Aircraft air data is estimated using a neural network trained to be independent of any signals from air data sensors whose values are based on air flow pressure measurements.

A wind speed detection system and a wind speed detection method are provided. The wind speed detection system includes a pipe body and a controller. The pipe body comprises a pressure sensing module and a suction pump. The pressure sensing module is connected to a first opening through a first pipe and connected to a second opening through a second pipe. The first pipe has a main pipe. Two ends of a first alternative pipe are connected to two ends of the main pipe. When the controller performs a self-checking operation, the main pipe is closed and the first alternative pipe is opened. The controller starts the suction pump to perform forward suction. The controller measures a first air pressure through the first pipe and measures a second air pressure through the second pipe by the pressure sensing module. The controller calculates a reference wind speed value according to the first and second air pressures.

A method for determining airspeed of an aircraft that includes determining a rotor model relating a power coefficient of a propeller of the aircraft to an axial inflow velocity through the propeller as a function of a set of rotor operating parameters; determining the set of rotor operating parameters by sampling an electronic control signal associated with an electric motor actuating the propeller; computing the axial inflow velocity through the propeller based on the set of rotor operating parameters using the rotor model; and determining the airspeed based on the axial inflow velocity.

Methods and systems are provided for utilization of vehicle speed and barometric pressure sensors. In one example, a method may include measuring a change in a barometric pressure resulting from a measured change in a vehicle speed, modeling the change in the barometric pressure based on a change in a ram-air pressure resulting from the change in the vehicle speed, and indicating a degraded barometric pressure measurement when a difference between the measured and the modeled change in the barometric pressure is greater than a threshold pressure difference.

A method of checking accuracy of an air data probe system onboard a vehicle is disclosed. An embodiment of the method involves: calculating airspeed measurements from air data provided by the probe system; calculating vehicle speed measurements based on sensor data collected from at least one sensor system onboard the vehicle, wherein the vehicle speed measurements are distinct and independent of the airspeed measurements, and the vehicle speed measurements are calculated without using the air data; comparing a calculated airspeed measurement against a calculated vehicle speed measurement to obtain a speed difference, wherein the calculated airspeed measurement and the calculated vehicle speed measurement correspond to a measurement time during which the vehicle is moving forward; and initiating at least one corrective action onboard the vehicle when magnitude of the speed difference exceeds a threshold value.

The present disclosure provides methods and systems for correcting a vertical speed of an aircraft. An instantaneous vertical speed of the aircraft is obtained, based on inertial data from an inertial reference unit on the aircraft. A first correction is applied to the instantaneous vertical speed to generate a baro-inertial vertical speed, and a second correction is applied to the baro-inertial vertical speed based on an error between a geometric vertical speed and the baro-inertial vertical speed to obtain a temperature-corrected baro-inertial vertical speed.

A foam sensor device is used for monitoring foam within a vessel. The sensor (e.g. accelerometer) is encapsulated inside a water-tight, sterilizable, shell, which floats on a liquid contained. In one example, the foam sensor device includes an accelerometer for detecting and measuring rotation and movement of the foam sensor device and generates movement data based on the detected movement. During a learning or calibration process, sensor data (e.g., movement data) from the foam sensor device is analyzed and classified using machine learning and/or signal processing methods to extract features indicative of different possible foam statuses, including varying levels of foam, or no foam and generate models for the different statuses. During normal operation, the foam sensor device transmits sensor data to an analyzer containing the pre-calibrated models, which determines whether there is foam or not. Based on the foam status, a pump controller adds anti-foam solution.

Methods and apparatus for monitoring fluid-dynamic drag on an object, such as a bicycle, ground vehicle, watercraft, aircraft, or portion of a wind turbine are provided. An array of sensors obtain sensor readings for example indicating: power input for propelling the object; air speed and direction relative to motion of the object; and ground speed of the object. Sensor readings may also indicate: temperature; elevation and humidity for providing a measurement of air density. Sensor readings may also indicate inclination angle and forward acceleration. Processing circuitry determines a coefficient of drag area based on the sensor readings and optionally one or more stored parameters, according to a predetermined relationship. A pitot tube based apparatus for measuring fluid speed and direction is also provided. Methods for dynamic in situ calibration of the pitot tube apparatus, and of adjusting correction factors applied to correct measurement errors of this apparatus are also provided.

Systems, methods, and apparatus for sensor fault detection and identification using residual failure pattern recognition are disclosed. In one or more embodiments, a method for sensor fault detection and identification for a vehicle comprises sensing, with sensors located on the vehicle, data. The method further comprises performing majority voting on the data for each of the types of data to generate a single voted value for each of the types of data. Also, the method comprises generating, for each of the types of data, estimated values by using some of the voted values. In addition, the method comprises generating residuals by comparing the estimated values to the voted values. Further, the method comprises analyzing a pattern of the residuals to determine which of the types of the data is erroneous to detect and identify a fault experienced by at least one of the sensors on the vehicle.

This application relates to an aircraft static port testing device in which a static leech may fixed to the static port of an aircraft. The static leech may be held in place by a suction cup surrounding the static port and the static port may be connected to an aircraft air data testing unit through a static port fitting. Vacuum may be created in the suction cup through a vacuum syringe or a vacuum pump.