System and method for terminal procedure prediction for flight planning

Abstract

To provide a system and method for terminal procedure prediction for flight planning.SOLUTION: A system and method for terminal procedure prediction for flight planning includes steps of: obtaining, on a processor, input data corresponding to an upcoming flight of an aircraft; obtaining, on the processor, predicted data corresponding to the upcoming flight; and processing, on the processor, the input data and predicted data in order to obtain a terminal procedure prediction associated with the upcoming flight. The terminal procedure prediction is at least partially based on flight planning of historical flights having conditions similar to the input data and the predicted data.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001]

[0001] The present disclosure relates generally to systems and methods for terminal procedure prediction for flight planning. [Background technology]

[0002]

[0002] As air traffic continues to grow, efficient aircraft management becomes increasingly important. One aspect of aircraft management involves the generation of an initial flight plan for each aircraft, including one or more terminal procedures associated with each of the departure and arrival airports. Terminal procedures are generally developed several hours in advance of the upcoming flight, based on experience, judgment, and currently available information approximately four hours prior to the flight.

[0003]

[0003] With the increasing challenges of modern air traffic, and ubiquitous complicating factors such as changing weather, it is often necessary to modify the flight plan to select new terminal procedures (one or more) while the aircraft is in flight. Such additional tasks burden the flight crew and interfere with other important flight tasks, such as maintaining the safety of passengers and the operational efficiency of the aircraft itself. Summary of the Invention

[0004]

[0004] In one particular embodiment, a device includes one or more processors configured to obtain input data corresponding to a future flight of the aircraft. The processor(s) are also configured to obtain forecast data corresponding to the future flight. The processor(s) are also configured to process the input data and the forecast data to obtain a terminal procedure forecast associated with the future flight. The terminal procedure forecast is based at least in part on flight plans of past flights having similar conditions to the input data and the forecast data.

[0005]

[0005] In another particular embodiment, a method includes obtaining, in a processor, input data corresponding to a future flight of an aircraft. The method also includes obtaining, in the processor, forecast data corresponding to the future flight. The method also includes processing, in the processor, the input data and the forecast data to obtain a terminal procedure forecast associated with the future flight. The terminal procedure forecast is based at least in part on flight plans of past flights having similar conditions as the input data and the forecast data.

[0006]

[0006] In another particular embodiment, a non-transitory computer-readable medium includes instructions that, when executed by one or more processors, cause the one or more processors to obtain input data corresponding to a future flight of an aircraft. The instructions also cause the one or more processors to obtain forecast data corresponding to the future flight. The instructions also cause the one or more processors to process the input data and the forecast data to obtain a terminal procedure forecast associated with the future flight. The terminal procedure forecast is based at least in part on a flight plan of a past flight having similar conditions as the input data and the forecast data.

[0007]

[0007] In another particular embodiment, a device includes means for obtaining, in a processor, input data corresponding to a future flight of an aircraft. The device also includes means for obtaining, in the processor, forecast data corresponding to the future flight. The device also includes means for processing, in the processor, the input data and the forecast data to obtain a terminal procedure forecast associated with the future flight. The terminal procedure forecast is based at least in part on flight plans of past flights having similar conditions as the input data and the forecast data.

[0008]

[0008] The features, functions, and advantages described herein can be realized alone in various embodiments or can be combined in yet other embodiments, further details of which can be seen with reference to the following specification and drawings. [Brief description of the drawings]

[0009] [Figure 1]

[0009] An exemplary system for terminal procedure prediction for flight planning according to some embodiments of the present disclosure is shown. [Diagram 2]

[0010] FIG. 1 illustrates an example diagram of a comparison of past planned flight paths for an aircraft traveling near multiple waypoints with respect to a first past actual flight path and a second past actual path, in accordance with some embodiments of the present disclosure. [Diagram 3]

[0011] 1 illustrates an example architecture for terminal procedure prediction for flight planning, in accordance with some embodiments of the present disclosure. [Figure 4]

[0012] 1 is a flowchart of an example method for terminal procedure prediction for flight planning, according to some embodiments of the present disclosure. [Diagram 5]

[0013] FIG. 1 is a block diagram of a computing environment including a computing device configured to support aspects of computer-implemented methods and computer-executable program instructions (or codes) according to some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010]

[0014] Accurate, automated, data-driven predictions of terminal procedures are not generally available. The disclosed systems and methods leverage existing databases, contextual information, and state predictions to generate accurate predictions of the most likely terminal procedure(s) for a particular flight of an aircraft, as well as predictions of the likelihood and location of direct maneuvers (e.g., deviations from a planned flight plan approved by an air traffic control system) that can, in some embodiments, modify the flight plan.

[0011]

[0015] Terminal procedures help ensure the safety of aircraft operations and are maintained by a combination of airlines, airports, and regulatory authorities, such as the Federal Aviation Administration. For example, terminal procedures include instructions that guide aircraft flight through arrival at a particular airport and that manage the flow of arriving aircraft into a busy terminal area. Terminal procedures may also include a set of predetermined waypoints, altitude and speed restrictions, and communication protocols between pilots and air traffic controllers.

[0012]

[0016] A technical advantage of the present disclosure is the ability to automatically and efficiently use historical data, contextual information, and state predictions to generate accurate predictions of the appropriate terminal procedures an aircraft will require at its arrival and departure airports. Aircraft specific models can be used in many data-driven decision-making processes, such as improving aircraft maintenance and optimizing fuel consumption.

[0013]

[0017] The drawings and the following description show several specific exemplary embodiments. Those skilled in the art will recognize that, even if not explicitly described or shown in the present specification, they may devise various configurations that embody the principles described herein and are included in the scope of the claims that follow this specification. Furthermore, any examples described herein are intended to aid in the understanding of the principles of the present disclosure and are not intended to be limiting. As a result, the present disclosure is not limited to the specific embodiments or examples described below, but is limited by the claims and their equivalents.

[0014]

[0018] Certain embodiments are described herein with reference to the drawings. In the description, common features are given common reference numbers throughout the drawings. Various terms are used herein only to describe particular implementations and are not intended to be limiting. For example, the singular forms "a," "an," and "the" are intended to include the plural, unless the context clearly indicates otherwise. Furthermore, some features described herein may be present in the singular in some embodiments and in the plural in other embodiments. To illustrate, FIG. 1 depicts a system 100 including one or more processors ("(one or more) processors 106" in FIG. 1), which indicates that in some embodiments, the system 100 includes a single processor 106 and in other embodiments, the system 100 includes multiple processors 106. For ease of reference herein, such features are generally introduced as "one or more" features, followed by a single or optionally multiple feature (typically indicated by "s"). This is unless expressly stated that multiple aspects relate to multiple features.

[0015]

[0019] Furthermore, the terms "comprise, comprise, and comprising" are used interchangeably with "include, includes, and including." Furthermore, the term "wherein" is used interchangeably with the term "where." As used herein, "exemplary" refers to an example, an implementation, and / or an aspect, and should not be construed as limiting, or as indicating a preference or preferred embodiment. As used herein, ordinal terms (e.g., "first," "second," "third," and the like) used to modify elements, such as structures, components, operations, etc., do not in themselves indicate a priority or order of the element relative to another element, but rather merely distinguish the element from another element having the same name (except for the use of ordinal terms). As used herein, the term "set" refers to a grouping of one or more elements, and the term "plurality" refers to a plurality of elements.

[0016]

[0020] As used herein, "generating," "calculating," "using," "selecting," "accessing," and "determining" are interchangeable unless the context indicates otherwise. For example, "generating," "calculating," or "determining" a parameter (or signal) can refer to actively generating, calculating, or determining a parameter (or signal), or can refer to using, selecting, or accessing a parameter (or signal) that has already been generated, for example, by another component or device. As used herein, "connected" may include "communicatively coupled," "electrically coupled," or "physically coupled," or may also (or alternatively) include any combination thereof. Two devices (or components) can be directly or indirectly coupled (communicatively coupled, electrically coupled, or physically coupled) via one or more other devices, components, wires, buses, networks (wired networks, wireless networks, or combinations thereof), etc. Two devices (or components) that are electrically coupled can be included in the same device or different devices and can be connected via electronics, one or more connectors, or inductive coupling, as illustrative, non-limiting examples. In some implementations, two devices (or components) that are communicatively coupled, such as by electrical communication, can send and receive electrical signals (digital or analog signals) directly or indirectly via one or more wires, buses, networks, etc. As used herein, "directly coupled" is used to describe two devices that are coupled (e.g., communicatively coupled, electrically coupled, or physically coupled) without any intervening components.

[0017]

[0021] As used herein, the term "machine learning" should be understood to have any of its usual and accustomed meanings in the fields of computer science and data science, including, for example, processes or techniques by which one or more computers can learn to perform certain actions or functions without being explicitly programmed. As a typical example, machine learning can be used to enable one or more computers to analyze data, identify patterns in the data, and generate results based on the analysis. In certain types of machine learning, the results generated include data that are indicative of underlying structures or patterns in the data itself. Such techniques include, for example, so-called "clustering" techniques, which identify clusters (e.g., groupings of data elements in the data).

[0018]

[0022] In certain types of machine learning, the results generated include a data model (also called a "machine learning model" or simply a "model"). Typically, the model is generated using a first data set to facilitate analysis of a second data set. For example, a first portion of the large data set can be used to generate a model, which can be used to analyze the remaining portion of the large data set. As another example, a set of historical data can be used to generate a model, which can be used to analyze future data.

[0019]

[0023] Because a model can be used to evaluate a set of data that is different from the data used to generate the model, a model can be considered a type of software (e.g., instructions, parameters, or both) that is automatically generated by a computer(s) during a machine learning process. Thus, a model can be portable (e.g., generated on a first computer and then moved to a second computer for further training, use, or both). Furthermore, a model can be used in combination with one or more other models to perform a desired analysis. By way of illustration, a first data can be provided as input to a first model to generate first model output data. This data can be provided as input to a second model (alone, together with the first data, or together with other data) to generate second model output data indicative of the results of the desired analysis. Depending on the analysis and the data involved, different combinations of models can be used to generate such results. In some examples, multiple models can provide model outputs that are input to a single model. In some examples, a single model provides model outputs as input to multiple models.

[0020]

[0024] Examples of machine learning models include, but are not limited to, perceptrons, neural networks, support vector machines, regression models, decision trees, Bayesian models, Boltzmann machines, adaptive neuro-fuzzy inference systems, as well as combinations, ensembles, and variations of these and other types of models. Variations of neural networks include, but are not limited to, prototype networks, autoencoders, transformers, self-attention networks, convolutional neural networks, deep neural networks, deep belief networks, etc. Variations of decision trees include, but are not limited to, random forests, boosted decision trees, etc.

[0021]

[0025] Since machine learning models are generated by (one or more) computers based on input data, machine learning models can be discussed in at least two different time windows: a creation / training phase and an execution (runtime) phase. In the creation / training phase, a model is created, trained, adapted, validated, or otherwise configured by a computer based on input data (commonly referred to as "training data" in the creation / training phase). It should be noted that a trained model corresponds to software that is generated and / or improved during the creation / training phase to perform a particular operation, such as classification, prediction, encoding, or other data analysis or data synthesis operation. During the runtime phase (or "inference" phase), the model is used to analyze the input data and generate model output. The content of the model output depends on the type of model. For example, as a non-limiting example, a model can be trained to perform a classification task or a regression task. In some implementations, a model can be updated continuously, periodically, or from time to time. In that case, the training time and the execution time can be interleaved, or one version of the model can be used for inference while a copy is updated. The updated copy can then be deployed for inference.

[0022]

[0026] In some implementations, a previously generated model is trained (or retrained) using machine learning techniques. In this context, "training" refers to adapting a model or parameters of a model to a specific dataset. Unless otherwise indicated from a particular context, the term "training" as used herein includes "retraining" or improving a model on a specific dataset. For example, training may include so-called "transfer learning". In transfer learning, a base model is trained using a general or typical dataset, and then the base model may be improved (e.g., retrained or further trained) using a more specific dataset.

[0023]

[0027] A data set used during training is called a "training data set" or simply "training data." A data set may be labeled or unlabeled. "Labeled data" refers to data that has been assigned a categorical label indicating the group or category to which the data relates, and "unlabeled data" refers to data that has not been assigned a label. Typically, a "supervised machine learning process" uses labeled data to train a machine learning model, and an "unsupervised machine learning process" uses unlabeled data to train a machine learning model. However, it should be understood that the label associated with the data is itself just another data element that may be used in any suitable machine learning process. By way of example, while many clustering operations may operate using unlabeled data, such clustering operations may use labeled data by ignoring the labels assigned to the data or treating the labels the same as other data elements.

[0024]

[0028] Training a model based on a training dataset generally involves modifying parameters of the model with the goal of making the model's output have certain characteristics based on the data input to the model. To distinguish it from model generation operations, model training may be referred to herein as optimization or optimization training. In this context, "optimization" refers to improving a metric, and does not mean finding an ideal value (e.g., a global maximum or minimum) of the metric. Examples of optimization training include, but are not limited to, backpropagation trainers, derivative-free optimizers (DFOs), and extreme learning machines (ELMs). As an example of model training, during supervised training of a neural network, input data samples are associated with labels. When the input data samples are provided to a model, the model generates output data. The output data is compared with the labels associated with the input data samples to generate an error value. To reduce (e.g., optimize) the error value, parameters of the model are modified. As another example of model training, during unsupervised training of an autoencoder, data samples are provided as input to the autoencoder. An autoencoder attempts to reduce the dimensionality of data samples (which is a lossy operation) and reconstruct the data samples as output data. In this example, the output data is compared to the input data samples to generate a reconstruction loss, and the autoencoder is modified in an attempt to reduce (e.g., optimize) the reconstruction loss.

[0025]

[0029] 1 illustrates an example system 100 for terminal procedure prediction for flight planning, in accordance with some embodiments of the present disclosure. In some implementations, system 100 includes a computing device 102 configured to communicate with one or more devices 104. Computing device 102 may include one or more processors 106 coupled to a memory 108 that includes instructions that, when executed by processor(s) 106, cause processor(s) 106 to perform certain functions, such as those described in more detail below.

[0026]

[0030] The processor(s) 106 may include one or more components configured to perform one or more of these functions, including a terminal procedure predictor 120, a past flight selector 126, or some combination thereof. In some aspects, the terminal procedure predictor 120 may be configured to obtain a terminal procedure prediction 122 that includes data associated with a prediction of a terminal procedure, a prediction of the probability that the predicted terminal procedure will be effective for all of the particular flights, or both. In one particular aspect, the terminal procedure predictor 120 may include a machine learning model 124 configured to provide the terminal procedure prediction 122 based on at least the training data 118. In some implementations, the past flight selector 126 may be configured to identify a set of past flights 128 based on one or more comparisons of the input data 110 and data predicted for particular conditions of the past flights, as described in more detail below.

[0027]

[0031] The memory 108 may include data to enable the systems and methods for terminal procedure prediction for flight planning described herein. For example, the memory 108 may include forecast data 114, conditions 115, historical flight data 116, other data to enable terminal procedure prediction for flight planning, or any combination thereof.

[0028]

[0032] In some aspects, forecast data 114 may include runway forecast data 150, weather forecast data 152, one or more airport traffic models 154, etc. In the same or alternative aspects, conditions 115 may include data associated with current conditions for a particular flight. For example, conditions 115 may include navigation data, current weather data, runway in use data, notices to air missions ("NOTAM" or "NOTAMs"), other information associated with the context for a particular upcoming flight, or some combination thereof.

[0029]

[0033] In some implementations, historical flight data 116 may include data values ​​associated with a past flight. For example, historical flight data 116 may include flight plan 112, which includes data associated with the flight plan for the past flight, historical conditions 130, which includes data associated with conditions (e.g., weather, runway usage, etc.) for the past flight, etc.

[0030]

[0034] The computing device 102 is configured to receive input data 110 generated by device(s) 104. The device(s) 104 may be any suitable electronic device 104 configured to transmit the input data 110 to the computing device(s) 102. The computing device(s) 104 may include one or more processors 132 coupled to a memory 134 that includes instructions that, when executed by the processor(s) 132, cause the processor(s) 132 to perform certain functions, such as those described in more detail below.

[0031]

[0035] In some aspects, memory 134 may also include future flight data 136 associated with a particular future flight. For example, future flight data 136 may include data for a particular future flight associated with date and time information 138, departure airport 140, arrival airport 142, aircraft type 144, aircraft configuration 146, weight and balance data 148, etc. In some implementations, device(s) 104 may be configured to provide input data 110 based on one or more data values ​​of future flight data 136.

[0032]

[0036] During operation, the processor(s) 106 may be configured to obtain input data 110 corresponding to an upcoming flight of an aircraft. For example, the device(s) 104 may transmit input data 110 corresponding to a particular upcoming flight indicating that the flight will depart from Los Angeles International Airport today, February 7, in four hours, and arrive at Chicago O'Hare with an estimated arrival time of 10:30 p.m. Central Standard Time. In one example shown, the aircraft for the flight is a Boeing 737 in a particular configuration and with a particular weight and balance.

[0033]

[0037] The processor(s) 106 may also be configured to obtain forecast data 114 corresponding to the upcoming flight. Continuing with one exemplary embodiment described above, the terminal procedure predictor 120 may be configured to obtain data including a prediction of the particular runway at Chicago O'Hare that the aircraft will use upon arrival, data associated with a weather forecast for Chicago at 10:30 PM CST on February 7, and data associated with a model of how congested air traffic will be at O'Hare upon arrival.

[0034]

[0038] The processor(s) 106 may also be configured to process the input data 110 and the forecast data 114 to obtain a terminal procedure prediction 122 associated with the upcoming flight. Continuing with one exemplary embodiment described above, the past flight selector 126 may be configured to process the input data 110 describing an upcoming flight from Los Angeles to Chicago and data associated with a prediction of conditions in Chicago at the arrival time of the particular flight. In some implementations, the terminal procedure prediction 122 may be based at least in part on a flight plan 112 of a past flight having similar historical conditions 130 as the input data 110 and the forecast data 114. For example, the processor(s) 106 may be configured to analyze a flight plan of a past flight from Los Angeles to Chicago around the time of the upcoming flight in early February, in conditions similar to the predicted conditions in Chicago around the arrival time of the upcoming flight, to obtain a terminal procedure prediction for the upcoming flight. For example, if forecast data indicates that the weather in Chicago will be cold and rainy, at least one runway will be closed due to bad weather, and aircraft traffic is expected to be relatively heavy, and flight plans of past flights having similar conditions indicate that a particular terminal procedure will be used upon arrival, terminal procedure predictor 120 may be configured to obtain a prediction of that particular terminal procedure.

[0035]

[0039] In some aspects, the terminal procedure predictor 120 is configured to process the input data 110 and the prediction data 114 using a machine learning model 124 trained on the training data 118. In one particular configuration, the training data 118 is based on the historical flight data 116.

[0036]

[0040] In some aspects, the historical flight selector 126 may be configured to access the historical flight data 116 to identify a set of historical flights 128 based on one or more comparisons of the input data 110 and the forecast data 114 to historical conditions 130. In one particular aspect, the terminal procedure prediction 122 is obtained based on a statistical analysis of the set of historical flights 128. For example, the historical flight selector 126 may be configured to analyze a set of flights from Los Angeles to Chicago in early February over the past five years in which weather conditions were similar to those predicted for the upcoming flight.

[0037]

[0041] In some aspects, the processor(s) 106 may also be configured to obtain aviation notices (e.g., NOTAM(s)). The terminal procedure prediction 122 may then be based on the aviation notices. The NOTAMs may include, for example, potential hazards along the flight route or at locations that may affect the flight (e.g., construction near the airport, special events occurring near the airport and / or along the flight route, runway closures, construction at the airport, etc.).

[0038]

[0042] In some aspects, the terminal procedure prediction 122 may include multiple waypoints. The processor(s) 106 may be configured to identify the likelihood of approval of a request for a direct route that bypasses one or more of the waypoints, as described in more detail below with reference to FIG. 2. In one particular aspect, the processor(s) 106 may be configured to analyze flight position data (e.g., flight plan 112) of a past flight to detect whether one or more of the waypoints were bypassed during a past flight.

[0039]

[0043] In some aspects, the processor(s) 106 may be configured to identify a fuel safety margin based on the flight plan for the upcoming flight, including the terminal procedure prediction 122. Generally, the fuel safety margin may include the amount of fuel an aircraft should carry to ensure safe operation of the flight while still optimizing the aircraft's weight. Generating an accurate terminal procedure prediction, including the likelihood of approval of a direct route request that bypasses one or more of the waypoints, may potentially enable a flight planner to reduce (or increase) the amount of fuel required for a particular flight plan while still ensuring safe operation of the upcoming flight.

[0040]

[0044] In some implementations, the device(s) 104 may be associated with, integrated within, or otherwise included in a flight dispatcher system. In such implementations, the processor(s) 106 may also be configured to submit the terminal procedure predictions 122 to an air traffic control approval system. The air traffic control approval system may be configured to approve the terminal procedure predictions 122, reject the terminal procedure predictions 122, recommend new terminal procedures, or a combination thereof. Obtaining accurate, data-driven terminal procedure predictions 122 may improve the efficiency of the air traffic control approval system.

[0041]

[0045] In some or alternative implementations, device(s) 104 may be associated with, integrated into, or otherwise included in an air traffic control clearance system. In such implementations, processor(s) 106 may be configured to compare terminal procedure predictions 122 with flight plans for upcoming flights submitted to the air traffic control clearance system. As discussed above, obtaining accurate data-driven terminal procedure predictions 122 may improve the efficiency of the air traffic control clearance system.

[0042]

[0046] System 100 may also include components not shown in Figure 1. For example, computing device 102 may also include a receiver configured to receive input data 110 from device(s) 104. The receiver may be configured to receive the data, for example, via a radio frequency link. As a further example, system 100 may also include one or more input / output interfaces, one or more network interfaces, etc. Additionally, although Figure 1 illustrates memory 108 of system 100 as storing particular data, more, less, and / or different data may be present in memory 108 without departing from the scope of the present disclosure.

[0043]

[0047] 1 illustrates certain operations occurring within the computing device 102, these operations may be performed by other components of the system 100 without departing from the scope of the present disclosure. For example, one or more components external to the computing device 102 may be configured to host or otherwise incorporate some or all of the machine learning model 124, the training data 118, the terminal procedure predictor 120, the past flight selector 126, or some combination thereof. Such component(s) may be located remotely from the computing device 102 and accessed via a modem of the computing device 102. As one particular example, the past flight data 116, the prediction data 114, or some combination thereof may be stored in one or more databases external to the computing device 102.

[0044]

[0048] 1 depicts computing device 102 and device(s) 104 separately, other configurations are possible without departing from the scope of this disclosure. For example, computing device 102 and device(s) 104 may be integrated into an air traffic control authorization system. As a further example, one or more components of computing device 102 may be distributed across multiple computing devices (e.g., a cluster of servers).

[0045]

[0049] 2 illustrates an example diagram 200 of a comparison of a past planned flight path for an aircraft 202 moving near a number of waypoints 214, 216, 218 with respect to a first past actual flight path and a second past actual path, according to some embodiments of the disclosure. Generally, the comparison may be performed by one or more components of the processor(s) 106 of FIG. 1. The waypoints 214, 216, 218 may be geographic locations associated with one or more landmarks for a particular flight. For example, a given waypoint may be associated with a departure airport, an arrival airport, a particular altitude at a particular location, etc.

[0046]

[0050] In one example of diagram 200, aircraft 202 is shown traveling along a route from a first waypoint 214 to its current location. The planned flight path for aircraft 202 includes a first segment 204 between first waypoint 214 and second waypoint 216, a second segment 206 between second waypoint 216 and third waypoint 218, and a third segment 208 from the third waypoint 218 to the current location of aircraft 202. In some implementations, the planned flight path may generally correspond to a flight plan submitted by aircraft 202 prior to aircraft 202 making a particular flight. In one particular configuration, the flight plan is stored as an operational flight plan ("OFP") and stored in a database for analysis, as described in more detail below with reference to FIG. 3.

[0047]

[0051] Although the planned flight path is contained within the flight plan, the exact location of the aircraft on a given flight may deviate from the planned flight plan. In most civil flights, the aircraft reports its position periodically during the course of its flight. By analyzing a compilation of these position reports, a system (e.g., system 100 of FIG. 1) may be configured to compare the actual flight path to the planned flight path. For example, processor(s) 106 of FIG. 1 may be configured to generate polygons 220, 222, 224 around the geographic locations associated with each of waypoints 214, 216, 218, respectively. By generating polygons 220, 222, 224, the system may capture the actual location of aircraft 202 within a threshold distance of waypoints 214, 216, 218, respectively, or within an area defined around waypoints 214, 216, 218.

[0048]

[0052] For example, data from aircraft 202 may indicate that in a first past flight, aircraft 202 traveled along first segment 210 from a first polygon 220 around first waypoint 214, through a second polygon 222 around second waypoint 216, to a third polygon 224 around third waypoint 218. From there, aircraft 202 traveled along segment 212 from the third polygon 224 around third waypoint 218 to its current location. By analyzing the actual past flight path of aircraft 202 with respect to polygons 220, 222, 224, the system can identify the actual flight path using the particular waypoint.

[0049]

[0053] As another example, data from the aircraft 202 indicates that in a second past flight, the aircraft 202 traveled from a first waypoint 214 along a first segment 204 to a second waypoint 216. At the second waypoint 216, the aircraft 202 deviated from the planned flight path via a direct flight 226 from the second waypoint 216 to its current location, bypassing a third waypoint 218. A direct flight may include a deviation from the planned flight path approved by a traffic control approval system. A direct flight may be authorized for a variety of reasons, including fuel consumption, air traffic control, passenger safety, etc.

[0050]

[0054] As described above with reference to FIG. 1, the terminal procedure prediction 122 may include multiple waypoints (e.g., waypoints 214, 216, 218). The processor(s) 106 may be configured to identify the likelihood of approval of a request for a direct route that bypasses one or more of the waypoints. In one particular aspect, the processor(s) 106 is configured to analyze flight position data of a past flight to detect whether one or more of the waypoints were bypassed during the past flight. As shown in the exemplary diagram 200, the processor(s) 106 of FIG. 1 may be configured to analyze flight position data of a first and second past flight of the aircraft 202 to detect that the aircraft 202 bypassed the third waypoint 218 during the second past flight. Based on analysis of the flight position data of the past flights (and, in some configurations, further data, such as whether a direct route was requested, flight position data of past flights of other aircraft along a flight path that included the same waypoints), the processor(s) 106 can identify the likelihood of approval of a direct route for a particular upcoming flight.

[0051]

[0055] 3 illustrates an example architecture 300 for terminal procedure prediction for flight planning according to some embodiments of the present disclosure. The example architecture 300 includes an input device 302 communicatively coupled to a processing device 304, an output device 306, one or more historical databases 308, one or more data sources for contextual information 318, and one or more predictors 328.

[0052]

[0056] Generally, the exemplary architecture 300 corresponds to the structure and functionality of the system 100 of Figure 1. For example, the input device 302 generally corresponds to the device(s) 104, the processing device 304 generally corresponds to the processor(s) 106, the historical database(s) generally corresponds to the historical flight data 116, the contextual information 318 generally corresponds to the conditions 115, the output from the predictor 328 generally corresponds to the forecast data 114, and the output device 306 generally corresponds to the terminal procedure predictor 120.

[0053]

[0057] As described above with reference to FIG. 1, a user, a device, or some combination thereof may input a plurality of input data corresponding to conditions associated with the upcoming flight, which in some aspects may include date and time information 138, departure airport 140, arrival airport 142, aircraft type 144, aircraft configuration 146, etc. With reference to FIG. 3, the data corresponding to conditions associated with the upcoming flight may be input at an input device 302. In one particular aspect, the input device 302 may include any suitable electronic device(s) configured to store the input data, including as a personal computer, laptop computer, smartphone, etc., various input / output devices such as a keyboard, mouse, touch screen, etc., data transfer from another electronic device, other suitable means for storing the input data, or some combination thereof.

[0054]

[0058] Once entered, input device 302 may communicate input data 110 of FIG. 1 to processing device 304. Processing device 304 may be any suitable electronic device configured to process input data 110 and forecast data (e.g., forecast data 114 of FIG. 1) to obtain a terminal procedure prediction (e.g., terminal procedure prediction 122 of FIG. 1) associated with the upcoming flight. For example, processing device 304 may be included within, include, share functionality with, or be otherwise associated with computing device(s) 102 of FIG. 1.

[0055]

[0059] The processing device 304 may be configured to obtain information from one or more sources of information, including historical flight data 116 in FIG. 1 from historical database(s) 308, conditions 115 from contextual information 318, forecast data 114 from predictor(s) 328, etc.

[0056]

[0060] In some implementations, each information source may include one or more sub-sources of information. For example, historical database(s) 308 may include historical weather database 310, position report database 312, historical NOTAM database 314, operational flight plan ("OFP") database 316, etc. Historical database(s) 308 generally correspond to historical flight data 116 of FIG. 1.

[0057]

[0061] The contextual information 318 may include one or more of a navigation database 320, a current weather database 322, a database of runways in use 324, a database of current NOTAMs 326, etc. The predictor(s) 328 may include an air traffic predictor 330 configured to provide an airport traffic model 154, a weather predictor 332 configured to provide a weather forecast 152, a runway usage predictor 334 configured to provide a runway forecast 150, etc.

[0058]

[0062] In some implementations, processing device 304 may be configured to match the actual and / or predicted data with historical condition data in block 336. For example, processing device 304 may compare input data 110, conditions 115, and historical flight data 116 with predicted data 114 from predictor(s) 328. Processing device 304 may be configured to identify, for example, a set of historical flights 128 of FIG. 1 that most closely resemble the particularities of the upcoming flight.

[0059]

[0063] The processing device 304 may also be configured to retrieve one or more most planned terminal procedures from the set of past flights 128, at block 338. In a particular aspect, the most planned terminal procedures may be retrieved from the OFP database 316. Once identified, the processing device 304 may also be configured to extract coordinates of a number of waypoints ("WPTs") associated with the(one or more) most planned terminal procedures, at block 340. In a particular aspect, the processing device 304 may retrieve the waypoint coordinates from the navigation database 320.

[0060]

[0064] The processing device 304 may also be configured to construct one or more polygons associated with each waypoint, as described in more detail with reference to FIG. 2, at block 342. The processing device 304 may also be configured to fit the aircraft position, as reported from the aircraft position report, to the spatial extent of the waypoint polygon, at block 344. The processing device 304 may also be configured to determine whether the number of position reports of a particular OFP satisfies a route threshold for the waypoint polygon, at block 346. For example, the route threshold may be a predetermined percentage (e.g., 50%) of waypoints whose aircraft reported position is within the associated waypoint polygon.

[0061]

[0065] If the OFP(s) meet the route threshold, the output device 306 may be configured to output a predicted terminal procedure (e.g., terminal procedure prediction 122) in block 348, as described above with reference to FIG. 1, including a likelihood that the predicted terminal procedure will remain valid during future flights. Using one embodiment described above, if past position reports indicate that the aircraft has passed within a majority of a polygon of waypoints, the output device 306 may be configured to output a likelihood that a given terminal procedure will remain valid. In one particular embodiment, this likelihood may be based on an analysis of multiple past flights that met the same route threshold criteria for a particular set of waypoints. In a set of 50 past flights that included predicted terminal procedures, if 30 of these past flights met the route threshold, the output device 306 may include a 60% likelihood that the terminal procedure will remain valid during future flights.

[0062]

[0066] If the OFP(s) does not meet the route threshold, the output device 306 may be configured to output a probability and location of a direct-through in block 350. As described with reference to FIG. 2, a direct-through may indicate that a particular past flight has bypassed one or more waypoints associated with the original OFP. By analyzing the input data 110, the past flight data 116, the conditions 115, and the forecast data 114, the processing device 304 may be configured to provide a probability that a particular flight will follow a particular terminal procedure. This probability includes the probability that a direct-through will bypass one or more portions of the original OFP.

[0063]

[0067] In some implementations, the processing device 304 may also be configured to update the historical database(s) 308 with data associated with the upcoming flight. The processing device 304 may, for example, collect actual weather data, location information, actual runway in use data, actual airport traffic data, etc. associated with the planned flight while the flight is in progress. The processing device 304 may collect this data from one or more data sources while the aircraft is in flight, after the flight, or some combination thereof. The processing device 304 may then be configured to update the historical database(s) 308 (and / or appropriate sub-sources of data) with the obtained actual flight data.

[0064]

[0068] As post-flight data is updated with data from actual flights, the database of historical data (e.g., historical database(s) 308) will have access to a more accurate and more robust data set. By improving the available historical data set, the example architecture 300 (and system 100 of FIG. 1 ) may improve the performance of obtaining terminal procedure predictions 122 (e.g., by processing device 304, computing device(s) 102 of FIG. 1 , etc.). For example, when training data 118 is based on a larger and more accurate set of historical flight data (e.g., historical flight data 116 of FIG. 1 ), the trained machine learning model 124 may more accurately predict terminal procedures. Continuously updating the historical flight data enables the systems and methods disclosed herein to continuously refine terminal procedure predictions for flight planning.

[0065]

[0069] 4 is a flowchart of an example method 400 for terminal procedure prediction for flight planning, in accordance with some embodiments of the present disclosure. Method 400 may be initiated, performed, or controlled by one or more processors executing instructions, such as by processor(s) 106 of FIG. 1 executing instructions from memory 108.

[0066]

[0070] In some implementations, method 400 includes, at 402, obtaining, at a processor, input data corresponding to a future flight of the aircraft. For example, processor(s) 106 of Figure 1 may obtain input data 110 of Figure 2 corresponding to a future flight of aircraft 202.

[0067]

[0071] In one embodiment of Figure 4, method 400 may also include, at a processor, obtaining forecast data corresponding to the upcoming flight, at 404. For example, processor(s) 106 of Figure 1 may obtain forecast data 114 corresponding to the upcoming flight.

[0068]

[0072] In one embodiment of FIG. 4 , method 400 may also include, at 406, processing, with the processor, the input data and the forecast data to obtain a terminal procedure prediction associated with the upcoming flight. The terminal procedure prediction is based at least in part on flight paths of past flights having similar conditions to the input data and the forecast data. For example, processor(s) 106 may process input data 110 and forecast data 114 to obtain a terminal procedure prediction 122 associated with the upcoming flight. The terminal procedure prediction 122 is based at least in part on flight paths 112 of past flights having similar conditions to the input data 110 and the forecast data 114.

[0069]

[0073] Although method 400 is illustrated as including a particular number of steps, more, fewer, and / or different steps may be included in method 400 without departing from the scope of the present disclosure. For example, method 400 may optionally include additional steps, as described in more detail below.

[0070]

[0074] In one embodiment of FIG. 4, method 400 may, at 408, optionally include obtaining airline notice information. The terminal procedure prediction is further based on the airline notice information. For example, processor(s) 106 of FIG. 1 may be configured to obtain airline notice information from database of historical NOTAMs 314, database of current NOTAMs 326 of FIG. 3, or some combination thereof. Processor(s) 106 may be configured to further base terminal procedure prediction 122 on the airline notice information.

[0071]

[0075] In one example of Figure 4, method 400 may optionally include, at 410, determining a likelihood of approval of a request for a direct route that bypasses one or more waypoints included within the terminal procedure prediction. For example, processor(s) 106 of Figure 1 may be configured to determine a likelihood of approval of a request for a direct route that bypasses one or more waypoints included within terminal procedure prediction 122, as described above with reference to Figures 2-3.

[0072]

[0076] In one embodiment of Figure 4, method 400 may also optionally include analyzing flight position data of the past flights to detect whether one or more of the waypoints were circumvented during the past flights, at 412. For example, as described above with reference to Figures 2-3, the processing device of Figure 3 may be configured to analyze flight position data from database of position reports 312 to detect whether one or more of the waypoints were circumvented during the past flights.

[0073]

[0077] 4 , the method 400 may optionally include, at 414, determining a fuel safety margin based on a flight plan for the upcoming flight that includes the terminal procedure prediction. For example, the processor(s) 106 may be configured to determine a fuel safety margin based on a flight plan for the upcoming flight that includes the terminal procedure prediction 122.

[0074]

[0078] As noted above, more, fewer, and / or different steps may be included in method 400 without departing from the scope of the present disclosure. For example, method 400 may vary depending on the number and type of input data received. In certain configurations, system 100 of FIG. 1 may be configured to obtain a preliminary terminal procedure prediction 122 when incomplete input data 110 is obtained and then update terminal procedure prediction 122 as more input data 110 is received.

[0075]

[0079] 5 is a block diagram of a computing environment 500 including a computing device 510 configured to support aspects of computer-implemented methods and computer-executable program instructions (or codes) according to some embodiments of the present disclosure. For example, the computing device 510, or a portion thereof, is configured to execute instructions to initiate, execute, or control one or more of the operations described in more detail above with reference to FIGS. 1-4. In one particular embodiment, the computing device 510 may include, correspond to, or be included within the computing device 102, device(s) 104, input device 302, processing device 304, output device 306, historical database(s) 308, contextual information 318, predictor(s) 328, one or more servers, one or more virtual devices, or combinations thereof of FIG. 1.

[0076]

[0080] The computing device 510 includes one or more processors 520. In one particular aspect, the processor(s) 520 correspond to the processor(s) 106 of FIG. 1. The processor(s) 520 are configured to communicate with a system memory 530, one or more storage devices 550, one or more input / output interfaces 540, one or more communication interfaces 560, or any combination thereof. The system memory 530 includes volatile memory devices (e.g., random access memory (RAM) devices), non-volatile memory devices (e.g., read-only memory (ROM) devices, programmable read-only memory, and flash memory), or both. The system memory 530 stores an operating system 532, which may include a basic input / output system for booting the computing device 510 as well as a full operating system for enabling the computing device 510 to interact with a user, other programs, and other devices. The system memory 530 stores system (program) data 538, such as the forecast data 114, conditions 115, historical flight data 116 of FIG. 1, or a combination thereof.

[0077]

[0081] The system memory 530 includes one or more applications 534 (e.g., collections of instructions) executable by the processor(s) 520. As an example, the one or more applications 534 include instructions 536 executable by the processor(s) 520 to initiate, control, or perform one or more of the operations described with reference to FIGS. 1-4. By way of example, the one or more applications 534 include instructions 536 executable by the processor(s) 520 to initiate, control, or perform one or more of the operations described with respect to processing the input data 110 and the prediction data 114 to obtain a terminal procedure prediction 122 associated with a future flight. The terminal procedure prediction 122 is based at least in part on a flight plan 112 of a past flight having similar conditions as the input data 110 and the prediction data 114.

[0078]

[0082] In one particular implementation, system memory 530 includes a non-transitory computer-readable medium (e.g., a computer-readable storage device) having instructions 536 stored thereon that, when executed by processor(s) 520, cause processor(s) 520 to initiate, execute, or control operations to improve an automated environment for aeronautical information services. The operations include obtaining, at the processor, input data corresponding to a future flight of the aircraft. The operations also include obtaining, at the processor, forecast data corresponding to the future flight. The operations also include processing, at the processor, the input data and the forecast data to obtain a terminal procedure forecast associated with the future flight. The terminal procedure forecast is based at least in part on flight plans of past flights having similar conditions to the input data and the forecast data.

[0079]

[0083] The one or more storage devices 550 include non-volatile storage devices, such as magnetic disks, optical disks, or flash memory devices. In one particular embodiment, the storage devices 550 include both removable and non-removable memory devices. The storage devices 550 are configured to store an operating system, images of the operating system, applications (e.g., one or more applications 534), and program data (e.g., program data 538). In one particular aspect, the system memory 530, the storage devices 550, or both, include tangible computer-readable media. In one particular aspect, one or more of the storage devices 550 are external to the computing device 510.

[0080]

[0084] The one or more input / output interfaces 540 enable the computing device 510 to communicate with one or more input / output devices 570 to facilitate interaction with a user. For example, the one or more input / output interfaces 540 may include a display interface, an input interface, or both. For example, the input / output interface 540 may be adapted to receive input from a user, from another computing device, or a combination thereof. In some embodiments, the input / output interface 540 complies with one or more standard interface protocols, including a serial interface (e.g., a universal serial bus (USB) interface or (IEEE (Institute of Electrical and Electronics Engineers) interface standard), a parallel interface, a display adapter, an audio adapter, or a custom interface. ("IEEE" is a registered trademark of the Institute of Electrical and Electronics Engineers, Inc. of Piscataway, NJ). In some embodiments, the input / output device(s) 570 include one or more user interface devices and displays, including any combination of buttons, keyboards, pointing devices, displays, speakers, microphones, touch screens, and other devices.

[0081]

[0085] The processor(s) 520 are configured to communicate with a device or controller 580 via one or more communication interfaces 560. For example, the one or more communication interfaces 560 may include a network interface. The device or controller 580 may include, for example, the device(s) 104 of FIG. 1.

[0082]

[0086] In some implementations, a non-transitory computer-readable medium (e.g., a computer-readable storage device) stores instructions that, when executed by one or more processors, cause the one or more processors to initiate, execute, or control operations to perform some or all of the functions described above. For example, the instructions may be executable to perform one or more of the operations or methods of Figures 1, 3, and 4. In some implementations, some or all of one or more of the operations or methods of Figures 1, 3, and 4 may be performed by one or more processors (e.g., one or more central processing units (CPUs), one or more graphics processing units (GPUs), one or more digital signal processors (DSPs)) executing instructions through dedicated hardware circuitry, or any combination thereof.

[0083]

[0087] In conjunction with several described embodiments, the apparatus includes a means for obtaining, at a processor, input data corresponding to a future flight of the aircraft. For example, the means for obtaining input data may include computing device 102 of FIG. 1, processor(s) 106, device(s) 104, processor(s) 132, historical database(s) 308 of FIG. 3, contextual information 318, input device 302, processing device 304, one or more other circuits or components configured to obtain, at a processor, input data corresponding to a future flight of the aircraft, or any combination thereof.

[0084]

[0088] The device also includes means for obtaining, at the processor, predictive data corresponding to the upcoming flight. For example, the means for obtaining predictive data may include computing device 102 of FIG. 1, processor(s) 106, device(s) 104, processor(s) 132, predictor(s) 328 of FIG. 3, input device 302, processing device 304, one or more other circuits or components configured to obtain, at the processor, predictive data corresponding to the upcoming flight, or any combination thereof.

[0085]

[0089] The device also includes means for processing the input data and the predicted data in the processor to obtain a terminal procedure prediction associated with the upcoming flight, the terminal procedure prediction being based at least in part on a flight plan of a past flight having similar conditions to the input data and the predicted data. The means for processing the input data and the predicted data includes the computing device 102 of FIG. 1, the processor(s) 106, the device 104, the processor(s) 132, the processing device 304 of FIG. 3, one or more circuits or components configured to process the input data and the predicted data in the processor to obtain a terminal procedure prediction associated with the upcoming flight, the terminal procedure prediction being based at least in part on a flight plan of a past flight having similar conditions to the input data and the predicted data, or any combination thereof.

[0086]

[0090] The illustrations of the several examples described herein are intended to provide a general understanding of the structure of various embodiments. These illustrations are not intended to exhaustively describe all elements and features of devices and systems that utilize the structures or methods described herein. Many other embodiments may become apparent to those skilled in the art upon review of this disclosure. Other embodiments may be utilized and derived from this disclosure, such that structural and logical substitutions and changes may be made without departing from the scope of the disclosure. For example, the method operations may be performed in a different order than shown in the figures, or one or more method operations may be omitted. Thus, the present disclosure and the figures should be considered illustrative rather than restrictive.

[0087]

[0091] Moreover, while specific examples have been shown and described herein, any subsequent configurations designed to achieve the same or similar results may be substituted for the specific embodiment shown. The present disclosure is intended to include any and all subsequent adaptations or variations of the various embodiments. Combinations of the above-described embodiments, as well as other embodiments not specifically described herein, will be apparent to those of skill in the art upon review of this specification.

[0088]

[0092] The Abstract of the Disclosure is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. In addition, in the above detailed description, various features may be grouped together or described within a single embodiment for the purpose of brevity of the disclosure. The above examples are illustrative of the disclosure, but are not limiting. Also, many modifications and variations are possible in accordance with the principles of the disclosure. As reflected in the following claims, the claimed subject matter may not be directed to all of the features of any of the disclosed embodiments. Thus, the scope of the disclosure is defined by the following claims and their equivalents.

[0089]

[0093] Furthermore, the present disclosure includes embodiments according to the following examples.

[0090]

[0094] According to Example 1, a device includes one or more processors, the one or more processors configured to perform the steps of obtaining input data corresponding to a future flight of an aircraft, obtaining forecast data corresponding to the future flight, and processing the input data and the forecast data to obtain a terminal procedure prediction associated with the future flight, the terminal procedure prediction being based at least in part on flight plans of past flights having similar conditions to the input data and the forecast data.

[0091]

[0095] Example 2 includes the device of example 1, in which the one or more processors are configured to process the input data and the prediction data using a trained machine learning model.

[0092]

[0096] Example 3 includes the device of example 1 or 2, where the trained machine learning model is trained based on the past flights.

[0093]

[0097] Example 4 includes the device of any one of examples 1-3, in which the one or more processors are configured to access the database of past flights to identify a set of the past flights based on one or more comparisons of the input data and the forecast data to conditions of the past flights.

[0094]

[0098] Example 5 includes the device of example 4, where the terminal procedure prediction is obtained based on a statistical analysis of the set of past flights.

[0095]

[0099] Example 6 includes the device of any one of examples 1 to 5, in which the input data includes at least one of date and time information, a departure airport, a arrival airport, an aircraft type, an aircraft configuration, or aircraft weight and balance data.

[0096]

[0100] Example 7 includes the device of any one of examples 1 to 6, in which the forecast data includes at least one of a runway forecast, a weather forecast, or an airport traffic model.

[0097]

[0101] Example 8 includes the device of any one of examples 1 to 7, in which the one or more processors are further configured to obtain airline advisory information, and the terminal procedure prediction is further based on the airline advisory information.

[0098]

[0102] Example 9 includes the device of any one of examples 1-8, in which the terminal maneuver prediction includes a plurality of waypoints, and the one or more processors are further configured to identify a likelihood of approval of a request for a direct route that bypasses one or more of the waypoints.

[0099]

[0103] Example 10 includes the device of example 9, in which the one or more processors are configured to analyze flight position data of the past flights and detect whether one or more of the waypoints were bypassed during the past flights.

[0100]

[0104] Example 11 includes the device of any one of examples 1-10, in which the one or more processors are configured to determine a fuel safety margin based on a flight plan for the upcoming flight that includes the terminal procedure prediction.

[0101]

[0105] Example 12 includes the device of any one of examples 1-11, in which the device is included in a traffic control system and the one or more processors are configured to submit the terminal procedure predictions to an air traffic control approval system.

[0102]

[0106] Example 13 includes the device of any one of examples 1-12, in which the device is included in an air traffic control clearance system, and the one or more processors are configured to compare the terminal procedure prediction with a flight plan for the upcoming flight submitted to the air traffic control clearance system.

[0103]

[0107] According to Example 14, a method includes obtaining, in a processor, input data corresponding to a future flight of an aircraft; obtaining, in the processor, forecast data corresponding to the future flight; and processing, in the processor, the input data and the forecast data to obtain a terminal procedure prediction associated with the future flight, the terminal procedure prediction being based at least in part on flight plans of past flights having conditions similar to the input data and the forecast data.

[0104]

[0108] Example 15 includes the method of example 14, in which a trained machine learning model is used to process the input data and the prediction data.

[0105]

[0109] Example 16 includes the method of example 14 or 15, in which processing the input data and the forecast data includes accessing the database of past flights to identify a set of the past flights based on one or more comparisons of the input data and the forecast data to conditions of the past flights.

[0106]

[0110] Example 17 includes the method of any one of examples 14 to 16, in which the input data includes at least one of date and time information, a departure airport, a arrival airport, an aircraft type, an aircraft configuration, or aircraft weight and balance data.

[0107]

[0111] Example 18 includes the method of any one of examples 14-17, in which the forecast data includes at least one of a runway forecast, a weather forecast, or an airport traffic model.

[0108]

[0112] Example 19 includes the method of any one of examples 14-18, in which the method further includes determining a likelihood of approval of a request for a direct route that bypasses one or more waypoints included within the terminal procedure forecast.

[0109]

[0113] According to Example 20, a non-transitory computer-readable medium includes instructions that, when executed by one or more processors, cause the one or more processors to obtain input data corresponding to a future flight of an aircraft, obtain forecast data corresponding to the future flight, and process the input data and the forecast data to obtain a terminal procedure prediction associated with the future flight, the terminal procedure prediction based at least in part on flight plans of past flights having conditions similar to the input data and the forecast data.

[0110]

[0114] Example 21 includes the non-transitory computer-readable medium of example 20, in which the instructions, when executed by the one or more processors, cause the one or more processors to process the input data and the prediction data using a trained machine learning model.

[0111]

[0115] Example 22 includes the non-transitory computer readable medium of example 20 or 21, in which the trained machine learning model is trained based on the past flights.

[0112]

[0116] Example 23 includes the non-transitory computer-readable medium of any one of Examples 20-22, in which the instructions, when executed by the one or more processors, cause the one or more processors to access the database of past flights to identify a set of the past flights based on one or more comparisons of the input data and the forecast data to conditions of the past flights.

[0113]

[0117] Example 24 includes the non-transitory computer readable medium of example 23, in which the terminal procedure prediction is obtained based on a statistical analysis of the set of past flights.

[0114]

[0118] Example 25 includes the non-transitory computer readable medium of any one of examples 20 to 24. The input data includes at least one of date and time information, a departure airport, a arrival airport, an aircraft type, an aircraft configuration, or aircraft weight and balance data.

[0115]

[0119] Example 26 includes the non-transitory computer readable medium of any one of examples 20 to 25, in which the forecast data includes at least one of a runway forecast, a weather forecast, or an airport traffic model.

[0116]

[0120] Example 27 includes the non-transitory computer-readable medium of any one of Examples 20 to 26, in which the instructions, when executed by the one or more processors, are further configured to cause the one or more processors to obtain flight advisory information, and the terminal procedure prediction is further based on the flight advisory information.

[0117]

[0121] Example 28 includes the non-transitory computer-readable medium of any one of examples 20 to 27, in which the terminal maneuver prediction includes a plurality of waypoints, and the instructions, when executed by the one or more processors, cause the one or more processors to identify likelihood of approval of a request for a direct route that bypasses one or more of the waypoints.

[0118]

[0122] Example 29 includes the non-transitory computer-readable medium of example 28, in which the instructions, when executed by the one or more processors, cause the one or more processors to analyze flight position data of the past flights and detect whether one or more of the waypoints were bypassed during the past flights.

[0119]

[0123] Example 30 includes the non-transitory computer-readable medium of any one of Examples 20 to 29, in which the instructions, when executed by the one or more processors, cause the one or more processors to determine a fuel safety margin based on a flight plan for the upcoming flight that includes the terminal procedure prediction.

[0120]

[0124] Example 31 includes the non-transitory computer-readable medium of any one of examples 20 to 30, in which the non-transitory computer-readable medium is included within a traffic control system, and the instructions, when executed by the one or more processors, cause the one or more processors to submit the terminal procedure prediction to an air traffic control approval system.

[0121]

[0125] Example 32 includes the non-transitory computer readable medium of any one of examples 20 to 31. The non-transitory computer readable medium is included within an air traffic control approval system, and the instructions, when executed by one or more processors, cause the one or more processors to compare the terminal procedure predictions with a flight plan for the upcoming flight that has been submitted to the air traffic control approval system.

[0122]

[0126] According to Example 33, the device includes means for obtaining, in a processor, input data corresponding to a future flight of the aircraft; obtaining, in the processor, forecast data corresponding to the future flight; and processing, in the processor, the input data and the forecast data to obtain a terminal procedure prediction associated with the future flight, the terminal procedure prediction being based at least in part on flight plans of past flights having conditions similar to the input data and the forecast data.

[0123]

[0127] Example 34 includes the device of example 33, in which a trained machine learning model is used to process the input data and the prediction data.

[0124]

[0128] Example 35 includes the device of example 33 or example 34, in which the means for processing the input data and the forecast data includes means for accessing the database of past flights to identify a set of the past flights based on one or more comparisons of the input data and the forecast data to conditions of the past flights.

[0125]

[0129] Example 36 includes the device of any one of examples 33 to 35, in which the input data includes at least one of date and time information, a departure airport, a arrival airport, an aircraft type, an aircraft configuration, or aircraft weight and balance data.

[0126]

[0130] Example 37 includes the device of any one of examples 33 to 36, in which the forecast data includes at least one of a runway forecast, a weather forecast, or an airport traffic model.

[0127]

[0131] Example 38 includes the method of any one of examples 33 to 37, in which the device further includes means for identifying likelihood of approval of a request for a direct route that bypasses one or more waypoints included within the terminal maneuver prediction.

Claims

1. A device (102) comprising one or more processors (106), the one or more processors (106) comprising: Obtaining input data (110) corresponding to an upcoming flight of the aircraft; obtaining predictive data (114) corresponding to said upcoming flight; and and processing the input data and the prediction data to obtain a terminal procedure prediction (122) associated with the upcoming flight, the terminal procedure prediction being based at least in part on a flight plan (112) of a past flight having conditions (115) similar to the input data and the prediction data.

2. The device of claim 1 , wherein the one or more processors are configured to process the input data and the predicted data using a trained machine learning model (124).

3. The device of claim 2 , wherein the trained machine learning model is trained (118) based on the past flights (116).

4. 2. The device of claim 1, wherein the one or more processors are configured to access the database of past flights (116) to identify a set of the past flights (128) based on one or more comparisons of the input data and the forecast data to conditions of the past flights (130).

5. The device of claim 4 , wherein the terminal procedure prediction is obtained based on a statistical analysis of the set of past flights.

6. 2. The device of claim 1, wherein the input data includes at least one of date and time information (138), a departure airport (140), a arrival airport (142), an aircraft type (144), an aircraft configuration (146), or aircraft weight and balance data (148).

7. The device of claim 1 , wherein the forecast data includes at least one of a runway forecast (150), a weather forecast (152), or an airport traffic model (154).

8. The device of claim 1 , wherein the one or more processors are further configured to obtain airline advisory information (314, 326), and the terminal procedure prediction is further based on the airline advisory information.

9. 2. The device of claim 1, wherein the terminal procedure prediction includes a plurality of waypoints (214, 216, 218), and the one or more processors are further configured to identify a likelihood of approval of a request for a direct route (226) that bypasses one or more of the waypoints.

10. 10. The device of claim 9, wherein the one or more processors are configured to analyze flight position data (312) of the past flights and detect whether one or more of the waypoints were circumvented during the past flights.

11. 2. The device of claim 1, wherein the one or more processors are configured to determine a fuel safety margin based on a flight plan for the upcoming flight that includes the terminal procedure prediction.

12. The device of claim 1 , wherein the device is included within a flight operations control system, and the one or more processors are configured to submit the terminal procedure predictions to an air traffic control approval system.

13. 2. The device of claim 1, wherein the device is included within an air traffic control approval system, and the one or more processors are configured to compare the terminal procedure prediction with a flight plan for the upcoming flight submitted to the air traffic control approval system.

14. Obtaining (402) input data (110) corresponding to a future flight of the aircraft, in a processor (106, 132); obtaining (404) in the processor predictive data (114) corresponding to the upcoming flight; and The method (400) includes processing (406) the input data and the prediction data in the processor to obtain a terminal procedure prediction (122) associated with the future flight, the terminal procedure prediction being based at least in part on flight plans (112) of past flights having conditions (115) similar to the input data and the prediction data.

15. The method of claim 14 , further comprising: processing the input data and the predicted data using a trained machine learning model (118).

16. 15. The method of claim 14, wherein processing the input data and the forecast data includes accessing the database of past flights (116) to identify a set of the past flights (128) based on one or more comparisons of the input data and the forecast data to conditions of the past flights (130).

17. 15. The method of claim 14, wherein the input data includes at least one of date and time information (138), a departure airport (140), a arrival airport (142), an aircraft type (144), an aircraft configuration (146), or aircraft weight and balance data (148).

18. The method of claim 14 , wherein the forecast data includes at least one of a runway forecast (150), a weather forecast (152), or an airport traffic model (154).

19. 15. The method of claim 14, further comprising identifying a likelihood of approval of a request for a direct route (226) that bypasses one or more waypoints (214, 216, 218) included within the terminal procedure forecast.

20. A non-transitory computer readable medium (530, 108, 134) comprising instructions (536) that, when executed by one or more processors (106, 132), cause the one or more processors to: Obtaining input data (110) corresponding to an upcoming flight of the aircraft; obtaining predictive data (114) corresponding to said upcoming flight; and and processing the input data and the prediction data to obtain a terminal procedure prediction (122) associated with the future flight, the terminal procedure prediction being based at least in part on a flight plan (112) of a past flight having conditions (115) similar to the input data and the prediction data.

Images