Selecting altitude changing phase routes for aircraft
A method for selecting an altitude changing phase route for an aircraft is presented. The method comprises receiving sequences of multivariate flight data from at least one prior flight, receiving a set of flight parameters for the aircraft including at least a total altitude change and a takeoff weight, and receiving a set of candidate altitude changing phase routes having candidate step profiles. For each candidate altitude changing phase route, a sequence of fuel burn quantities is predicted for the respective candidate step profile based on at least the sequences of multivariate flight data and the set of flight parameters. The fuel burn quantities are summed over the candidate altitude changing phase route to obtain an estimated fuel burn. A preferred candidate altitude changing phase route having a lowest estimated fuel burn is indicated.
1 . A method for selecting an altitude changing phase route for an aircraft that is at least a partially autonomous aircraft, the method performed by a computing system of one or more computing devices, the method comprising:
receiving sequences of multivariate flight data from at least one prior flight, the multivariate flight data discretized based on step profiles and an amount of fuel burn for altitude changing phases of each prior flight, each step profile comprising a plurality of steps, each step characterized by a step size indicating a duration where the aircraft remains level, and a threshold indicating a delta flight level between time steps;
receiving a set of flight parameters for the aircraft including at least a total altitude change for a planned altitude changing phase and a takeoff weight;
receiving a set of candidate altitude changing phase routes, each candidate altitude changing phase route having a separate candidate step profile;
for each candidate altitude changing phase route,
predicting a sequence of fuel burn quantities for the respective candidate step profile based on at least the sequences of multivariate flight data and the set of flight parameters; and
summing the fuel burn quantities over the candidate altitude changing phase route to obtain an estimated fuel burn;
indicating a preferred candidate altitude changing phase route having a lowest estimated fuel burn; and
controlling the aircraft to follow the preferred candidate altitude changing phase route.
2 . The method of claim 1 , further comprising fueling the aircraft based at least on the lowest estimated fuel burn.
3 . The method of claim 1 , wherein the planned altitude changing phase is a climb phase.
4 . The method of claim 1 , wherein the planned altitude changing phase is a descent phase.
5 . The method of claim 4 , wherein the flight parameters further include a top-of-descent weight of the aircraft.
6 . The method of claim 4 , wherein the flight parameters further include a time to landing.
7 . The method of claim 1 , wherein the flight parameters further include a lateral distance.
8 . The method of claim 7 , wherein a length of one or more altitude changing phases included in the multivariate flight data is adjusted to a common altitude changing phase length.
9 . The method of claim 1 , wherein predicting the sequence of fuel burn quantities is further based on a hidden state of a trained machine, the hidden state developed in a trainable machine, wherein for each of a pre-selected series of prior flights, a corresponding sequence of multivariate flight data recorded during a respective prior flight of the pre-selected series of prior flights is processed in the trainable machine to develop the hidden state, which minimizes an overall residual for replicating the fuel burn quantities in each corresponding sequence.
10 . The method of claim 1 , wherein discretizing multivariate flight data includes grouping together multivariate flight data for flights with similar characteristics into a plurality of buckets.
11 . The method of claim 1 , wherein discretizing multivariate flight data includes adjusting a combination of step size and threshold based on which combinations produce datasets with sufficient size to evaluate candidate altitude changing phase routes.
12 . The method of claim 1 , wherein the sequence of fuel burn quantities for the respective candidate step profile is further based on atmospheric conditions for the candidate altitude changing phase route.
13 . A machine trained to make fuel burn predictions for aircraft flight, comprising:
an input engine configured to:
receive sequences of multivariate flight data from at least one prior flight of an aircraft, the multivariate flight data discretized based on step profiles and an amount of fuel burn for altitude changing phases of each prior flight, each step profile comprising a plurality of steps, each step characterized by a step size indicating a duration where the aircraft remains level, and a threshold indicating a delta flight level between time steps;
receive a set of candidate altitude changing phase routes, each candidate altitude changing phase route having a separate candidate step profile; and
receive a set of flight parameters including at least a total altitude change for a planned altitude changing phase and a takeoff weight;
a trained encoder arranged logically upstream of a trained decoder, wherein the encoder is trained to emit a vector that featurizes an input sequence of multivariate flight data, and wherein the decoder is trained to replicate fuel burn quantities of the input sequence based on the vector, thereby generating an output sequence;
a prediction engine configured to, for each candidate altitude changing phase route, predict a sequence of fuel burn quantities for the respective candidate step profile based on at least the sequences of multivariate flight data, the set of flight parameters, and the output sequence;
a summation engine configured to sum the fuel burn quantities over each candidate altitude changing phase route to obtain an estimated fuel burn; and
an output engine configured to indicate a preferred candidate altitude changing phase route having a lowest estimated fuel burn.
14 . The machine of claim 13 , wherein the planned altitude changing phase is one of a climb phase and a descent phase.
15 . The machine of claim 13 , wherein the multivariate flight data is discretized based on step profile.
16 . The machine of claim 13 , further comprising an adjustment engine configured to adjust a length of one or more altitude changing phases included in the multivariate flight data to a common altitude changing phase length.
17 . The machine of claim 13 , wherein the encoder and the decoder are configured according to a long short-term memory (LSTM) architecture.
18 . The machine of claim 17 , further comprising a fully connected layer configured to interpret the fuel burn quantities at each time step of the output sequence.
19 . A system for controlling an aircraft that is at least a partially autonomous aircraft, the system comprising:
a controller comprising one or more logic machines and one or more storage machines, the one or more storage machines storing instructions that when executed, cause the controller to:
receive sequences of multivariate flight data from at least one prior flight, the multivariate flight data discretized based on step profiles and an amount of fuel burn for altitude changing phases of each prior flight, each step profile comprising a plurality of steps, each step characterized by a step size indicating a duration where the aircraft remains level, and a threshold indicating a delta flight level between time steps;
receive a set of flight parameters for the aircraft including at least a total altitude change for a planned altitude changing phase and a takeoff weight;
receive a set of candidate altitude changing phase routes, each candidate altitude changing phase route having a separate candidate step profile;
for each candidate altitude changing phase route,
predict a sequence of fuel burn quantities for the respective candidate step profile based on at least the sequences of multivariate flight data and the set of flight parameters; and
sum the fuel burn quantities over the candidate altitude changing phase route to obtain an estimated fuel burn;
indicate a preferred candidate altitude changing phase route having a lowest estimated fuel burn; and
control the aircraft to follow the preferred candidate altitude changing phase route.
20 . The system of claim 19 , wherein the one or more storage machines further storing instructions that when executed, cause the controller to:
fuel the aircraft based at least on the lowest estimated fuel burn.