Air data indicating device and calibration method thereof

Abstract

The invention relates to an air data indication and calibration device (1) and a method for a vertical take-off and landing aircraft, in particular a helicopter (50), for providing information of the airspeed of the vertical take-off and landing aircraft and for providing information of the height of the vertical take-off and landing aircraft. The vertical take-off and landing aircraft comprises pitot tube equipment (51) used for determining stagnation point air pressure at the position where the pitot tube equipment (51) is located; and the static pressure hole equipment (52) is used for determining the static pressure at the position of the static pressure hole equipment (52). The air data indicating device (1) comprises an airspeed and altitude determining module (2) used for determining the airspeed and altitude of the vertical take-off and landing aircraft in real time according to flight data by using a regression device (3) obtained by training an artificial neural network through training data.

Description

Technical Field

[0001] The present invention relates to an air data indicating device for a vertical take-off and landing (VTOL) aircraft (particularly a helicopter), which is used to provide airspeed information of the vertical take-off and landing aircraft and to provide altitude information of the vertical take-off and landing aircraft. Therefore, the vertical take-off and landing aircraft comprises: a pitot tube device, which is used to determine the stagnation air pressure at the position of the pitot tube device and provide pitot tube data including the stagnation air pressure information at the position of the pitot tube device; and a static pressure hole device, which is used to determine the static air pressure at the position of the static pressure hole device and provide static pressure hole data including the information of the static air pressure at the position of the static pressure hole device. In addition, the present invention also relates to a method for calibrating such an air data indicating device. Background Art

[0002] As is known, air data indicating devices belong to the initially mentioned technical field. They are included in the so-called pitot-static system implemented in vertical take-off and landing (VTOL) aircraft. Such pitot-static system measures the stagnation air pressure at the location of the pitot tube device using a pitot tube device installed on the vertical take-off and landing aircraft, and measures the static air pressure at the location of the static port device using a static port device installed on the vertical take-off and landing aircraft. Using the air data indicating device, the airspeed and altitude of each vertical take-off and landing aircraft are determined using the pitot tube data (including the stagnation air pressure information measured at the location of the pitot tube device on the vertical take-off and landing aircraft using the pitot tube device) and using the static port data (including the static air pressure information measured at the static port device on the vertical take-off and landing aircraft using the static port device). The airspeed and altitude of the vertical take-off and landing aircraft are then displayed to the pilot of the vertical take-off and landing aircraft, or the data including the airspeed and altitude information of the vertical take-off and landing aircraft are forwarded to the autopilot of the vertical take-off and landing aircraft so that the vertical take-off and landing aircraft can fly automatically in the autopilot mode.

[0003] These pitot-static systems are critical to the safety of the VTOL aircraft. If the pilot does not know the correct airspeed and the correct altitude, or even relies on incorrect values ​​for the VTOL aircraft's airspeed and altitude, the pilot may attempt a fly maneuver that causes the VTOL aircraft to crash. Likewise, if data containing incorrect airspeed and / or incorrect VTOL aircraft altitude information is forwarded to the VTOL aircraft's autopilot, it may cause the VTOL aircraft to crash.

[0004] Therefore, the pitot-static system needs to reliably display the VTOL aircraft's airspeed and altitude to the pilot with at least the accuracy required by regulatory specifications. To achieve this, the air data indicating device needs to reliably determine the VTOL aircraft's airspeed and altitude with at least the accuracy required by regulatory specifications and provide correct information about the VTOL aircraft's airspeed and altitude.

[0005] However, in a vertical take-off and landing aircraft, the stagnation pressure at the position of the pitot tube device and the static pressure at the position of the static port device depend not only on the actual airspeed and actual altitude of the vertical take-off and landing aircraft, but also on the current flight configuration and current flight conditions of the vertical take-off and landing aircraft. More precisely, there are airflows and turbulences around the vertical take-off and landing aircraft, so the pitot tube device and the static port device are arranged on the vertical take-off and landing aircraft. These airflows and turbulences at the positions of the pitot tube device and the static port device change with the changes of the flight configuration and flight conditions of the vertical take-off and landing aircraft. Therefore, at a given airspeed and altitude of the vertical take-off and landing aircraft, the stagnation pressure measured by the pitot tube device and the static pressure measured by the static port device depend on the current flight configuration and current flight conditions of the vertical take-off and landing aircraft. Therefore, in order to provide the airspeed and altitude to the pilot of the vertical take-off and landing aircraft with acceptable accuracy, the air data indicating device of the vertical take-off and landing aircraft must be calibrated.

[0006] Methods for calibrating air data indicating devices are described, for example, by Denis Hamel and Alex Kolarich in the Vertical Flight Society's 76 th Annual Forum & Technology Display, Oct 06-08, 2020, Virtual presented the article "GPS-BASED Airspeed Calibration for Rotocraft: Generalized Application for All Flight Regimes". The article deals with the calibration of the pitot-static system. Therefore, according to the article, the GPS-based true airspeed method, with appropriate execution and analysis techniques, is identified as the most practical in terms of equipment and efficiency to provide calibration of the complete airspeed system.

[0007] However, there is no known calibration method capable of calibrating the values ​​of airspeed and altitude determined by the air indicating device of a vertical take-off and landing aircraft with the accuracy required by regulatory specifications for all flight configurations and flight conditions.

[0008] In addition to the calibration issues mentioned above, the stagnation pressure at the location of the pitot tube device and the static pressure at the location of the static port device also depend on the location of the pitot tube device and the static port device on the vertical take-off and landing aircraft. For example, it is generally observed that the closer the pitot tube device and the static port device are set to the vertical take-off and landing aircraft fuselage, the more the stagnation pressure measured by the pitot tube device and the static pressure measured by the static port device deviate from the effective values ​​of the stagnation pressure and the static pressure. However, when designing a new vertical take-off and landing aircraft including a pitot-static system, it is often necessary to repeatedly reposition the pitot tube device and the static port device because the deviations of the measured stagnation pressure and static pressure from the effective values ​​of the stagnation pressure and the static pressure are too large to be calibrated to achieve the required accuracy. This usually leads to multiple design iterations, in each of which, after test flights with a prototype of such a vertical take-off and landing aircraft, the air data indicating device of the adopted pitot tube system is recalibrated to verify the accuracy of the pitot tube system, until a design of the vertical take-off and landing aircraft is found that meets the regulatory specifications for the pitot-static system, as well as the arrangement of the pitot tube device and the static port device on the vertical take-off and landing aircraft. Since these iterations are very time-consuming and costly, it makes sense to reduce the number of iterations required. One known method of reducing the number of iterations is to place the pitot tube device and the static port device at a location in the non-critical pressure field, specifically away from the fuselage of the vertical take-off and landing aircraft. However, this has the disadvantage of being costly and causing safety issues for ground personnel. SUMMARY OF THE INVENTION

[0010] The object of the invention is to create an air data indicating device belonging to the initially mentioned technical field and a method for calibrating such an air data indicating device, enabling said air data indicating device to provide airspeed and altitude values ​​that are correct and with the accuracy required by regulatory specifications for all flight configurations and flight conditions, and making the design procedure for designing vertical take-off and landing aircraft cheaper and safer.

[0011] The solution of the present invention is described by the features of claim 1. According to the present invention, the air data indicating device is connectable to a pitot tube device for receiving pitot tube data provided by the pitot tube device, and the air data indicating device is connectable to a static port device for receiving static port data provided by the static port device. Therefore, the air data indicating device comprises an airspeed and altitude determining module, the airspeed and altitude determining module is used to determine the airspeed of the vertical take-off and landing aircraft and the altitude of the vertical take-off and landing aircraft in real time according to flight data using a regressor obtained by training an artificial neural network with training data, wherein the flight data comprises at least: pitot tube data, static port data, vertical speed data including vertical speed information of the vertical take-off and landing aircraft, and pitch attitude angle data including pitch attitude angle information of the vertical take-off and landing aircraft.

[0012] According to the invention, an air data indicating device is used for a vertical take-off and landing (VTOL) aircraft, in particular a helicopter. Therefore, it is not important whether the VTOL aircraft or the helicopter is a manned aircraft or an unmanned aircraft. If the VTOL aircraft or the helicopter is a manned aircraft, the pilot of the VTOL aircraft or the helicopter can be located on the VTOL aircraft or the helicopter, respectively, or, if the VTOL aircraft or the helicopter, respectively, can be remotely controlled by a remote controller, the pilot can be located on the ground. If the VTOL aircraft or the helicopter, respectively, is an unmanned aircraft, the VTOL aircraft or the helicopter, respectively, can advantageously be remotely controlled by a remote controller. In all these cases, the VTOL aircraft or the helicopter, respectively, can also include an autopilot, which relies on a pitot-static system or the like comprising the air data indicating device according to the invention.

[0013] According to the present invention, the air data indicating device is used to provide information about the airspeed of the vertical take-off and landing aircraft and to provide information about the height of the vertical take-off and landing aircraft. Therefore, the air data indicating device is advantageously suitable for providing the airspeed information of the vertical take-off and landing aircraft determined by the airspeed and height determination module, and is suitable for providing the height information of the vertical take-off and landing aircraft determined by the airspeed and height determination module. Therefore, in one example, the air data indicating device includes a display for displaying the airspeed and height of the vertical take-off and landing aircraft. In this example, the airspeed information of the vertical take-off and landing aircraft and the height information of the vertical take-off and landing aircraft are provided by the air data indicating device by displaying the airspeed and height on the display. In another example, the air data indicating device includes an output port for outputting output data including information about the airspeed of the vertical take-off and landing aircraft and information about the height of the vertical take-off and landing aircraft. In this other example, the output port can be connected to the autopilot of the vertical take-off and landing aircraft. Alternatively, the output port can be connected to some other device, such as an onboard computer of the vertical take-off and landing aircraft, for transmitting the output data from the air data indicating device to the onboard computer to display the airspeed and height on a display controlled by the onboard computer. Alternatively, in the case where the vertical take-off and landing aircraft can be remotely controlled by a remote controller, the output port can be connected to the remote controller of the vertical take-off and landing aircraft to transmit the output data from the air data indicating device to the remote controller to display the airspeed and altitude on the remote controller. Therefore, the air data indicating device can be, for example, located in the vertical take-off and landing aircraft and transmit the output data to the remote controller, or can be, for example, located in the remote controller to control and receive the pitot tube data and static pressure port data sent by the vertical take-off and landing aircraft. In any variant with an output port, the airspeed information of the vertical take-off and landing aircraft and the altitude information of the vertical take-off and landing aircraft are both provided by the air data indicating device in the form of output data.

[0014] According to the present invention, the air data indicating device comprises an airspeed and altitude determination module, which is adapted to determine the airspeed of the vertical take-off and landing aircraft and the altitude of the vertical take-off and landing aircraft in real time according to the flight data using a regressor obtained by training an artificial neural network with training data. In one example, the airspeed and altitude determination module is a computer program product running on a computing unit (e.g., a control computer of the vertical take-off and landing aircraft, or another computing unit separate from the control computer of the vertical take-off and landing aircraft). In another example, the airspeed and altitude determination module is a computing unit adapted to determine the airspeed of the vertical take-off and landing aircraft and the altitude of the vertical take-off and landing aircraft in real time according to the flight data using a regressor obtained by training an artificial neural network with training data.

[0015] Whether the airspeed and altitude determination module is a computer program product or a computing unit, the airspeed and altitude determination module is suitable for determining the airspeed of the vertical take-off and landing aircraft and the altitude of the vertical take-off and landing aircraft in real time according to the flight data using a regressor obtained by training an artificial neural network with training data. Therefore, in the operation of the airspeed and altitude determination module, the flight data is advantageously fed to the regressor in real time to determine the airspeed of the vertical take-off and landing aircraft and the altitude of the vertical take-off and landing aircraft in real time according to the flight data. Therefore, in one example, the regressor outputs the airspeed and altitude of the vertical take-off and landing aircraft. In another example, the airspeed and altitude of the vertical take-off and landing aircraft can be calculated by the airspeed and altitude determination module based on the output of the regressor. In the latter example, the output of the regressor can be, for example, a calibrated stagnation pressure and a calibrated static pressure, and the airspeed and altitude determination module can calculate the airspeed of the vertical take-off and landing aircraft and the altitude of the vertical take-off and landing aircraft based on the calibrated stagnation pressure and the calibrated static pressure.

[0016] According to the present invention, the flight data at least includes: pitot tube data, static pressure port data, vertical speed data including vertical speed information of the vertical take-off and landing aircraft, and pitch attitude angle data including pitch attitude angle information of the vertical take-off and landing aircraft.

[0017] Since the pitot tube data includes the stagnation pressure information at the location of the pitot tube device, the pitot tube data may be, for example, the stagnation pressure expressed in arbitrary units and output by the pitot tube device and measured by the pitot tube device, an uncalibrated airspeed calculated based on the measured stagnation pressure and the measured static pressure, or a pre-calibrated airspeed. The pre-calibrated airspeed may be, for example, an uncalibrated airspeed calibrated using a known position calibration in a lookup table.

[0018] Since the static pressure hole data includes information about the static air pressure at the location of the static pressure hole, the static pressure hole data may be, for example, the static air pressure expressed in arbitrary units and output by the static pressure hole and measured by the static pressure hole, an uncalibrated height calculated based on the measured static air pressure, or a pre-calibrated height. The pre-calibrated height may be, for example, a pre-calibrated height calibrated using a known position calibration in a lookup table.

[0019] Since the vertical speed data includes vertical speed information of the vertical take-off and landing aircraft, the vertical speed data can be obtained from the static port data, for example, using the change in the value of the static port data over time. For example, this can be the change in the value of the static air pressure measured by the static port and output by the static port over time (expressed in arbitrary units), the change in the uncalibrated altitude over time calculated based on the measured static air pressure, or the change in the pre-calibrated altitude over time. In either case, this can be the change within each predefined time unit.

[0020] Since the pitch attitude angle data includes the pitch attitude angle information of the vertical take-off and landing aircraft, the pitch attitude angle data can be obtained, for example, from the air data attitude and heading reference system (ADAHRS) of the vertical take-off and landing aircraft, specifically from the gyroscopic flight instrument or the micro-electrochemical system (MEMS) gyroscope. In order to receive the pitch attitude angle data, the flight data indicating device can be advantageously connected to a pitch attitude angle data providing unit that provides the pitch attitude angle data. The pitch attitude angle data providing unit can, for example, be a gyroscopic flight instrument or a micro-electrochemical system (MEMS) gyroscope. However, the pitch attitude angle data providing unit can also be a computer, which receives the pitch attitude angle data from another unit or the mentioned gyroscopic flight instrument or the micro-electrochemical system (MEMS) gyroscope, respectively. Therefore, the pitch attitude angle data providing unit can, for example, become a part of the air data attitude and heading reference system (ADAHRS) of the vertical take-off and landing aircraft.

[0021] In the method for calibrating an air data indicating device according to the present invention, an airspeed and altitude determination module of the air data indicating device is calibrated using a regressor obtained by training a neural network with training data to calibrate the air data indicating device, wherein the training data comprises a training data set. Thus, each training data set is associated with a flight condition and comprises flight data obtained during a flight with a vertical take-off and landing aircraft, in particular a helicopter, of a type of vertical take-off and landing aircraft for which the air data indicating device is calibrated under the respective flight condition. Each training data set includes reference output data corresponding to the expected output of the regressor during the flight of the vertical take-off and landing aircraft of the respective type of vertical take-off and landing aircraft under the respective flight conditions, wherein the flight data at least includes: pitot tube data, obtained from the pitot tube device of the vertical take-off and landing aircraft of the respective type of vertical take-off and landing aircraft during the flight of the vertical take-off and landing aircraft of the respective type of vertical take-off and landing aircraft under the respective flight conditions; static pressure port data, obtained from the static pressure port device of the vertical take-off and landing aircraft of the respective type of vertical take-off and landing aircraft during the flight of the vertical take-off and landing aircraft of the respective type of vertical take-off and landing aircraft under the respective flight conditions; vertical speed data, including information on the vertical speed of the vertical take-off and landing aircraft of the respective type of vertical take-off and landing aircraft during the flight of the vertical take-off and landing aircraft of the respective type of vertical take-off and landing aircraft under the respective flight conditions, and pitch attitude angle data, including information on the pitch attitude angle of the vertical take-off and landing aircraft of the respective type of vertical take-off and landing aircraft during the flight of the vertical take-off and landing aircraft of the respective type of vertical take-off and landing aircraft under the respective flight conditions.

[0022] Therefore, advantageously, for each training data set, the flight data of the respective training data set have been obtained and advantageously recorded simultaneously. Therefore, advantageously, for each training data set, the flight data of the respective training data set have been obtained and advantageously recorded during the same test flight of a vertical take-off and landing aircraft of the respective type of vertical take-off and landing aircraft during a maneuvering flight under the respective flight conditions. This has the advantage that, for each training data set, different types of flight data can be put together. Different training data sets of training data can be obtained during the same test flight or during different test flights. In the latter case of different test flights, it is advantageous to obtain different training data sets of training data using the same vertical take-off and landing aircraft of the corresponding type of vertical take-off and landing aircraft. However, different training data sets of training data can also be obtained during different test flights of different vertical take-off and landing aircraft of the same type of vertical take-off and landing aircraft.

[0023] In all of these variants, for each training data set, reference output data corresponding to the expected output of the regressor during the flight of the vertical take-off and landing aircraft of the respective type under the respective flight conditions and the flight data of the respective training data set may be obtained or recorded simultaneously, respectively. However, the reference output data may also be obtained by calculation based on the flight data of the respective training data set.

[0024] Thus, for example, flight data and reference output data may be recorded by measurement during one or more test flights of a vertical take-off and landing aircraft of a particular type of vertical take-off and landing aircraft, after which the recorded flight data and reference output data may be used to calibrate the air data indicating device of each vertical take-off and landing aircraft, as well as to calibrate the air data indicating devices of other vertical take-off and landing aircraft of each type. In another example, flight data are recorded by measurement while reference output data are calculated from the flight data, or flight data are recorded by measurement during one or more test flights for approving a particular vertical take-off and landing aircraft, after which the recorded flight data and the recorded or calculated reference output data are used to calibrate the air data indicating device of each vertical take-off and landing aircraft.

[0025] The air data indicating device according to the invention and the method according to the invention for calibrating the air data indicating device have the following advantages: they enable to quickly provide a calibrated air data indicating device, which provides correct airspeed and altitude values ​​for all flight configurations and flight conditions, and has the accuracy required by regulatory specifications. Therefore, the solution according to the invention enables to improve the safety of the operation of the vertical take-off and landing aircraft, because it can provide the correct airspeed and altitude values ​​of the vertical take-off and landing aircraft to the pilot and the autopilot of the vertical take-off and landing aircraft in real time. In addition, the air data indicating device according to the invention and the method according to the invention for calibrating the air data indicating device according to the invention enable to design the vertical take-off and landing aircraft with a cheaper and safer design procedure, wherein only a small number of, or even no, re-arrangement iterations of the pitot tube device and the static pressure port are required. In addition, the solution according to the invention enables the pitot tube device and the static pressure port to be arranged closer to the fuselage of the vertical take-off and landing aircraft than with the known air data indicating device. It is avoided that the components protrude far from the fuselage, reducing the risk of injury to the aircraft operator. Furthermore, the solution of the present invention utilizes the existing pitot tube equipment and static pressure holes of each vertical take-off and landing aircraft, and can be easily implemented in existing vertical take-off and landing aircraft, wherein after test flights are conducted using each vertical take-off and landing aircraft to obtain training data, and after the artificial neural network is trained using the training data, the air data indicating device can be easily calibrated.

[0026] Preferably, the flight data includes roll attitude angle data, which includes roll attitude angle information of the vertical take-off and landing aircraft. The advantage is that the air data device can be calibrated more accurately using the method for calibrating the air data device. Since the roll attitude angle data includes the roll attitude angle information of the vertical take-off and landing aircraft, the roll attitude angle data can be obtained, for example, from an air data attitude and heading reference system (ADAHRS) of the vertical take-off and landing aircraft, specifically from a gyroscopic flight instrument or a micro-electrochemical system (MEMS) gyroscope.

[0027] Alternatively, however, the flight data does not include roll attitude angle data. This has the advantage that calibration of the air data unit is simpler and requires less computing power.

[0028] Advantageously, the flight data comprises sideslip angle data, which comprises information on the sideslip angle of the vertical take-off and landing aircraft. This has the advantage that the air data device can be calibrated more accurately using the method for calibrating the air data device. In a variant that enables more accurate calibration of the air data device, the flight data comprises: roll attitude angle data (including information on the roll attitude angle of the vertical take-off and landing aircraft), and sideslip angle data (including information on the sideslip angle of the vertical take-off and landing aircraft). Since the sideslip angle data comprises information on the sideslip angle of the vertical take-off and landing aircraft, the sideslip angle data can be obtained, for example, from a dedicated sensor. For example, a dedicated sideslip sensor can be used, which calculates the sideslip angle using the total pressure measured at two other static pressure ports (one pointing to the right side of the vertical take-off and landing aircraft and one pointing to the left side).

[0029] However, the flight data may not include sideslip angle data. This has the benefit of making the calibration of the air data unit simpler and requiring less computing power.

[0030] Preferably, the flight data comprises lateral acceleration data, which comprises information of the lateral acceleration of the vertical take-off and landing aircraft, specifically the amount of the lateral acceleration of the vertical take-off and landing aircraft. The advantage is that the air data device can be calibrated more accurately using the method for calibrating an air data device. Since the lateral acceleration data comprises information of the lateral acceleration of the vertical take-off and landing aircraft, the lateral acceleration data can be obtained, for example, from an air data attitude and heading reference system (ADAHRS) of the vertical take-off and landing aircraft, specifically from one or more accelerometers.

[0031] In a first variant, wherein the air data device can be calibrated more accurately, the flight data includes: roll attitude angle data including information about the roll attitude angle of the vertical take-off and landing aircraft; and lateral acceleration data including information about the lateral acceleration of the vertical take-off and landing aircraft, specifically the amount of the lateral acceleration of the vertical take-off and landing aircraft. In a second variant, wherein the air data device can also be calibrated more accurately, the flight data includes: lateral acceleration data including information about the lateral acceleration of the vertical take-off and landing aircraft, specifically the amount of the lateral acceleration of the vertical take-off and landing aircraft; and sideslip angle data including information about the sideslip angle of the vertical take-off and landing aircraft. In a third variant, wherein the air data device can be calibrated more accurately, the flight data includes: roll attitude angle data including information about the roll attitude angle of the vertical take-off and landing aircraft; sideslip angle data including information about the sideslip angle of the vertical take-off and landing aircraft; and lateral acceleration data including information about the lateral acceleration of the vertical take-off and landing aircraft, specifically the amount of the lateral acceleration of the vertical take-off and landing aircraft.

[0032] Alternatively, however, there is no lateral acceleration data in the flight data. The benefit is that the calibration of the air data unit is simpler and requires less computing power.

[0033] Advantageously, a pitot-static system comprises an air data indicating device according to the present invention, a pitot tube apparatus and a static pressure port.

[0034] Preferably, a vertical take-off and landing (VTOL) aircraft, in particular a helicopter, comprises the air data indicating device according to the present invention. The VTOL aircraft advantageously further comprises a pitot tube device and a static pressure port. In this case, the VTOL aircraft advantageously comprises the aforementioned pitot-static system, which comprises the air data indicating device according to the present invention. However, alternatively, the VTOL aircraft has neither a pitot tube device nor a static pressure port. In either case where the VTOL aircraft comprises the air data indicating device according to the present invention, the VTOL aircraft advantageously further comprises a display for displaying the airspeed of the VTOL aircraft based on the airspeed information of the VTOL aircraft received from the air data indicating device, and for displaying the altitude of the VTOL aircraft based on the altitude information of the VTOL aircraft received from the air data indicating device.

[0035] In an alternative to these variants, however, the air data indicating device according to the invention is separated from the mentioned pitot-static system and from the mentioned vertical take-off and landing aircraft.

[0036] If the vertical take-off and landing aircraft is an unmanned aircraft, the air data indicating device is advantageously part of a combination of the vertical take-off and landing aircraft and a remote control for controlling the vertical take-off and landing aircraft. In this case, the air data indicating device can be arranged, for example, in the vertical take-off and landing aircraft or in the remote control. In the latter case, the air data indicating device is separated from the vertical take-off and landing aircraft because it is arranged in the remote control.

[0037] Alternatively, the air data indicating device may be produced and sold completely independently of the vertical take-off and landing aircraft and independently of any remote controller. Thus, the air indicating device may be suitable for being arranged in a vertical take-off and landing aircraft, or may be suitable for being arranged in a remote controller, for example.

[0038] Preferably, in the method for calibrating an air data indicating device, in each training data set, reference output data corresponding to the expected output of the regressor of the type of vertical take-off and landing aircraft during flight under the respective flight conditions are obtained from one or more reference sensors of the vertical take-off and landing aircraft of the type of vertical take-off and landing aircraft during flight under the respective flight conditions. This has the advantage that the reference output data can be obtained in a reliable and easy to understand manner. The one or more reference sensors are advantageously calibrated sensors arranged on the vertical take-off and landing aircraft. Thus, the one or more reference sensors can be sensors arranged on the vertical take-off and landing aircraft, which are only used to obtain reference output data during the test flight when flying under the respective flight conditions. After the test flight is over, the one or more reference sensors can be removed from the vertical take-off and landing aircraft. However, in one variant, the one or more reference sensors are permanently installed on the vertical take-off and landing aircraft.

[0039] It is immaterial whether the reference output data is identical to the data output by one or more reference sensors, or whether the reference output data is calculated from the data output by one or more reference sensors. In either case, the one or more reference sensors may be arranged, for example, on a nose boom of the vertical take-off and landing aircraft, or on a trailing bomb towed behind the vertical take-off and landing aircraft during a test flight, to obtain the reference output data. Such a nose boom and such a trailing bomb both enable the one or more reference sensors to be arranged at a position away from the vertical take-off and landing aircraft fuselage, so that they provide data that are as accurate as possible to obtain the reference output data. Therefore, when the one or more reference sensors are calibration sensors, the data obtained are particularly accurate.

[0040] Depending on the desired output of the regressor during vertical take-off and landing aircraft flight of the vertical take-off and landing aircraft type under the respective flight conditions, the reference output data may be obtained, for example, from airspeed and pressure altitude sensors that have been calibrated to include the effects of wind and turbulence, from dynamic pressure and static pressure altitude sensors that have been calibrated to include the effects of wind and turbulence, from total pressure and static pressure altitude sensors that have been calibrated to include the effects of wind and turbulence, or from ground speed and climb rate sensors such as GPS and inertial units.

[0041] Alternatively, however, the reference output data is calculated or otherwise obtained by flight data based on the respective training data sets. For example, the reference output data may be obtained by calibrating the flight data using a GPS calibration method as described by Denis Hamel and Alex Kolarich in Vertical Flight Society's 76 th Annual Forum & Technology Display, Oct 06-08, 2020, Virtual presentation of the article "GPS-BASED Airspeed Calibration for Rotocraft: Generalized Application for All Flight Regimes".

[0042] Advantageously, for at least one flight condition in the list of flight conditions, the training data comprises at least one training data set associated with the respective flight condition, wherein the list of flight conditions comprises level flight at a first level flight speed, climb at a first climb rate and a first climb flight speed, and descent at a first descent rate and a first descent flight speed. Thus, in a variant of vertical climb, the first climb flight speed is 0 knots. Furthermore, in a variant of vertical descent, the first descent flight speed is 0 knots. More advantageously, for each of at least two flight conditions in the list of flight conditions, the training data comprises at least one training data set associated with the respective flight condition. Even more advantageously, for each of at least three flight conditions in the list of flight conditions, the training data comprises at least one training data set associated with the respective flight condition. Thus, the more different the flight conditions in the list of flight conditions associated with the training data comprising at least one training data set, the more accurately the air data indicating device can be calibrated.

[0043] Advantageously, the flight condition list also includes level flight at a second level flight speed, wherein the second level flight speed is greater than the first level flight speed. Therefore, the training data advantageously includes at least two training data sets, wherein one training data set is related to the flight condition level flight at the first level flight speed, and wherein the other training data set is related to the flight condition level flight at the second level flight speed. This has the advantage that the air data indicating device can be calibrated more accurately. If the first level flight speed and the second level flight speed are substantially equidistant (e.g., 100 knots and 200 knots), the accuracy can be further improved. However, the first level flight speed and the second level flight speed may also be unequally spaced.

[0044] Alternatively, the flight condition list does not include level flight at a second level flight speed, wherein the second level flight speed is greater than the first level flight speed.

[0045] Advantageously, the flight condition list also includes a climb performed at a second climb rate and a first climb flight speed, wherein the second climb rate is greater than the first climb rate. Therefore, the training data advantageously includes at least two training data sets, wherein one training data set is associated with a flight condition climb at a first climb rate at a first climb flight speed, and wherein another training data set is associated with a flight condition climb at a second climb rate at the first climb flight speed. This has the advantage that the air data indicating device can be calibrated more accurately. If the first climb rate and the second climb rate are substantially equidistant (e.g., 500 feet per minute and 1,000 feet per minute), the accuracy can be further improved. However, the first climb rate and the second climb rate may also be unequally spaced.

[0046] The flight condition list advantageously includes a climb at a first climb rate and a second climb flight speed, wherein the second climb flight speed is greater than the first climb flight speed. Therefore, the training data advantageously includes at least two training data sets, wherein one training data set is associated with a flight condition climb at a first climb rate at a first climb flight speed, and wherein another training data set is associated with a flight condition climb at the first climb rate at a second climb flight speed. This has the advantage that the air data indicating device can be calibrated more accurately. If the first climb flight speed and the second climb flight speed are substantially equidistant (e.g., 50 knots and 100 knots), the accuracy can be further improved. However, the first climb flight speed and the second climb flight speed may also be unequally spaced.

[0047] Advantageously, the flight condition list also includes a climb performed at a second climb rate and a second climb flight speed. This has the advantage that the air data indicating device can be calibrated more accurately. This accuracy can be further improved if the first climb flight speed and the second climb flight speed are substantially equidistant (e.g., 50 knots and 100 knots). However, the first climb flight speed and the second climb flight speed may also be unequally spaced.

[0048] Alternatively, the flight condition list does not include a climb at a second climb rate, wherein the second climb rate is greater than the first climb rate.

[0049] The flight condition list advantageously further includes a descent at a second descent rate and a first descent flight speed, wherein the second descent rate is greater than the first descent rate. Therefore, the training data advantageously includes at least two training data sets, wherein one training data set is associated with a descent in flight conditions at a first descent rate at a first descent flight speed, and wherein another training data set is associated with a descent in flight conditions at a second descent rate at the first descent flight speed. This has the advantage that the air data indicating device can be calibrated more accurately. If the first descent rate and the second descent rate are substantially equidistant (e.g., 700 feet per minute and 1400 feet per minute), the accuracy can be further improved. However, the first descent rate and the second descent rate may also be unequally spaced.

[0050] The flight condition list advantageously further includes a descent at a third descent rate and a first descent flight speed, wherein the third descent rate is greater than the second descent rate. Therefore, the training data advantageously includes at least three training data sets, wherein one training data set is associated with a descent at a first descent rate and a first descent flight speed, wherein another training data set is associated with a descent at a second descent rate and a first descent flight speed, and wherein another training data set is associated with a descent at a third descent rate and a second descent flight speed. Such a benefit is that the air data indicating device can be calibrated more accurately. If the first descent rate, the second descent rate, and the third descent rate are substantially equidistant (e.g., 700 feet / minute, 1400 feet / minute, and 2100 feet / minute), the accuracy can be further improved. However, the first descent rate, the second descent rate, and the third descent rate may also be unequally spaced.

[0051] The flight condition list advantageously includes a descent at a first descent rate and a second descent flight speed, wherein the second descent flight speed is greater than the first descent flight speed. Therefore, the training data advantageously includes at least two training data sets, one of which is associated with a descent in flight conditions at a first descent rate at a first descent flight speed, and another of which is associated with a descent in flight conditions at a first descent rate at a second descent flight speed. This has the advantage that the air data indicating device can be calibrated more accurately. If the first descent flight speed and the second descent flight speed are substantially equidistant (e.g., 50 knots and 100 knots), the accuracy can be further improved. However, the first descent flight speed and the second descent flight speed may also be unequally spaced.

[0052] The flight condition list advantageously further includes a descent at a second descent rate and a second descent flight speed. This has the advantage that the air data indicator can be calibrated more accurately. If the first descent flight speed and the second descent flight speed are substantially equidistant (e.g., 50 knots and 100 knots), the accuracy can be further improved. However, the first descent flight speed and the second descent flight speed may also be unequally spaced.

[0053] The flight condition list advantageously further includes a descent at a third descent rate and a second descent flight speed, wherein the third descent rate is greater than the second descent rate. Therefore, the training data advantageously includes at least three training data sets, wherein one training data set is associated with a descent under a flight condition at a first descent rate and a second descent flight speed, wherein another training data set is associated with a descent under a flight condition at a second descent rate and a second descent flight speed, wherein yet another training data set is associated with a descent under a flight condition at a third descent rate and a second descent flight speed. This has the advantage that the air data indicating device can be calibrated more accurately.

[0054] It is particularly advantageous that the training data advantageously includes at least six training data sets, one of which is related to a flight condition descent at a first descent rate and a first descent flight speed, one of which is related to a flight condition descent at a second descent rate and a first descent flight speed, one of which is related to a flight condition descent at a third descent rate and a first descent flight speed, one of which is related to a flight condition descent at a first descent rate and a second descent flight speed, one of which is related to a flight condition descent at a second descent rate and a second descent flight speed, and one of which is related to a flight condition descent at a third descent rate and a second descent flight speed. This has the advantage that the air data indicating device can be calibrated more accurately.

[0055] However, in one variant, the list of flight conditions does not include descending at a third descent rate, wherein the third descent rate is greater than the second descent rate.

[0056] Independently of the descent flight speed, if the list of flight conditions includes a descent with a second descent rate or even a descent with a third descent rate, the flight condition as a descent with a maximum descent rate is advantageously associated with a power-free descent (sometimes also called an autorotation descent), while the other one or more other flight conditions as a descent with a descent rate are associated with a powered descent.

[0057] Alternatively, the flight condition list does not include descending at a second descent rate, wherein the second descent rate is greater than the first descent rate. In addition, at the second descent flight speed, the flight condition list can be implemented without any descent. Advantageously, the above-mentioned first level flight speed, second level flight speed, first climb rate, second climb rate, first climb flight speed, second climb flight speed, first descent rate, second descent rate and third descent rate, first descent flight speed and second descent flight speed are constants. However, as described below, one or more of the first level flight speed, second level flight speed, first climb rate, second climb rate, first climb flight speed, second climb flight speed, first descent rate, second descent rate, third descent rate, first descent flight speed and second descent flight speed can change over time when acceleration in either direction is applied to simulate one of the corresponding flight configurations described below.

[0058] Preferably, each training data set is associated with a flight configuration and comprises flight data obtained during flight in the respective flight configuration and flight conditions, each training data set being associated with flight conditions of a vertical take-off and landing aircraft of a respective type of vertical take-off and landing aircraft for which the air data indicating device is to be calibrated, wherein the training data comprises at least one training data set associated with at least one of the following list of flight configurations: intermediate center of gravity, longitudinal fully forward center of gravity, longitudinal fully aft center of gravity, longitudinal slightly forward center of gravity, longitudinal slightly aft center of gravity.

[0059] Thus, each training data set is advantageously associated with one flight condition and one flight configuration. Thus, the flight condition is advantageously one of the above-mentioned list of flight conditions, and the flight configuration is advantageously one of the above-mentioned list of flight configurations.

[0060] Advantageously, for each of the at least two flight configurations in the flight configuration list, the training data comprises at least one training data set associated with the respective flight configuration. More advantageously, for each of the at least three flight configurations in the flight configuration list, the training data comprises at least one training data set associated with the respective flight configuration. Even more advantageously, for each of the at least four flight configurations in the flight configuration list, the training data comprises at least one training data set associated with the respective flight configuration. Most advantageously, for each flight configuration in the flight configuration list, the training data comprises at least one training data set associated with the respective flight configuration.

[0061] In a more advantageous variant, for each of at least two flight configurations in the flight configuration list, the training data comprises at least one training data set associated with the respective flight condition and associated with the respective flight configuration. More advantageously, for each of at least three flight configurations in the flight configuration list, the training data comprises a training data set associated with the respective flight condition and associated with the respective configuration. Even more advantageously, for each of at least four flight configurations in the flight configuration list, the training data comprises at least one training data set associated with the respective flight condition and associated with the respective flight configuration. Most advantageously, for each flight condition of each flight configuration in the flight configuration list, the training data comprises at least one training data set associated with the respective flight condition and the respective configuration.

[0062] If the flight configuration is an intermediate CG, the VTOL aircraft may be physically configured in an intermediate CG configuration, or the VTOL aircraft may be physically configured in a different configuration, such as a slightly aft CG configuration, and simulated flying the intermediate CG configuration at a constant forward acceleration with a pitch attitude angle equal to the intermediate CG configuration. This simulation of the intermediate CG configuration may be achieved in all of the flight conditions in the above flight condition list.

[0063] If the flight configuration is a longitudinal full forward CG, the VTOL aircraft may be physically configured in a longitudinal full forward CG configuration, or the VTOL aircraft may be physically configured in a different configuration, such as an intermediate CG configuration, and simulated flying a longitudinal full forward CG at a constant forward acceleration with a pitch attitude angle equal to the full forward CG configuration. This simulation of a longitudinal full forward CG configuration may be achieved in all of the flight conditions listed above.

[0064] If the flight configuration is a longitudinal full aft CG, the VTOL aircraft may be physically configured in a longitudinal full aft CG configuration, or the VTOL aircraft may be physically configured in a different configuration, such as an intermediate CG configuration, and simulated flying a longitudinal full aft CG at a constant aft acceleration to a pitch attitude angle equal to the full aft CG configuration. This simulation of a longitudinal full aft CG configuration may be achieved in all of the flight conditions listed above.

[0065] If the flight configuration is a longitudinal slightly forward center of gravity, the vertical takeoff and landing aircraft may be physically configured in a longitudinal slightly forward center of gravity configuration, or the vertical takeoff and landing aircraft may be physically configured in a different configuration, such as an intermediate center of gravity configuration, and simulated flight with a longitudinal slightly forward center of gravity at a constant forward acceleration such that the pitch attitude angle is equal to the slightly forward center of gravity configuration. This simulation of a longitudinal slightly forward center of gravity configuration may be achieved in all flight conditions in the above list of flight conditions.

[0066] If the flight configuration is a longitudinal slightly aft CG, the VTOL aircraft may be physically configured in a longitudinal slightly aft CG configuration, or the VTOL aircraft may be physically configured in a different configuration, such as an intermediate CG configuration, and simulated flying with a longitudinal slightly aft CG at a constant aft acceleration to achieve a pitch attitude angle equal to the slightly aft CG configuration. This simulation of a longitudinal slightly aft CG configuration may be achieved in all of the flight conditions listed above.

[0067] Simulating one flight configuration of the flight configuration list while physically configuring the vertical take-off and landing aircraft to another flight configuration of the flight configuration list has the advantage that training data sets related to both flight configurations can be collected in the same test flight. Therefore, it is particularly advantageous to obtain or record training data respectively when physically configuring the vertical take-off and landing aircraft to one flight configuration of the flight configuration list (for example, the center of gravity intermediate configuration) while simulating other flight configurations of the flight configuration list, so as to obtain or record training data sets related to other flight configurations in the flight configuration list other than the flight configuration physically configured for the vertical take-off and landing aircraft.

[0068] However, as an alternative to these variants, the training data may only include a training data set related to one flight configuration, in particular to one flight configuration of the list of flight configurations.

[0069] Advantageously, the regressor is a neural network regressor, in particular a fully connected neural network regressor, comprising an output layer.

[0070] Advantageously, the neural network regressor is a fully connected feed-forward neural network regressor. This has the advantage that the neural network regressor is easier to operate because information is only propagated forward in the network. However, in an alternative embodiment, the neural network regressor is a recurrent neural network regressor.

[0071] Advantageously, the output layer has a hyperbolic tangent (Tanh) transfer function. This has the advantage that the output of the transfer function provides a value between -1 and +1, so that a penalty can be imposed on the node instead of just not triggering the node. This provides a larger output range, thereby making the calibration of the air data indicating device more accurate. In addition, the derivative of the hyperbolic tangent (Tanh) is easy to calculate.

[0072] Alternatively, however, the output layer has a transfer function other than hyperbolic tangent (Tanh).

[0073] Advantageously, the regressor comprises at least two hidden layers. This has the advantage that the air data indicating device can be calibrated more accurately than if the regressor only comprises one hidden layer, or even no hidden layer.

[0074] However, alternatively, the regressor may include only one hidden layer or no hidden layers.

[0075] Preferably, the at least two hidden layers each contain at least 32 neurons, more preferably at least 60 neurons, and most preferably at least 100 neurons. By at least two hidden layers, each containing at least 32 neurons, a good calibration of the air data indicating device can be achieved. However, the more neurons each of the at least two hidden layers contains, the more accurate the calibration that can be achieved by the air data indicating device. However, the more neurons each of the at least two hidden layers contains, the greater the computing power required to calibrate the air data indicating device. Therefore, advantageously, at least two hidden layers each contain less than 300 neurons. Nevertheless, alternatively, at least two hidden layers can each contain less than 32 neurons, 300 neurons, or even more than 300 neurons.

[0076] Preferably, the first hidden layer of the at least two hidden layers has a Relu transfer function. This has the advantage that it enables reliable calibration of the air data indicating device while requiring relatively little computing power.

[0077] Advantageously, each of the at least two hidden layers, except for the last hidden layer of the at least two hidden layers, has a Relu transfer function. This has the advantage that it enables reliable calibration of the air data indicating device while requiring relatively little computational power. This advantage is particularly evident when the regressor comprises more than two hidden layers.

[0078] Advantageously, each of the at least two hidden layers has a Relu transfer function. This has the advantage that the air data indicating device can be reliably calibrated while requiring relatively little computing power. However, in a variant, the last of the at least two hidden layers has a continuously distinguishable transfer function (particularly a Tanh transfer function). This has the advantage that a more accurate calibration of the air data indicating device can be achieved.

[0079] In all the above variants with Relu transfer function, a transfer function different from Relu transfer function may be used. For example, in the above variants with Relu transfer function, the transfer function is Gelu transfer function or SiLu transfer function instead of Relu transfer function.

[0080] Advantageously, in each training data set, each type of flight data (e.g., pitot tube data, static pressure port data, etc.) is a value obtained by filtering a data stream of flight data of the respective type having a length of at least 0.5 seconds, particularly advantageously at least 1 second, and more advantageously at least 2 seconds measured under respective flight conditions and respective flight configurations (if applicable). This has the advantage that each training data set contains reliable and representative numbers of each type of flight data, and the flight data represents the flight conditions and flight configurations associated with the respective training data sets. In preferred variants of these variants, in each training data set, each type of flight data (e.g., pitot tube data, static pressure port data, etc.) is a value obtained by filtering a data stream of flight data of the respective type having a length of 10 seconds or less measured under respective flight conditions and respective flight configurations (if applicable).

[0081] Therefore, when filtering the data stream to obtain the corresponding value of the respective type of flight data, in one example, the filter used is the average value of the data stream of the respective type of flight data calculated by the filter length of the data stream. In another example, the filter used is a low-pass filter for the data stream of the respective type of flight data at the filter length of the data stream, wherein the output value of the low-pass filter is, for example, 2 Hz.

[0082] In one alternative, in each training data set, each type of flight data (e.g., pitot tube data, static pressure port data, etc.) is a value obtained by filtering a data stream of flight data of a respective type having a length of less than 0.5 seconds or greater than 10 seconds measured under respective flight conditions and respective flight configurations (if applicable). In another alternative, each of the training data sets does not include a value obtained by filtering a data stream of the respective type of flight data for each type of flight data.

[0083] Advantageously, the calibration is verified using further training data. This has the advantage that the safety of the calibration can be controlled. To achieve this, advantageously approximately 80% to 90% of the training data is used for calibration, while the remaining approximately 20% to 10% of the training data is used for verification.

[0084] Alternatively, however, the method does not require such verification.

[0085] Further advantageous embodiments and feature combinations emerge from the following detailed description and from the entire claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] The accompanying drawings used to explain the embodiments show:

[0087] Figure 1 is a simplified schematic diagram of a pitot-static system of a vertical take-off and landing (VTOL) aircraft (specifically a helicopter), which is used to indicate the airspeed and altitude of the vertical take-off and landing aircraft to the pilot of the vertical take-off and landing aircraft, and the pitot-static system includes an air data indicating device according to the present invention,

[0088] Figure 2 is a simplified schematic side view of the front part of a helicopter as an example of a vertical take-off and landing aircraft having an air data indicating device according to the present invention,

[0089] Figure 3a , Figure 3b are data recorded during two test flights of the helicopter, from which training data can be obtained for calibrating the air data indicating device of the invention according to the method of the invention,

[0090] Figure 4 data recorded during the third test flight for verifying the calibration of the air data indicating device according to the present invention, and

[0091] Figure 5 Detailed views of data during three flight maneuvers performed during the third test flight are provided to illustrate in more detail the operation of the method of the invention and the air data indicating device of the invention.

[0092] In the drawings, the same components are provided with the same reference numerals.

[0093] Preferred Implementation

[0094] Figure 1A simplified schematic diagram of a pitot-static system 100 for a vertical take-off and landing (VTOL) aircraft (specifically a helicopter) is shown, which is used to indicate the airspeed of the VTOL aircraft and the altitude of the VTOL aircraft to the pilot of the VTOL aircraft. The pitot-static system 100 includes a pitot tube device 51, which is used to determine the stagnation air pressure at the position of the pitot tube device 51, and provide pitot tube data including the stagnation air pressure information at the position of the pitot tube device 51. In addition, the pitot-static system 100 includes a static pressure hole device 52, which is used to determine the static air pressure at the position of the static pressure hole device 52, and provide static pressure hole data including the static air pressure information at the position of the static pressure hole device 52. In addition, the pitot-static system 100 includes the air data indicating device 1 for a vertical take-off and landing aircraft (specifically a helicopter) of the present invention, which is used to provide airspeed information about the VTOL aircraft, and provide altitude information about the VTOL aircraft. The pitot-static system 100 further includes a display 101 for displaying the airspeed of the vertical take-off and landing aircraft and the altitude of the vertical take-off and landing aircraft, thereby indicating the airspeed and altitude of the vertical take-off and landing aircraft to the pilot of the vertical take-off and landing aircraft.

[0095] When the pitot-static system 100 is applied to a vertical take-off and landing aircraft, it is incorporated into the air data attitude and heading reference system (ADAHRS) of the vertical take-off and landing aircraft. Thus, the pitot tube device 51 and the static hole device 52 of the pitot-static system 100 are installed on the vertical take-off and landing aircraft, and thus belong to the vertical take-off and landing aircraft. In addition, the display 101 is also arranged to display the airspeed and altitude of the vertical take-off and landing aircraft to the pilot of the vertical take-off and landing aircraft. Therefore, if the pilot should sit in the cockpit of the vertical take-off and landing aircraft, the display 101 is arranged in the cockpit of the vertical take-off and landing aircraft, and therefore belongs to the vertical take-off and landing aircraft. However, in the case where the vertical take-off and landing aircraft can be remotely controlled, the display 101 can be arranged in a remote controller for controlling the vertical take-off and landing aircraft. In this case, the display belongs to the remote controller.

[0096] When the pitot-static system 100 is applied to a vertical take-off and landing aircraft, the air data indicating device 1 is connected to the pitot tube device 51 for receiving the pitot tube data provided by the pitot tube device 51, and is connected to the static port device 52 for receiving the static port data provided by the static port device 52. In addition, the air data indicating device 1 is connected to the display 101 for providing the airspeed information of the vertical take-off and landing aircraft and the altitude information of the vertical take-off and landing aircraft to the display 101, so as to be displayed to the pilot through the display 101. Therefore, the air data indicating device 1 can be arranged in the vertical take-off and landing aircraft, for example, and thus become a part of the vertical take-off and landing aircraft, or, in the case where the vertical take-off and landing aircraft is remotely controllable, the air data indicating device 1 can be arranged in the remote controller. In either case, if the vertical take-off and landing aircraft is provided with an autopilot to make the vertical take-off and landing aircraft fly automatically, the air data indicating device 1 is connected to the autopilot to provide the autopilot of the vertical take-off and landing aircraft with information about the airspeed of the vertical take-off and landing aircraft and information about the altitude of the vertical take-off and landing aircraft.

[0097] The air data indicating device 1 of the present invention can be produced and sold separately from the vertical take-off and landing aircraft and the pitot-static system 100. However, since the air data indicating device 1 can be a part of the vertical take-off and landing aircraft and can also be a part of the above-mentioned pitot-static system 100, the air data indicating device 1 can be connected to the pitot tube device 51 to receive the pitot tube data provided by the pitot tube device 51, and can be connected to the static pressure hole device 52 to receive the static pressure hole data provided by the static pressure hole device 52.

[0098] According to the present invention, the air data indicating device 1 includes an airspeed and altitude determination module 2. The airspeed and altitude determination module 2 is suitable for determining the airspeed of the vertical take-off and landing aircraft and the altitude of the vertical take-off and landing aircraft in real time according to the flight data using the regressor 3 obtained by training the artificial neural network through training data. In one example, the airspeed and altitude determination module 2 is a computer program product running on a computing unit (such as a control computer of the vertical take-off and landing aircraft, or another computing unit separated from the control computer of the vertical take-off and landing aircraft). In another example, the airspeed and altitude determination module 2 is a computing unit (such as a computer on the vertical take-off and landing aircraft, or a computer included in a remote controller), which is suitable for determining the airspeed of the vertical take-off and landing aircraft and the altitude of the vertical take-off and landing aircraft in real time according to the flight data using the regressor 3 obtained by training the artificial neural network through training data.

[0099] The flight data at least includes: pitot tube data, static pressure port data, vertical speed data including vertical speed information of the vertical take-off and landing aircraft, and pitch attitude angle data including pitch attitude angle information of the vertical take-off and landing aircraft.

[0100] Since the pitot tube data includes the stagnation pressure information at the position of the pitot tube device 51, the pitot tube data can be, for example, the stagnation pressure measured by the pitot tube device 51 and output by the pitot tube device 51 and expressed in arbitrary units, an uncalibrated wind speed calculated based on the measured stagnation pressure and the measured static pressure, or a pre-calibrated wind speed. The pre-calibrated airspeed can be, for example, an uncalibrated airspeed calibrated by using a known position calibration in a lookup table.

[0101] Since the static pressure hole data includes the static air pressure information at the location of the static pressure hole device 52, the static pressure hole data may be, for example, the static air pressure measured by the static pressure hole device 52 and expressed in arbitrary units and output by the static pressure hole device 52, an uncalibrated height calculated based on the measured static air pressure, or a pre-calibrated height. The pre-calibrated height may be, for example, an uncalibrated height calibrated using a known position calibration in a lookup table.

[0102] Since the vertical speed data includes vertical speed information of the vertical take-off and landing aircraft, the vertical speed data can be obtained from the static port data, for example, by using the change in the value of the static port data over time. For example, this can be the change in the value of the static air pressure measured by the static port device 52 and output by the static port device 52 over time (expressed in arbitrary units), the change in the uncalibrated altitude calculated based on the measured static air pressure over time, or the change in the pre-calibrated altitude over time. In either case, this can be the change within each predefined time unit.

[0103] Since the pitch attitude angle data includes the pitch attitude angle information of the vertical take-off and landing aircraft, the pitch attitude angle data can be obtained, for example, from the air data attitude and heading reference system (ADAHRS) of the vertical take-off and landing aircraft, specifically from the gyroscopic flight instrument or the micro-electrochemical system (MEMS) gyroscope. In order to receive the pitch attitude angle data, the flight data indicating device 1 can be advantageously connected to a pitch attitude angle data providing unit that provides the pitch attitude angle data. The pitch attitude angle data providing unit can, for example, be a gyroscopic flight instrument or a micro-electrochemical system (MEMS) gyroscope. However, the pitch attitude angle data providing unit can also be a computer, which receives the pitch attitude angle data from another unit or the mentioned gyroscopic flight instrument or the micro-electrochemical system (MEMS) gyroscope, respectively. Therefore, the pitch attitude angle data providing unit can, for example, become a part of the air data attitude and heading reference system (ADAHRS) of the vertical take-off and landing aircraft.

[0104] In one variant, the flight data also includes roll attitude angle data, which includes information about the roll attitude angle of the vertical take-off and landing aircraft. Since the roll attitude angle data includes the roll attitude angle information of the vertical take-off and landing aircraft, the roll attitude angle data can be obtained, for example, from the air data attitude and heading reference system (ADAHRS) of the vertical take-off and landing aircraft, specifically from a gyroscopic flight instrument or a micro-electrochemical system (MEMS) gyroscope. In order to receive the roll attitude angle data, the flight data indicating device is advantageously connectable to a roll attitude angle data providing unit that provides the roll attitude angle data. Therefore, the roll attitude angle data providing unit can be the same unit as the pitch attitude angle data providing unit mentioned above, or can be separate from the pitch attitude angle data providing unit mentioned above. The roll attitude angle data providing unit can, for example, be a gyroscopic flight instrument or a micro-electrochemical system (MEMS) gyroscope. However, the roll attitude angle data providing unit can also be a computer, which receives the roll attitude angle data from another unit or the gyroscopic flight instrument or micro-electrochemical system (MEMS) gyroscope mentioned above. Thus, the roll attitude angle data providing unit may, for example, become a part of an Air Data Attitude and Heading Reference System (ADAHRS) of a vertical take-off and landing aircraft.

[0105] In a further variant, the flight data also includes sideslip angle data, which includes information about the sideslip angle of the vertical take-off and landing aircraft. In a variant that enables more accurate calibration of the air data device, the flight data includes: roll attitude angle data (including information about the roll attitude angle of the vertical take-off and landing aircraft), and sideslip angle data (including information about the sideslip angle of the vertical take-off and landing aircraft). Since the sideslip angle data includes information about the sideslip angle of the vertical take-off and landing aircraft, the sideslip angle data can be obtained from a dedicated sensor, for example. For example, a dedicated sideslip sensor can be used, which uses the total pressure measured at two other static pressure holes (one pointing to the right side of the vertical take-off and landing aircraft and one pointing to the left side) to calculate the sideslip angle.

[0106] In yet another variant, the flight data further comprises lateral acceleration data, which comprises information on the lateral acceleration of the vertical take-off and landing aircraft, in particular the amount of the lateral acceleration of the vertical take-off and landing aircraft. Since the lateral acceleration data comprises information on the lateral acceleration of the vertical take-off and landing aircraft, the lateral acceleration data can be obtained, for example, from an Air Data Attitude and Heading Reference System (ADAHRS) of the vertical take-off and landing aircraft, in particular from one or more accelerometers. In order to receive the lateral acceleration data, the flight data indicating device is advantageously connectable to a lateral acceleration data providing unit that provides the lateral acceleration data.

[0107] In a variant enabling a more accurate calibration of the air data device, the flight data comprises: roll attitude angle data comprising information on the roll attitude angle of the vertical take-off and landing aircraft, and lateral acceleration data comprising information on the lateral acceleration of the vertical take-off and landing aircraft, in particular the amount of the lateral acceleration of the vertical take-off and landing aircraft. In a further variant, wherein the air data device can also be calibrated more accurately, the flight data comprises: lateral acceleration data comprising information on the lateral acceleration of the vertical take-off and landing aircraft, in particular the amount of the lateral acceleration of the vertical take-off and landing aircraft; and sideslip angle data comprising information on the sideslip angle of the vertical take-off and landing aircraft. In a third variant, wherein the air data device can be calibrated more accurately, the flight data comprises: roll attitude angle data comprising information on the roll attitude angle of the vertical take-off and landing aircraft; sideslip angle data comprising information on the sideslip angle of the vertical take-off and landing aircraft; and lateral acceleration data comprising information on the lateral acceleration of the vertical take-off and landing aircraft, in particular the amount of the lateral acceleration of the vertical take-off and landing aircraft.

[0108] Figure 2 A simplified schematic side view of the front of a helicopter 50 as an example of a vertical take-off and landing aircraft having an air data indicating device 1 of the present invention is shown. The helicopter 50 is equipped with a pitot-static system 100 and thus includes the air data indicating device 1 of the present invention. Therefore, a pitot tube device 51 is installed on the right side of the front of the helicopter 50, and static pressure hole devices 52 are installed on the left and right sides of the front of the helicopter. These static pressure hole devices 52 are interconnected. The pitot tube device 51 and the static pressure hole device 52 are arranged and positioned in a manner known in the art. The pitot tube device 51 is used to determine the stagnation air pressure at the location of the pitot tube device 51 and provide pitot tube data including stagnation air pressure information at the location of the pitot tube device 51. The interconnected static pressure hole device 52 is used to determine the static air pressure at the location of the static pressure hole device 52 and provide static pressure hole data including static air pressure information at the location of the static pressure hole device 52. The air data indicating device 1 is connected to the pitot tube device 51 for receiving the pitot tube data provided by the pitot tube device 51, and is connected to the static pressure hole device 52 for receiving the static pressure hole data provided by the static pressure hole device 52. Furthermore, the air data indicating device 1 is adapted to derive vertical speed data including helicopter vertical speed information from the static port data by determining changes in the static port data over time.

[0109] The helicopter 50 further comprises an air data attitude and heading reference system (ADAHRS) 56 known in the art. The air data indicating device 1 is connected to the ADAHRS 56 for receiving pitch attitude angle data determined and provided by the ADAHRS 56 .

[0110] In the helicopter 50, the air data indicating device 1 is connected to a display 101 ( Figure 2(not shown) for providing the airspeed information and altitude information of the helicopter 50 to the display 101, so as to display the airspeed and altitude to the pilot of the helicopter 50 through the display 101. In addition, the air data indicating device 1 is connected to the autopilot of the helicopter 50, for providing the airspeed information and altitude information of the helicopter 50 to the autopilot. Therefore, Figure 2 The helicopter 50 shown may be flown by a pilot and autopilot using an air data indicating device 1 calibrated by the method of the present invention.

[0111] In order to obtain reference output data for training data during the test flight, the helicopter 50 is equipped with Figure 2 The nose boom 53 is shown. At the front end of the nose boom 53, a reference pitot tube device 54 and a reference static pressure hole device 55 are installed. Because the nose boom 53, the reference pitot tube device 54 and the reference static pressure hole device 55 are installed in a non-critical pressure field far away from the fuselage of the helicopter 50, the influence of the airflow and turbulence around the helicopter 50 is minimized, which will distort the stagnation pressure and static pressure measured using the reference pitot tube device 54 and the reference static pressure hole device 55. Based on the data obtained from the reference pitot tube device 54 and the reference static pressure hole device 55, a calibrated reference wind speed can be calculated in a manner known in the art, and based on the reference static pressure hole device 55, a calibrated reference static pressure can be calculated in a manner known in the art. Therefore, the calibrated reference wind speed and the calibrated reference static pressure are calibrated in a manner known in the art. Since the reference pitot tube device 54 and the reference static pressure port device 55 are arranged on the top of the nose boom 53, and since they are calibrated in a manner known in the art, they are known to provide values ​​within the accuracy required by regulatory specifications for all flight configurations and flight conditions. In addition to arranging the reference pitot tube device 54 and the reference static pressure port device 55 on the top of the nose boom 53, they can also be installed in the towed bomb to obtain reference output data. This will also provide reference output data that meets the accuracy required by regulatory specifications.

[0112] By performing two test flights on the helicopter 50, training data for training the neural network to obtain the regressor 3 and thus calibrate the air data indicating device 1 has been obtained. The data recorded during the two test flights, such as Figure 3a and 3bAs shown. The flight data of the training data includes: pitot tube data, static pressure port data, vertical speed data including vertical speed information of the helicopter 50, and pitch attitude angle data including pitch attitude angle information of the helicopter 50. These flight data have been obtained from the pitot tube device 51, the static pressure port device 52 and the ADAHRS 56 as described above. In the embodiment shown here, the flight data does not include roll attitude angle data, sideslip data and lateral acceleration data. When one, two or all three of the roll attitude angle data, sideslip data and lateral acceleration data are added to the flight data, the calibration of the air indicating device 1 is more accurate than that shown in this example.

[0113] Figure 3a 5 shows data recorded during the first of two test flights conducted by helicopter 50, and Figure 3b 1 shows data recorded during the second of two test flights conducted by helicopter 50, from which the training data were obtained. Figure 3a and 3b In the figure, six graphs show the data recorded during the respective test flights, which are related to the time (in seconds) of the respective test flights.

[0114] exist Figure 3a , Figure 3b , the top graph shows the uncalibrated airspeed (in knots) calculated using the pitot tube data and static port data obtained from the pitot tube device 51 and the static port device 52, and the formula is:

[0115]

[0116] where IAS is the uncalibrated airspeed shown in the figure, and p SSL is the standard sea level pressure p SSL =101325Pa,ρ SSL is the standard sea level air density ρ SSL =1.225kg / m 3 ,γ is the specific heat capacity ratio of air γ=1.4, p t_e is the uncalibrated stagnation pressure obtained from the Pitot tube device 51, p s_e is the uncalibrated static air pressure obtained from the static pressure hole device 52.

[0117] exist Figure 3a , Figure 3b In the figure, the second graph shows the vertical speed (in feet per minute) calculated based on the uncalibrated static air pressure. In addition, in these two figures, the third graph shows the pitch attitude angle data obtained from the ADAHRS 56, and the fourth graph shows the uncalibrated altitude (in feet) calculated based on the static air pressure obtained from the static pressure hole device 52. Therefore, the uncalibrated altitude can be calculated based on the static air pressure p obtained from the static pressure hole device 52.s_e Use the following formula to calculate:

[0118]

[0119] where p SSL Still the standard sea level pressure p SSL =101325Pa, and a is the standard sea level temperature lapse rate a=0.001982K / ft, g c =32.17Ibm / slug, g is the acceleration due to gravity g = 31.174049ft / sec 2 , and R = 96.0340 (ft·lbf) / (lbm·K).

[0120] exist Figure 3a , Figure 3b In the figure, the two bottommost graphs show the calibrated reference airspeed (in knots) and the calibrated reference altitude (in feet) obtained from the reference pitot tube device 54 and the reference static port device 55 on the nose boom 53 of the helicopter 50, respectively. The calibrated reference airspeed and the calibrated reference altitude are thus verified by the known GPS calibration method. In this GPS calibration method, ideally, GPS data recorded only in windless flights after air density correction are used as calibration data together with the vertical speed. However, in the present case, for windy conditions, the GPS quasi-static nose and tail wind method (quasi-static GPS) has been applied to eliminate the influence of wind. For example, the method is described in the originally mentioned publication, in the Vertical Flight Society's 76 th Annual Forum & Technology Display, Oct 06-08, 2020, Virtual presentation of the article "GPS-BASED Airspeed Calibration for Rotocraft: Generalized Application for All Flight Regimes".

[0121] During both test flights, the helicopter 50 was physically in an intermediate center of gravity configuration. During the test flights, the aircraft performed different maneuvers, such as level flight at different constant airspeeds, climbing at different constant climb rates, descending at different descent rates until unpowered descent in autorotation during flight. In addition, these maneuvers were performed at different forward accelerations and different rearward accelerations to simulate different flight configurations with different centers of gravity, until a longitudinal full forward center of gravity configuration and a longitudinal full rearward center of gravity configuration. In this way, the entire flight condition and flight configuration are completed. It should be noted that at least two equally spaced climb rates and at least three equally spaced descent rates are covered, where the fastest descent rate is an autorotation descent, while the slower descent rate is a powered descent flight.

[0122] from Figure 3a and Figure 3b In the data shown, a total of 6400 training data sets are automatically extracted. For each training data set, flight data and corresponding reference output data are extracted by averaging the data streams of each type of data that are longer than 2 seconds. Therefore, in each training data set, each type of flight data (i.e., pitot tube data, static pressure port data, vertical speed data, and pitch attitude angle data), as well as each type of reference output data (i.e., reference airspeed and reference static pressure) are all obtained by averaging and filtering the data streams of each type of flight data measured under respective flight conditions and respective flight configurations for a length of 2 seconds. Thus, the time windows of adjacent training data sets with a length of 2 seconds overlap by 50%. In addition to this example, the time window for averaging and filtering the data stream of each type of data can be selected to be a length different from 2 seconds. For example, the time window can be selected to be 0.5 seconds, 5 seconds, or 10 seconds. In addition, another filtering method (e.g., low-pass filtering) can be adopted instead of filtering the data stream of each type of data by averaging.

[0123] The training data is used to train the regressor 3 to calibrate the airspeed and altitude determination module 2, thereby calibrating the air data indicating device 1. The regressor 3 is a fully connected neural network regressor, including two hidden layers and an output layer. The transfer function of the two hidden layers is the Relu transfer function, and the transfer function of the output layer is the hyperbolic tangent (Tanh) function. The two hidden layers each contain 256 neurons. The regressor 3 for calculating the calibrated airspeed (CAS) can be expressed by the following formula:

[0124] CAS=Tanh(C3·Relu(C2·Relu(C1·X+I1)+I2)+I3),

[0125] Where C1, C2 and C3 are the weight matrices of the first hidden layer, the second hidden layer and the output layer respectively, and I1, I2 and I3 are the constant vectors of the first hidden layer, the second hidden layer and the output layer respectively.

[0126] By training the regressor 3 with the training data as described, the air data indicating device 1 is calibrated. The helicopter 50 performs a third test flight to verify the calibration of the air data indicating device 1. As a result, the helicopter 50 is physically in an intermediate center of gravity configuration again. During the test flight, the aircraft performs different maneuvers, such as level flight at different constant airspeeds, climbing at different constant climb rates, descending at different descent rates until unpowered descent in autorotation during flight. In addition, these maneuvers are performed at different forward accelerations and different backward accelerations to simulate different flight configurations with different centers of gravity, until a longitudinal full forward center of gravity configuration and a longitudinal full backward center of gravity configuration. In this way, the entire flight condition and flight configuration are completed.

[0127] Data recorded during this third test flight, such as Figure 4 Therefore, Figure 4 Six graphs are shown showing the data recorded during the third test flight versus the time (in seconds) of the third test flight, the configuration of which is Figure 3a and Figure 3b The top graph shows the uncalibrated airspeed (in knots) calculated from the pitot tube data and static port data obtained from the pitot tube device 51 and the static port device 52, calculated in the same manner as Figure 3a and Figure 3b In addition, the second graph shows the vertical speed (in feet per minute) calculated based on the uncalibrated static air pressure, while the third graph shows the pitch attitude angle data obtained from ADAHRS56, and the fourth graph shows the uncalibrated altitude (in feet) calculated based on the static air pressure obtained from the static pressure port device 52, which is calculated in the same manner as Figure 3a and Figure 3b The same method as shown in .

[0128] and Figure 3a , Figure 3b on the contrary, Figure 4The two bottom graphs show a comparison between airspeeds (in knots) determined in different ways, and a comparison between altitudes (in feet) determined in different ways, respectively. The dashed lines are the calibrated reference airspeed and the calibrated reference altitude (in feet) obtained from the reference pitot tube device 54 and the reference static port device 55 on the nose boom 53 of the helicopter 50, as known in the art. Therefore, these dashed lines correspond to the reference output data of the third test flight. It can be seen that the values ​​of these dashed lines fully meet the accuracy required by regulatory specifications. The dotted lines are the airspeed calibrated using the classical GPS-based calibration method known in the art, and the altitude calibrated using the classical GPS-based calibration method known in the art, both of which are calculated based on the pitot tube data from the pitot tube device 51 and the static port data from the static port device 52, and calibrated using a lookup table. Therefore, calibration was performed using the GPS-based calibration method, which is described in the originally mentioned publication, Denis Hamel and Alex Kolarich in Vertical Flight Society's 76 th Annual Forum & Technology Display, Oct 06-08, 2020, Virtual presented the article “GPS-BASED Airspeed Calibration for Rotocraft: Generalized Application for All Flight Regimes”. Therefore, the dotted line is used for comparison with the known classical calibration method. The solid line is the airspeed determined using the calibrated air data indicating device 1 and thereby with the aid of the trained regressor 3, and the altitude determined using the calibrated air data indicating device 1. Therefore, with the aid of the trained regressor 3, the solid line is determined as described above by flight data including the pitot tube data from the pitot tube device 51, the static pressure port data from the static pressure port device 52, the vertical speed data, and the pitch attitude angle data.

[0129] from Figure 4As can be seen in the figure, in the two bottom graphs, the solid line (from the calibrated air data indicating device 1) and the dashed line (reference output data) correspond well, while the dotted line (from the classical calibration) deviates the most from the other two lines. The airspeed residual is usually close to zero, and in the worst case of extreme flight conditions and rotor configurations, the airspeed residual can reach +-2 knots. This shows that the method of the present invention for calibrating the air data indicating device 1 is very effective. Specifically, the entire flight conditions and flight configurations have been covered since the third test flight. After the regressor 3 is determined as described above, because the air data indicating device 1 based on the pitot tube data from the pitot tube device 51 and the static pressure port data from the static pressure port device 52 can be operated without the nose boom 53 to obtain the airspeed and altitude of the helicopter 50, the nose boom 53 can be removed from the helicopter 50. Furthermore, the regressor 3 can also be used in air data indicating devices of other helicopters of the same type as the helicopter 50 equipped with the pitot tube device 51 and the static pressure port device 52.

[0130] In order to explain the working effect of the method and the air data indicating device 1 of the present invention in more detail, Figure 5 shows a detailed view of the data during the three maneuvers performed during the third test flight. Figure 4 Enlarged cropped portion of the data shown. Figure 5 The six graphs on the left show the dynamic descent process in a full forward center of gravity configuration, while Figure 5 The middle six graphs show data from the autorotation descent in a full forward CG configuration. Figure 5 The six graphs on the right side of the diagram show the climb first in a full forward CG configuration and then in a full aft CG configuration.

[0131] In conclusion, it is noteworthy that the present invention provides an air data indicating device belonging to the initially mentioned technical field and a method for calibrating such an air data indicating device, so that the air data indicating device can provide correct airspeed and altitude values ​​with the accuracy required by regulatory specifications for all flight configurations and flight conditions, and makes the design procedure for designing vertical take-off and landing aircraft cheaper and safer.

Claims

1. An air data indicating device (1) for a vertical take-off and landing aircraft, in particular a helicopter (50), for providing information on the airspeed of the vertical take-off and landing aircraft, and for providing information on the altitude of the vertical take-off and landing aircraft, wherein the vertical take-off and landing aircraft comprises: - a Pitot tube device (51) for determining a stagnation pressure at a location of the Pitot tube device (51) and providing Pitot tube data including information about the stagnation pressure at the location of the Pitot tube device (51), and - a static pressure hole device (52) for determining a static air pressure at a location of the static pressure hole device (52) and providing static pressure hole data including information about the static air pressure at the location of the static pressure hole device (52), wherein the air data indicating device (1) is connected to the pitot tube device (51) for receiving the pitot tube data provided by the pitot tube device (51), and wherein the air data indicating device (1) is connected to the static pressure hole device (52) for receiving the static pressure hole data provided by the static pressure hole device (52), The air data indicating device (1) comprises an airspeed and altitude determining module (2), wherein the airspeed and altitude determining module (2) is adapted to utilize a regressor (3) obtained by training an artificial neural network with training data to determine in real time based on flight data: - said airspeed of said VTOL aircraft, and - said altitude of said vertical take-off and landing aircraft, The flight data at least includes: a) the Pitot tube data, b) the static pressure hole data, c) vertical speed data, which includes vertical speed information of the vertical take-off and landing aircraft, and d) pitch attitude angle data, which includes pitch attitude angle information of the vertical take-off and landing aircraft.

2. The air data indicating device (1) according to claim 1, characterized in that: The flight data includes roll attitude angle data, and the roll attitude angle data includes information on the roll attitude angle of the vertical take-off and landing aircraft.

3. The air data indicating device (1) according to any one of claims 1 or 2, characterized in that: The flight data includes sideslip angle data, and the sideslip angle data includes information on the sideslip angle of the vertical take-off and landing aircraft.

4. The air data indicating device (1) according to any one of claims 1 to 3, characterized in that: The flight data includes lateral acceleration data, and the lateral acceleration data includes information on the lateral acceleration of the vertical take-off and landing aircraft, specifically, the amount of the lateral acceleration of the vertical take-off and landing aircraft.

5. A vertical take-off and landing aircraft, in particular a helicopter (50), comprising the air data indicating device (1) according to any one of claims 1 to 4.

6. A method for calibrating an air data indicating device (1) according to any one of claims 1 to 5, characterized in that: The airspeed and altitude determination module (2) of the air data indicating device (1) is calibrated by obtaining a regressor (3) by training an artificial neural network using training data, the training data comprising a training data set, wherein each training data set is associated with a flight condition and comprises flight data obtained during flight under the respective flight condition using a vertical take-off and landing aircraft, in particular a helicopter (50), of a type for which the air data indicating device (1) is calibrated, Each training data set comprises reference output data corresponding to an expected output of a regressor (3) during flight of said vertical take-off and landing aircraft of said type under respective flight conditions, wherein said flight data comprises at least: a) Pitot tube data, obtained from said Pitot tube device (51) of said vertical take-off and landing aircraft of said type of vertical take-off and landing aircraft during flight of said type of vertical take-off and landing aircraft under respective flight conditions, b) static port data obtained from said static port device (52) of said vertical take-off and landing aircraft of said type of vertical take-off and landing aircraft during flight under respective flight conditions of said vertical take-off and landing aircraft, c) vertical speed data, comprising information on the vertical speed of said vertical take-off and landing aircraft of said type during flight in the respective flight conditions, and d) pitch attitude angle data, comprising information on the pitch attitude angle of the vertical take-off and landing aircraft of the type during flight of the vertical take-off and landing aircraft under respective flight conditions.

7. The method according to claim 6, characterized in that In each training data set, the reference output data corresponding to the expected output of the regressor (3) during flight of the vertical take-off and landing aircraft of the type of vertical take-off and landing aircraft under respective flight conditions are obtained from one or more reference sensors (54, 55) of the vertical take-off and landing aircraft of the type of vertical take-off and landing aircraft during flight under respective flight conditions.

8. The method according to claim 6 or 7, characterized in that: The training data includes at least one training data set associated with the respective flight condition for at least one flight condition in a flight condition list, wherein the flight condition list includes: a) level flight at the first level flight speed, b) a climb at the first rate of climb and first climb flight speed, and c) Descent at a first rate of descent and a first descent flight speed.

9. The method according to any one of claims 6 to 8, characterized in that: Each training data set is associated with a flight configuration and comprises flight data obtained during flight in a respective flight configuration and flight condition, wherein for said flight condition each training data set is associated with said vertical take-off and landing aircraft of said type of vertical take-off and landing aircraft, wherein said air data indicating device (1) is calibrated for said type of vertical take-off and landing aircraft, wherein the training data comprises at least one training data set associated with at least one of the following list of flight configurations: a) Middle center of gravity, b) longitudinal full forward center of gravity, c) longitudinal fully aft center of gravity, d) Slightly forward center of gravity longitudinally, e) Slightly rearward longitudinally.

10. The method according to any one of claims 6 to 9, characterized in that: The regressor (3) is a neural network regressor, specifically a fully connected neural network regressor, which includes an output layer.

11. The method according to claim 10, characterized in that The output layer has a hyperbolic tangent (Tanh) transfer function.

12. The method according to claim 10 or 11, characterized in that: The regressor includes at least two hidden layers.

13. The method according to claim 12, characterized in that Each of the at least two hidden layers comprises at least 32 neurons, preferably at least 60 neurons, and more preferably at least 100 neurons.

14. The method according to claim 12 or 13, characterized in that The first hidden layer of the at least two hidden layers has a ReLU transfer function.

15. The method according to any one of claims 6 to 14, characterized in that: In each training data set, data of each type of the flight data are values ​​obtained by filtering a data stream having a length of at least 0.5 seconds of the respective flight data type measured under respective flight conditions.

Images