Using aircraft data recorded during flight to predict aircraft engine behavior
Historical aircraft data recorded during flight associated with a plurality of aircraft engines and a plurality of prior aircraft flights is accessed and metrics from the aircraft data recorded during flight is automatically calculated on a per-flight basis, and a probabilistic model is employed to capture and represent relationships based on the calculated metrics, the relationships including a plurality of engine parameters and flight parameters. Conditional probability distributions are then calculated for a particular aircraft engine during a potential or historical aircraft flight based on the probabilistic model, engine parameter values associated with the particular aircraft engine, and flight parameter values associated with the potential or historical aircraft flight, and indications associated with the calculated conditional probability distributions are displayed.
1. A method associated with aircraft engines, comprising:
accessing historical aircraft data recorded during flight associated with a plurality of aircraft engines and a plurality of prior aircraft flights;
automatically calculating metrics from the aircraft data recorded during flight on a per-flight basis;
employing a probabilistic model to capture and represent relationships based on the calculated metrics, the relationships including a plurality of engine parameters and flight parameters;
calculating at least one conditional probability distribution for a particular aircraft engine during a potential or historical aircraft flight based on the probabilistic model, engine parameter values associated with the particular aircraft engine, and flight parameter values associated with the potential or historical aircraft flight; and
displaying an indication associated with the at least one calculated conditional probability distribution.
2. The method of claim 1 , wherein the at least one conditional probability distribution represents probabilities that an exhaust gas temperature value will exceed a maximum threshold value during the potential aircraft flight.
3. The method of claim 2 , wherein the probabilistic model comprises a Gaussian mixture model.
4. The method of claim 3 , wherein metrics from the aircraft data recorded during flight are further automatically calculated on at least one of: (i) a per-airport basis, (ii) a per-engine type basis, (iii) a per-engine model basis, (iv) a per-aircraft type basis, and (v) a per-aircraft model basis.
5. The method of claim 1 , further comprising:
receiving, from an operator via an interactive graphical display interface, an adjustment to at least one of an engine parameter value and a flight parameter value;
re-calculating the at least one conditional probability distribution for the particular aircraft engine during the potential aircraft flight based on the probabilistic model in accordance with the adjustment; and
displaying an indication associated with the re-calculated at least one conditional probability distribution.
6. The method of claim 1 , further comprising:
automatically generating a recommended adjustment to at least one of an engine parameter value and a flight parameter value based on the conditional probability distribution for the particular aircraft engine during the potential aircraft flight.