System and method for determining flight path of aircraft

Abstract

Systems and methods for determining a flight path of an aircraft are disclosed, the system including an aircraft including a user interface having a display. The control unit is in communication with the user interface. The control unit is configured to determine a flight path for flight of the aircraft based on the tail number specific data of the aircraft and the weather condition.

Description

TECHNICAL FIELD

[0001] Examples of the present disclosure relate generally to systems and methods for determining a flight path for an aircraft, and more particularly, to determining an optimal flight path for an aircraft. BACKGROUND

[0002] Aircraft are used to transport passengers and cargo between various locations. Many aircraft leave and arrive at typical airports each day.

[0003] The lateral flight path (i.e., the lateral and longitudinal path between locations) of an aircraft is determined by flight plan design personnel, who typically look at possible route options and construct a route from a departure airport to an arrival airport. The flight path is typically based on current restrictions for the aircraft (such as closed airspace) and general performance data. The flight path can be the most fuel efficient or cost efficient route available, and is based on assumptions about weather, weight, performance, and assumed fuel range. Each flight path is submitted (such as to air traffic control), and is typically not adjusted over time.

[0004] During a flight, the pilot typically faces multiple decisions in terms of lateral changes. For example, air traffic control can provide the pilot with a guide, reroute, or other change to the original flight path. Thus, the pilot needs to evaluate whether such a change is a better option, and determine whether the adjusted route provides any advantages (e.g., cost savings in terms of fuel burn). In other words, pre-flight and in-flight dynamics can suggest changes and different options.

[0005] An air traffic controller can not know whether a direct route between two different locations provides a flight benefit change. Specifically, the air traffic controller can not consider weather, the mission profile of the flight, and other such factors. Instead, the air traffic controller assumes that a shorter route is better. Furthermore, the operations control center often does not have the time, nor the means to re-run the flight plan to find a better option for the given change dynamics. Finally, the pilot can not have enough time to evaluate the route change, search for a better lateral option, or evaluate the impact of the change on the flight plan. Instead, the pilot can rely on the flight management computer, which can provide very basic predictions based on general performance data. SUMMARY

[0006] There is a need for systems and methods for efficiently and effectively evaluating flight paths, including changes to existing flight paths. Furthermore, there is a need for systems and methods for accurately determining an optimal flight path based on specific flight data for a specific aircraft.

[0007] In view of these needs, certain examples of the present disclosure provide a system including an aircraft having a user interface including a display. A control unit is in communication with the user interface. The control unit is configured to determine a flight path for a flight of the aircraft based on tail number specific data of the aircraft and weather conditions.

[0008] In at least one example, the control unit is configured to determine the flight path prior to the flight of the aircraft. In at least one other example, the control unit is configured to determine the flight path during the flight of the aircraft.

[0009] In at least one example, the control unit is configured to determine the flight path from a machine learning model. For example, the control unit is further configured to use the machine learning model to simulate a plurality of possible flight paths and determine the flight path from the plurality of possible flight paths. As a further example, the control unit is further configured to load and use the machine learning model based on data from a current flight (and optionally data from past flights), current (and optionally past) weather data, and aspects of changes in state of the aircraft. In at least one example, the control unit includes an artificial neural network configured to identify the flight path.

[0010] In at least one example, the aircraft includes the control unit.

[0011] The weather conditions include current weather conditions and / or predicted weather conditions.

[0012] The control unit can be further configured to automatically operate the aircraft in accordance with the flight path.

[0013] The control unit is further configured to display the flight path on the display.

[0014] The control unit can be further configured to automatically select the flight path for the flight of the aircraft.

[0015] Certain examples of the present disclosure provide a method for a system including an aircraft, the aircraft including a user interface having a display and a control unit in communication with the user interface. The method includes determining, by the control unit, a flight path for a flight of the aircraft based on tail number specific data of the aircraft and weather conditions.

[0016] Certain examples of the present disclosure provide an aircraft including a controller configured to operate the aircraft, a user interface having a display, and a control unit in communication with the user interface, as described herein. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 Illustrative block diagram of a system in accordance with examples of the present disclosure.

[0018] Figure 2 A front view of a display showing a flight path is shown in accordance with examples of the present disclosure.

[0019] Figure 3 A flowchart of a method in accordance with examples of the present disclosure is shown.

[0020] Figure 4 A schematic block diagram of a control unit in accordance with examples of the present disclosure is shown.

[0021] Figure 5 A perspective front view of an aircraft in accordance with examples of the present disclosure is shown. DETAILED DESCRIPTION

[0022] The foregoing summary, as well as certain examples, will be better understood when read in conjunction with the following detailed description. As used herein, an element or step recited in the singular and preceded by the word "a" or "an" should be understood as not necessarily excluding plural elements or steps, unless such exclusion is explicitly recited. Furthermore, references to "one example" are not intended to be interpreted as excluding the existence of additional examples that also incorporate the recited features. Moreover, unless explicitly stated to the contrary, examples "comprising" or "having" an element or a plurality of elements are intended to include additional elements not recited.

[0023] Examples of the present disclosure provide systems and methods that allow a pilot to receive real-time advisories based on tail-specific performance of a particular aircraft. The advisories and assessments include accurate fuel and time calculations that allow the pilot to find a preferred route and adjust the flight trajectory based on actual, precise data. The systems and methods use tail-specific data of the aircraft, rather than generic performance data. Notably, the use of generic data to calculate the impact of changes to a flight path, such as a direct or re-planned, is often inaccurate, which can result in incorrect assessments and yield fuel and time losses.

[0024] The systems and methods described herein are configured to optimize a flight path of an aircraft. The systems and methods include a control unit that assesses up-to-date weather conditions and tail-specific performance of the aircraft to determine a flight path. The number of trajectory options and randomness in weather changes can be so vast that performing a static simulation of a trajectory and assessing all possible options can be prohibitive in terms of time spent and accuracy of calculations. In at least one example, the control unit uses a machine learning model that is built using simulation data from multiple assessments of all possible trajectory options and possible weather conditions. The resulting model is loaded onto a computing device, such as a flight computer, a handheld smart device, etc., and used in real-time to dynamically select the best fuel and time- economic path among various options as the state of the aircraft and weather conditions change.

[0025] The systems and methods described herein optimize flight paths by using tail number specific performance (i.e., performance of a specific actual aircraft as opposed to a different test aircraft) that delivers precise data as compared to preset fixed speeds generated by flight planning systems. Certain examples of the present disclosure provide systems and methods that use tail number specific data modeling in combination with iterative algorithms to find the most efficient flight path between different locations, such as between a departure airport and an arrival airport, or at a point within a flight path to an arrival airport.

[0026] Figure 1 A schematic block diagram of a system 100 in accordance with examples of the present disclosure is illustrated. In at least one example, the system 100 is configured to determine a flight path for an aircraft 102. As an example, the flight path is between a departure airport or location and an arrival or destination airport or location. As another example, the flight path can be or otherwise include a change from an original flight path, such as a direct change or re-planning to a destination location from a point along the original flight path.

[0027] The aircraft 102 includes a controller 104 configured to control operation of the aircraft 102. For example, the controller 104 includes one or more of a control handle, a yoke, a joystick, a control surface controller, an accelerator, a decelerator, and the like.

[0028] The aircraft 102 also includes a plurality of sensors 106 that detect various aspects of the aircraft 102. As an example, the sensors 106 include one or more flight recorders 106a that record various aspects of the aircraft 102 during a flight, including various stages of the flight path, legs, and the like. A speed sensor 106b of the aircraft 102 outputs a speed signal indicative of a ground and / or air speed of the aircraft 102. A height sensor 106c of the aircraft 102 outputs a height signal indicative of a height of the aircraft 102. A position sensor 106d outputs a position signal of the aircraft. As an example, the position signal can be an Automatic Dependent Surveillance - Broadcast (ADS-B) signal. As another example, the position signal can be a Global Positioning System (GPS) signal monitored by a corresponding GPS monitor. In at least one example, the GPS allows for position determination and the ADS-B allows for the transmission system to broadcast that position, which can be determined by GPS and / or inertial sensors.

[0029] The sensors 106 can also include one or more environmental sensors 106e. For example, the environmental sensors 106e can include a temperature sensor configured to detect an ambient temperature around the aircraft 102. As another example, the environmental sensors 106e can include a wind speed sensor.

[0030] The sensors 106 can also include one or more weight sensors 106f. For example, the weight sensors 106f can include sensors configured to detect a total weight of the aircraft. As another example, the weight sensors 106f can include sensors configured to detect a fuel weight within the aircraft 102. As another example, the weight sensors 106f can include sensors configured to determine a center of gravity of the aircraft 102.

[0031] The sensors 106 can include more or fewer sensors than shown. The sensors 106 can detect additional aspects of the aircraft 102 in addition to position, velocity, and altitude. For example, one or more temperature sensors can detect a temperature of one or more portions of the aircraft (such as an engine temperature sensor). As another example, a fuel quantity sensor can detect a remaining fuel quantity of the aircraft.

[0032] The sensors 106 output data 108 indicative of the various aspects detected thereby. For example, the data 108 includes avionics data output by the flight recorder 106a. The control unit 110 is in communication with the sensors 106 by one or more wired or wireless connections and is configured to receive the data 108 from the sensors 106.

[0033] In at least one example, the control unit 110 is on the aircraft 102. For example, the control unit 110 can be part of a flight management computer of the aircraft 102. As another example, the control unit 110 can be part of a handheld device (such as a smartphone or smart tablet), a portable computer, a computer workstation, etc. within the aircraft 102. As another example, the control unit 110 can be remote from the aircraft 102.

[0034] The aircraft 102 also includes a user interface 112 including a display 114 in communication with an input device 116. The display 114 can be a monitor, a screen, a television, a touchscreen, etc. The input device 116 can include a keyboard, a mouse, a stylus, a touchscreen interface (i.e., the input device 116 can be integrated with the display 114), etc. The user interface 112 can be part of a handheld device (such as a smartphone or smart tablet), a portable computer, a computer workstation, etc. within the aircraft 102. In at least one example, the control unit 110 and the user interface 112 are part of a common computing device.

[0035] The control unit 110 also communicates with a weather subsystem 118, such as over one or more wired or wireless connections. The weather subsystem 118 can be a weather forecast or a meteorological service. As another example, the weather subsystem 118 can provide information, such as over an aircraft communication addressing and reporting system (ACARS) message. ACARS is a digital datalink system that transmits short messages between aircraft and ground stations, for example, over radio signals or satellites. The control unit 110 and the weather subsystem 118 can be at different locations. Alternatively, the control unit 110 and the weather subsystem 118 can be at a common location.

[0036] The control unit 110 also communicates with a database 120 that stores tail number specific data 122 for the aircraft 102. For example, the tail number specific data 122 can include various types of information specific to a particular aircraft 102, rather than a generic data set for a particular type of aircraft. In at least one example, the tail number specific data 122 can be a tail number specific model for the particular aircraft 102.

[0037] In operation, the control unit 110 analyzes weather data from the weather subsystem 118, the tail number specific data 122, and / or the data 108 to determine one or more flight paths for the aircraft 102 in order to enable the aircraft 102 to be operated efficiently and economically for the aircraft 102. In at least one example, the control unit 110 analyzes such data prior to a flight of the aircraft to determine an efficient flight path for the aircraft 102. As another example, the control unit 110 analyzes such data during a flight of the aircraft to determine an efficient change to a flight path. Rather than relying on generic determinations of flight parameters, the control unit 110 determines flight parameters or attributes for the aircraft, such as airspeed and altitude, based on actual data 108 output by the sensors 106 of the aircraft 102 during one or more actual flights of the aircraft 102. For example, the control unit 110 can determine efficient flight parameters for a future flight of the aircraft 102 based on data 108 from one or more previous flights. In at least one example, the control unit 110 determines flight parameters for a future flight based on data 108 received from a previous flight of the aircraft 102. As another example, the control unit 110 determines flight parameters for a future flight of the aircraft based on data 108 from multiple previous flights, such as the most recent 10, 20, 30, 40, or more flights of the aircraft 102. In this way, additional data from multiple flights of the aircraft 102 provides a more robust and refined determination of flight parameters.

[0038] In at least one example, the control unit 110 determines the effective flight parameters to determine the flight path of the current or future flight of the aircraft 102 by generating one or more flight models of the aircraft 102 based on data 108 received from the actual aircraft 102 (i.e., the specific tail number associated with the aircraft 102) rather than a different aircraft or a generic model.

[0039] In operation, the sensors 106 detect various aspects of the aircraft 102 during flight. The sensors 106 output data 108 indicative of the various aspects of the aircraft 102. The control unit 110 receives the data 108 of the specific aircraft 102 (as opposed to a test or generic aircraft). In at least one example, the flight recorder(s) 106a include aircraft interface devices and transmitters that output data 108, such as avionics data, to the control unit 110. As noted, the control unit 110 communicates with the flight recorder(s) 106a over one or more wired or wireless connections, such as over WiFi, Bluetooth, cellular, or other such connections. After the flight of the aircraft 102, the data 108 can be stored, such as in a cloud server, which can be used to perform post-flight analysis to estimate savings, further fine-tune performance models, etc.

[0040] In at least one example, the control unit 110 generates the optimal flight path based on data of the specific tail number of the aircraft 102 received from the weather subsystem 118 and current and / or predicted weather at various locations. The control unit 110 improves fuel efficiency by using tail number specific performance, which improves accuracy as compared to generic data generated by flight planning systems.

[0041] In at least one example, for each aircraft 102 (i.e., tail number), the control unit 110 uses actual flight records to construct a tail number specific deep neural network model that estimates airspeed, fuel flow, altitude, etc. during various legs of the flight path. For a given flight condition, the control unit 110 iterates over a range of cost indices (such as based on a predetermined descent table in the flight) to determine the optimal flight path of the aircraft 102.

[0042] In at least one example, the control unit 110 automatically operates one or more controllers 104 of the aircraft 102 during flight to automatically operate the aircraft 102 according to the determined flight path. For example, the control unit 110 determines various trajectories, airspeeds, and altitudes for different legs of the flight path of the aircraft 102. The control unit 110 automatically operates the controllers 104 to ensure that the aircraft 102 operates according to the determined flight path. Optionally, the control unit 110 can not automatically operate the aircraft 102.

[0043] The control unit 110 uses tail-specific performance data (as opposed to generic performance data) of the aircraft 102 to determine an efficient flight path between locations. In contrast, previously known methods use generic databases and do not account for performance differences of specific tail numbers, which in turn can result in inefficiencies.

[0044] In at least one example, the control unit 110 is a machine learning system that simulates many possible flight paths to ultimately determine the most efficient flight path of the aircraft 102. For example, the control unit 110 evaluates possible flight paths and possible weather conditions along such flight paths. However, evaluating all possible trajectory options with all possible operating conditions is computationally expensive and time consuming. Also, weather conditions can change rapidly. Accordingly, the control unit 110 builds a machine learning model based on ground-based simulations and evaluates all possible options and then once before any flight. Because the control unit 110 predetermines all possible options (including weather conditions, flight trajectories, and tail-specific performance data of the aircraft) prior to the actual flight (or during the flight), the control unit 110 can then evaluate the current weather conditions, flight data of the aircraft 102 (as detected by the sensors 106) and quickly and efficiently select a match among the predetermined options of flight paths and, thus, the most efficient flight path of the aircraft 102. The control unit 110 can then output a signal to the user interface 112 and electronically show the determined flight path on the display 114. Accordingly, the control unit 110 predetermines a machine learning model of flight paths including possible weather conditions (including wind direction and speed) and then selects the most efficient, optimal flight path for the aircraft 102 according to the current weather conditions and tail-specific data of the aircraft 102.

[0045] In at least one example, the control unit 110 is configured to intelligently select a flight path from a plurality of predetermined flight path and route options. As an example, for each waypoint along a flight path, the control unit 110 selects N closest waypoints within a specified threshold of the trajectory angle as candidate next waypoints. In doing so, the control unit 110 improves the computing device (and thereby reduces power consumption and computation time) by limiting the number of evaluation options by only considering relevant segments.

[0046] The control unit 110 receives weather data from the weather subsystem 118. The weather data includes past historical weather of various locations, as well as predicted weather of the location. The control unit 110 merges the predicted weather with the historical weather to determine limits of trajectory evaluation, which also improves the computing device (and thereby reduces power consumption and computation time) by limiting the number of evaluation options by only considering relevant weather conditions.

[0047] In at least one example, the control unit 110 uses a machine learning model to evaluate any combination of lateral path changes. The control unit 110 can further update, load, and / or use the machine learning model based on flight path data from the current flight (and optionally from past flights), current (and optionally past) weather data, aspects of the state of the particular aircraft 102 determined from the sensors 106, etc. That is, as the control unit 110 generates the machine learning model, the control unit 110 can continuously refine the machine learning model. In at least one example, the machine learning model is updated prior to a flight and then used by the control unit 110 during the flight. The machine learning model can be updated periodically, such as after a predetermined number of flights or a predetermined period of time (such as a week, month, etc.).

[0048] In at least one example, the machine learning model includes a tail number specific fuel flow model. The tail number specific fuel flow model is a model regarding the fuel flow of a particular aircraft (as opposed to general fuel data). The tail number specific fuel flow model can be updated periodically, for example, every month, two months, etc. In at least one further example, the machine learning model also includes a flight specific trajectory model, which relates to the specific trajectory of an actual flight (as opposed to general flight data). The flight specific trajectory model can be constructed and updated for each flight of the aircraft 102 and deleted after each flight.

[0049] As described, the control unit 110 receives weather data from the weather subsystem 118, receives specific performance data of the actual aircraft 102 from the tail number specific data 122 and / or from data received by the sensors 106, and uses a machine learning model to simulate various flight paths. The control unit 110 evaluates the current weather conditions (as received in data from the weather subsystem 118) to match the weather conditions of the simulated flight paths of the specific aircraft within the machine learning model (i.e., the tail number specific data of the aircraft 102). The control unit 110 selects, within the machine learning model, a flight path that matches (e.g., matches or closest match) the current weather conditions as well as the data of the specific tail number of the aircraft 102 at the location.

[0050] In at least one example, the system 100 includes an aircraft 102 that includes a user interface 112 having a display 114. A control unit 110 is in communication with the aircraft 102. The control unit is configured to determine one or more flight paths for a flight of the aircraft 102 based on tail number specific data 122 of the aircraft 102 and weather conditions, such as at various locations along a flight path. In at least one example, the control unit 110 is configured to determine the one or more flight paths prior to the flight of the aircraft 102. As another example, the control unit 110 is configured to determine the one or more flight paths during the flight of the aircraft 102.

[0051] Figure 2 A front view of the display 114 showing a flight path 200 is shown in accordance with examples of the present disclosure. The flight path 200 includes a departure airport 202 and an arrival airport 204. Various legs exist between the departure airport 202 and the arrival airport 204. For example, a first leg 206a is between a first waypoint 208a and a second waypoint 208b. A second leg 206b is between the second waypoint 208b and a third waypoint 208c. Referring to Figure 1 and Figure 2 The control unit 110 determines the flight path between the departure airport 202 and the arrival airport 204 prior to the actual flight of the aircraft 102. As another example, the control unit 110 determines the flight path between different points, such as between different waypoints, or between a waypoint and the arrival airport 204, during the flight of the aircraft. That is, the control unit 110 determines changes in the flight path during the flight.

[0052] Figure 3 A flowchart of a method in accordance with examples of the present disclosure is shown. Referring to Figure 1 and Figure 3 At 300, a flight plan is input. The flight plan is or includes an initial flight path between locations. The flight plan can be input through the user interface 112, which can be on the aircraft 102 or remote from the aircraft 102, such as at an operations control center. The control unit 110 receives the flight plan from the user interface 112, for example via one or more electronic signals including data.

[0053] At 302, after receiving the flight plan, the control unit 110 determines candidate trajectories for the flight path based on weather conditions. The weather conditions are current weather conditions and / or predicted weather conditions at various locations along the flight path as received from a weather subsystem 118, such as via one or more electronic signals including data.

[0054] At 304, control unit 110 simulates a flight path. Control unit 110 simulates the flight path from a machine learning model that pre-determines the flight path based on weather conditions and specific tail number data for aircraft 102. Control unit 110 can be updated. The machine learning model is loaded and / or used based on current and predicted weather conditions, flight restrictions (such as restricted airspace), current flight data of a specific aircraft 102 detected by sensor 106, etc.

[0055] Based on current weather conditions, control unit 110 can exclude various flight paths that do not conform to the current and / or predicted weather conditions within the machine learning model. Furthermore, based on specific data related to the aircraft's current tail number, control unit 110 can exclude various flight paths that do not conform to the current operational capabilities of aircraft 102.

[0056] After determining possible flight paths, control unit 110 then calculates the cost of the flight path based on the tail number-specific data of aircraft 102. Control unit 110 can then exclude flight paths that exceed a predetermined cost threshold (e.g., in terms of fuel combustion) and / or are too long. At 308, control unit 110 determines candidate trajectories for the flight path. At 310, control unit 110 determines the most cost-effective and / or time-efficient flight path. At 312, control unit 110 then electronically displays the determined flight path on display 114 (e.g., control unit 110 outputs an electronic signal having data including the determined flight path and operates display 114 to display the determined flight path).

[0057] The pilot can then select a flight path. As another example, control unit 110 automatically selects a flight path, such as via input received through input device 116. For instance, the pilot can provide instructions via input device 116 to select the most fuel-efficient flight path or the fastest flight path to the destination. Control unit 110 receives the instruction and automatically selects a flight path accordingly.

[0058] In at least one example, the control unit 110 is operable to operate the aircraft's controller to automatically operate the aircraft according to a flight path. As an example, the flight path can provide input for an automated pilot operation mode.

[0059] As described herein, control unit 110 uses tail-specific data 122 (instead of general data) of aircraft 102 and weather conditions (e.g., current and / or predicted weather at various locations) to determine the flight path of aircraft 102. Control unit 110 determines the flight path (such as changes to the initial flight path during flight) before and / or during the flight of aircraft 102.

[0060] In at least one example, the control unit 110 adapts the flight path based on current and predicted / forecasted weather conditions, such as wind direction and wind speed at various flight segments, rather than using weather information that is not current. The control unit 110 receives information about the latest winds, thereby ensuring effective adaptation of the flight path.

[0061] The systems and methods described herein allow the pilot to fly the aircraft 102 along the optimal flight path, which saves a significant amount of fuel.

[0062] Figure 4 A schematic block diagram of the control unit 110 is shown in accordance with examples of the present disclosure. In at least one example, the control unit 110 includes at least one processor 410 in communication with a memory 412. The memory 412 stores instructions 414, received data 416, and generated data 418. Figure 4 The control unit 110 shown in FIG. 4 is merely an example and is not limiting.

[0063] As used herein, the terms "control unit," "central processing unit," "CPU," "computer," and the like can include any processor-based or microprocessor-based system including systems using microcontrollers, reduced instruction set computers (RISC), application specific integrated circuits (ASICs), logic circuitry, and any other circuit or processor capable of executing the functions described herein. This is merely exemplary and therefore is not intended to limit in any way the definition and / or meaning of such terms. For example, as described herein, the control unit 110 can be or include one or more processors configured to control operations.

[0064] The control unit 110 is configured to execute a set of instructions that are stored in one or more data storage elements or components (such as one or more memories) in order to process data. For example, the control unit 110 can include or be coupled with one or more memories. The data storage elements can also store data or other information as desired or needed. The data storage elements can be in the form of information sources or physical memory elements within a processing machine.

[0065] The set of instructions can include various commands that instruct the control unit 110 as a processing machine to perform various processes, such as the methods and processes for various examples of the subject matter described herein. The set of instructions can be in the form of a software program. The software can be in various forms such as system or application software. Further, the software can be in the form of a collection of separate programs, a sub- routine within a larger program or a portion of a program within a larger program. The software can also include modular programming in the form of object-oriented programming. The processing of input data by the processing machine can be in response to user commands, or in response to results of previous processes, or in response to a request made by another processing machine.

[0066] The diagrams of the examples herein can show one or more control or processing units, such as control unit 110. It should be understood that a processing or control unit can represent circuitry, which can be implemented as hardware (e.g., software stored on a tangible and non-transitory computer readable storage medium such as a computer hard drive, ROM, RAM, etc.) having associated instructions that perform the operations described herein, circuitry, or portions thereof. The hardware can include state machines hardwired to perform the functions described herein. Alternatively, the hardware can include electronic circuitry including and / or connected to one or more logic-based devices, such as microprocessors, processors, controllers, etc. Alternatively, control unit 110 can represent processing circuitry, such as one or more of a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a microprocessor, etc. The circuitry in the different examples can be configured to perform one or more algorithms to perform the functions described herein. Whether explicitly identified in a flowchart or method or not, one or more algorithms can include aspects of the examples disclosed herein.

[0067] As used herein, the terms "software" and "firmware" are interchangeable, and include any computer program stored in a data storage unit (e.g., one or more memories), including RAM memory, ROM memory, EPROM memory, EEPROM memory, and nonvolatile RAM (NVRAM) memory. The above memory types are exemplary only, and are thus not limiting as to the types of memory usable for storage of a computer program.

[0068] In at least one example, control unit 110 can also control controllers 104 of aircraft 102 to operate aircraft 102 based at least in part on the determined flight path. For example, based on the determined flight path, control unit 110 can automatically operate controllers 104 to increase or decrease the ground or airspeed of aircraft 102, the rate of climb, etc.

[0069] In at least one example, all or a portion of the systems and methods described herein can be or otherwise include an artificial intelligence (AI) or machine learning system that can automatically perform the operations of the methods also described herein. For example, the control unit 110 can be an artificial intelligence or machine learning system. These types of systems can be trained from external information and / or self-train to repeatedly improve the accuracy of analyzing data to determine flight paths between different locations, as well as adapt parameters based on tail number specific data 122 and weather conditions. Over time, these systems can improve by determining flight path parameters with increased accuracy and speed, thereby significantly reducing the likelihood of any potential errors. The AI or machine learning systems described herein can include techniques enabled by adaptive predictive capabilities and exhibit at least some degree of autonomous learning to automate and / or enhance pattern detection (e.g., identifying irregularities or regularities in data), customization (e.g., generating or modifying rules to optimize record matching), and the like. The systems can be trained and retrained using feedback from one or more prior analyses of data, aggregate data, and / or other such data. Based on this feedback, the systems can be trained by adjusting one or more parameters, weights, rules, criteria, and the like used in the analysis system. This process can be performed using data and aggregate data rather than training data and can be repeated multiple times to repeatedly improve the determination of flight paths. Training minimizes conflicts and interference by performing an iterative training algorithm in which the system utilizes updated data sets (e.g., data 108 received during and / or after each flight of the aircraft 102) and re-trains based on feedback examined prior to the most recent training of the system. This provides a robust analysis model that can better determine the most cost effective and efficient flight paths for a particular aircraft 102.

[0070] In at least one example, the control unit 110 includes or represents an artificial neural network (ANN) that identifies patterns in visual representations of data, classifies the patterns based on the content of the identified patterns (e.g., assigns a class to the identified patterns, such as class #1, class #2, etc.), and identifies one or more flight paths based on the classification. Using a specially trained ANN in this way to identify flight paths provides improvements over traditional methods of determining flight paths, including more accurate identification of valid flight paths, and identification of various types of flight paths on a much larger scale than possible for a human to determine flight paths, and identification of flight paths at a much faster and / or much more frequent rate than possible for a human. The ANN can be implemented by software, hardware, or a combination of software and hardware. The structure of the ANN can be a series of layers, each layer including one or more artificial neurons arranged in one or more arrays of neurons. Each of these neurons can include or represent a register, a microprocessor, and at least one input. Each neuron can produce an output or activation based on an activation function using the output of a previous layer and a set of weights as inputs. Each neuron in a neuron array can be connected to another neuron in the same layer or another layer via one or more synapse circuits. The synapse circuits can include memory for storing synapse weights. An example of this ANN can be a deep neural network with an input layer, an output layer, and multiple fully connected hidden layers. In some examples, the ANN (e.g., control unit 110) can be implemented by an application-specific integrated circuit (ASIC) that is specially tailored for the particular artificial intelligence application described herein, and provides superior computing power and reduced power consumption compared to traditional computers.

[0071] The training data can be historical data that the neural network can use to learn patterns in visual representations of data to identify or detect the same (or similar) patterns in other data collected from other components or devices. The trained ANN monitors additional visual representations of data to identify patterns and classify the patterns. If the trained ANN detects one or more patterns, the trained ANN can classify the patterns to generate classification data that can be output to a user and / or used to retrain the ANN. For example, the classification data can identify a type or pattern of a potential or upcoming failure of a component or device.

[0072] The ANN of the control unit 110 can continue to learn to improve the recognition of patterns in the data visualizations and to improve the classification of the recognized patterns. This continued learning can occur by, for example, changing the output generated by one or more of the neurons in response to receiving the same input (e.g., the neurons produce different outputs after the change), changing the activation function of one or more of the neurons, changing one or more of the weights, and / or changing one or more of the connections between the neurons (or which neurons are connected to each other). Changing one or more of these factors can cause the ANN to produce different outputs (e.g., recognize different patterns and / or select different classifications) than before the change.

[0073] Examples of the present disclosure provide systems and methods that allow for a large amount of data to be quickly and efficiently analyzed by a computing device. For example, the control unit 110 can analyze various aspects of a flight of the aircraft 102 based on the data 108 received from the sensors 106 and weather information for various flight paths. Further, the control unit 110 creates variables based on the various aspects and determines a flight path from the variables, which can be in a format that is not easily discernible by a human. As such, a large amount of data that can not be discernible by a human is being tracked and analyzed. The large amount of data is efficiently organized and / or analyzed by the control unit 110 as described herein. The control unit 110 analyzes the data in a relatively short amount of time in order to quickly and efficiently determine a flight path for the aircraft 102. A human could not efficiently analyze such a large amount of data in such a short amount of time. As such, examples of the present disclosure provide increased and efficient functionality and greatly superior performance in relation to a human analyzing a large amount of data.

[0074] The components of the system 100, such as the control unit 110, provide and / or enable a computer system to operate as a specialized computer system for determining a flight path for the aircraft 102. The control unit 110 improves a computing device by allowing for an effective flight path to be determined based on tail number specific data and weather conditions and it greatly reduces computation time and power.

[0075] Figure 5A perspective front view of an aircraft 102 is shown in accordance with examples of the present disclosure. The aircraft 102 includes a propulsion system 512 including, for example, engines 514. Optionally, the propulsion system 512 can include more engines 514 than shown. The engines 514 are carried by a wing 516 of the aircraft 102. In other examples, the engines 514 can be carried by a fuselage 518 and / or a tail 520. The tail 520 can also support a horizontal stabilizer 522 and a vertical stabilizer 524. The fuselage 518 of the aircraft 102 defines an interior cabin 530 including a cockpit or flight deck, one or more crew sections (e.g., a galley, a crew personal effects area, etc.), one or more passenger sections (e.g., first class, business class, and economy class sections), one or more lavatories, etc. Figure 5 An example of an aircraft 102 is shown. It should be appreciated that the size, shape, and configuration of the aircraft 102 can differ from that shown in FIG. 1. Figure 5

[0076] Further, the present disclosure includes examples in accordance with the following clauses:

[0077] Clause 1. A system comprising:

[0078] an aircraft, the aircraft including a user interface having a display; and

[0079] a control unit in communication with the user interface, wherein the control unit is configured to determine a flight path for a flight of the aircraft based on tail number specific data of the aircraft and weather conditions.

[0080] Clause 2. The system of clause 1, wherein the control unit is configured to determine the flight path prior to the flight of the aircraft.

[0081] Clause 3. The system of clause 1 or 2, wherein the control unit is configured to determine the flight path during the flight of the aircraft.

[0082] Clause 4. The system of any of clauses 1-3, wherein the control unit is configured to determine the flight path from a machine learning model.

[0083] Clause 5. The system of clause 4, wherein the control unit is further configured to use the machine learning model to simulate a plurality of possible flight paths and determine the flight path from the plurality of possible flight paths.

[0084] Clause 6. The system of clause 4 or 5, wherein the control unit is further configured to load the machine learning model based on aspects of data from a current flight, current weather data, and changes in a state of the aircraft.

[0085] Clause 7. The system of any of clauses 1-6, wherein the control unit includes an artificial neural network configured to identify the flight path.​

[0086] Item 8. The system of any of items 1-7, wherein the aircraft comprises a control unit.

[0087] Item 9. The system of any of items 1-8, wherein the weather conditions comprise current weather conditions and predicted weather conditions.

[0088] Item 10. The system of items 1-9, wherein the control unit is further configured to automatically operate the aircraft according to the flight path.

[0089] Item 11. The system of any of items 1-10, wherein the control unit is further configured to display the flight path on the display.

[0090] Item 12. The system of any of items 1-11, wherein the control unit is further configured to automatically select the flight path for the aircraft.

[0091] Item 13. A method for a system, comprising:

[0092] an aircraft, the aircraft comprising a user interface having a display; and

[0093] a control unit in communication with the user interface,

[0094] the method comprising determining, by the control unit, a flight path for the aircraft to fly based on tail number specific data for the aircraft and weather conditions.

[0095] Item 14. The method of item 13, wherein determining comprises determining the flight path prior to the aircraft flying and determining the flight path during the aircraft flying.

[0096] Item 15. The method of item 13 or 14, wherein determining comprises using a machine learning model to determine the flight path.

[0097] Item 16. The method of item 15, wherein using comprises:

[0098] simulating a plurality of possible flight paths; and

[0099] determining the flight path from the plurality of possible flight paths.

[0100] Item 17. The method of item 15 or 16, further comprising updating the machine learning model based on data from current flights, data from past flights, current and past weather data, and changing aspects of the aircraft.

[0101] Item 18. The method of any of items 13-17, further comprising automatically operating, by the control unit, the aircraft according to the flight path.

[0102] Item 19. The method of any of items 13-18, further comprising automatically selecting, by the control unit, a flight path for the aircraft.

[0103] Item 20. An aircraft, comprising:

[0104] a controller configured to operate the aircraft;

[0105] a user interface having a display; and

[0106] a control unit in communication with the user interface, wherein the control unit is configured to:

[0107] simulate, using a machine learning model, a plurality of possible flight paths for a flight of the aircraft,

[0108] determine, from the plurality of possible flight paths, a flight path for the flight of the aircraft based on tail number specific data for the aircraft and weather conditions,

[0109] use the machine learning model based on data from a current flight, current weather data, and aspects of changes in state of the aircraft,

[0110] automatically select a flight path for the aircraft, and

[0111] display the flight path on the display.

[0112] As described herein, examples of the present disclosure provide systems and methods for efficiently and effectively evaluating flight paths, including changes to existing flight paths. Further, examples of the present disclosure provide systems and methods for accurately determining optimal flight paths based on specific flight data for a particular aircraft.

[0113] While various spatial and directional terms, such as top, bottom, lower, mid, lateral, horizontal, vertical, anterior, posterior, and the like, can be used herein to relate to the illustrations, it is understood that such terms are merely used with respect to the orientations in the drawings. The orientation can be reversed, rotated by 90 degrees or otherwise changed such that the upper is lower, the lower is upper, horizontal is vertical, etc.

[0114] As used herein, a structure, limitation, or element that is “configured to” perform a task or operation is specifically configured in a manner corresponding to the task or operation, such that the task or operation is performed. For clarity and avoidance of doubt, an object that is merely capable of being modified to perform the task or operation is not “configured to” perform the task or operation as those terms are used herein.

[0115] It should be understood that the foregoing description is intended to be illustrative and not restrictive. For example, the above-described examples (and / or aspects thereof) can be used in combination with each other. Also, many modifications can be made to adapt a particular situation or material to the teachings of the various examples of the present disclosure without departing from their scope. While the dimensions and types of materials described herein are intended to define the aspects of the various examples of the present disclosure, the examples are by no means limiting, but are exemplary examples. Many other examples will be apparent to those of ordinary skill in the art upon reviewing the above description. The scope of the various examples of the present disclosure should, therefore, be determined not with reference to the above description, but instead with reference to the appended claims, along with their full scope of equivalents to which such claims are entitled. In the appended claims and the following detailed description, the terms “including” and “in which” are used as the plain English equivalents of the respective terms “comprising” and “wherein.” Also, the use of the term “about” is meant to allow for a number of variations and / or approximations. Additionally, the use of the term “first,” “second,” and “third,” etc. are simply used as labels, and are not intended to impose numerical requirements on their objects. Furthermore, the limitations of the following claims are not written in means-plus-function format and are not intended to be interpreted to so, unless and until such claims limitations are explicitly drafted as being means-plus-function format and expressly recite a step limitation at the end of the claim. Various examples of the present disclosure are described herein with reference to the following drawings.

[0116] This written description uses examples to disclose various examples of the present disclosure, including the best mode, and also to enable any person skilled in the art to practice various examples of the present disclosure, including making and using any devices or systems and performing any incorporated methods. The patentable scope of the various examples of the present disclosure is defined by the claims, and can include other examples that occur to those skilled in the art. Such other examples are intended to fall within the scope of the claims if they have structural elements that do not differ from the literal language of the claims, or if they include equivalent structural elements with insubstantial differences from the literal languages of the claims.

Claims

1. A system for determining the flight path of an aircraft, comprising: The aircraft includes a user interface with a display; as well as The control unit communicates with the user interface. The control unit is configured to determine the flight path of the aircraft based on specific data of the aircraft's tail number and weather conditions.

2. The system according to claim 1, wherein, The control unit is configured to determine the flight path before the aircraft takes flight.

3. The system according to claim 1, wherein, The control unit is configured to determine the flight path during the flight of the aircraft.

4. The system according to claim 1, wherein, The control unit is configured to determine the flight path from a machine learning model.

5. The system according to claim 4, wherein, The control unit is further configured to use the machine learning model to simulate multiple possible flight paths and determine the flight path from the multiple possible flight paths.

6. The system according to claim 4, wherein, The control unit is further configured to load and use the machine learning model based on data from the current flight, current weather data, and changes in the aircraft's state.

7. The system according to claim 1, wherein, The control unit includes an artificial neural network configured to identify the flight path.

8. The system according to claim 1, wherein, The aircraft includes the control unit.

9. The system according to claim 1, wherein, The weather conditions include current weather conditions and predicted weather conditions.

10. The system according to claim 1, wherein, The control unit is further configured to automatically operate the aircraft according to the flight path.

11. The system according to claim 1, wherein, The control unit is further configured to display the flight path on the display.

12. The system according to claim 1, wherein, The control unit is further configured to automatically select the flight path of the aircraft.

13. A method for determining the flight path of an aircraft, the method being implemented in the system according to claim 1, the method comprising: The control unit determines the flight path of the aircraft based on specific data of the aircraft's tail number and weather conditions.

14. The method according to claim 13, wherein, The determination includes determining the flight path before the aircraft takes flight and determining the flight path during the aircraft's flight.

15. The method according to claim 13, wherein, The determination includes using a machine learning model to determine the flight path.

16. The method according to claim 15, wherein, The use includes: Simulate multiple possible flight paths; and The flight path is determined from the plurality of possible flight paths.

17. The method of claim 15, further comprising: The machine learning model is updated based on data from the current flight, data from past flights, current and past weather data, and changes in the aircraft's state.

18. The method of claim 13, further comprising: The control unit automatically operates the aircraft according to the flight path.

19. The method of claim 13, further comprising: The control unit automatically selects the flight path for the aircraft.

20. An aircraft comprising: The controller is configured to operate the aircraft; User interface with display; as well as The control unit communicates with the user interface, wherein the control unit is configured to: A machine learning model was used to simulate multiple possible flight paths for the aircraft. Based on the specific tail number data of the aircraft and weather conditions, the flight path is determined from the plurality of possible flight paths. Based on data from the current flight, current weather data, and changes in the aircraft's state, the machine learning model is loaded and used. Automatically select the flight path of the aircraft, and The flight path is displayed on the monitor.

Images