high dimensionality in the flight dataset using a mini-batch training process and performance evaluation in the logarithmic domain. The developed model is expected to be an effective addition to current anomaly analysis and monitoring technologies for scheduled commercial flight.
Collected and summarized from the source below by Minh Pham https://db.vista.gov.vn:2095/science/article/pii/S0968090X19305418