An aviation component inspection device includes a camera, a display, an input device, and a computer. The camera is configured to capture images of an aviation component under inspection. The computer is configured to receive an image from the camera, evaluate the image with one or more machine-learning aviation component-detection models. Each machine-learning aviation component-detection model is previously trained to output at least one confidence score indicating a confidence that a corresponding aviation component is present in the image. The computer is configured to present, via the display, a list of candidate aviation components based on corresponding confidence scores output by the one or more machine-learning aviation component-detection models, and add data previously-associated with a selected candidate aviation component from the list to a digital inspection report responsive to receiving user verification, via the input device, confirming the selected candidate aviation component is present in the image.

An aviation component inspection device includes a camera, a display, an input device, and a computer. The camera is configured to capture images of an aviation component under inspection. The computer is configured to receive an image from the camera, evaluate the image with one or more machine-learning aviation component-detection models. Each machine-learning aviation component-detection model is previously trained to output at least one confidence score indicating a confidence that a corresponding aviation component is present in the image. The computer is configured to present, via the display, a list of candidate aviation components based on corresponding confidence scores output by the one or more machine-learning aviation component-detection models, and add data previously-associated with a selected candidate aviation component from the list to a digital inspection report responsive to receiving user verification, via the input device, confirming the selected candidate aviation component is present in the image.

An impact detection device includes an impact detector, a wireless communication device, an energy storage device, an autonomous electrical energy generation device, a device for receiving energy by radio frequency, the device being configured to adopt the following two modes: a first mode, referred to as autonomous mode, in which the autonomous electrical energy generation device is configured to supply the impact detector and the wireless communication device; a second mode, referred to as external mode, in which the device for receiving energy by radio frequency is configured to supply the impact detector and the wireless communication device.

Cameras and lights positioning system for hose inspection during air-to-air refueling, which comprises a substructure that can be attached to a container or capsule or Pod, one or two guidance-substructures (13) that enclose the hose, a toroid volume, to house the cameras (22) and lights (23) and a cameras and lights control subsystem. The system allows for the cameras (22) and lights (23) to maintain a fixed relative position with respect to the hose (1) during moments of imagery acquisition, despite the inclination and the five different movements that the hose has and makes, at the same time allowing protuberances (38) to pass through the system.

A method and a system for controlling a plurality of control stations of an aircraft. The control method comprises determining a current position of a portable electronic terminal in relation to the aircraft, identifying a current control station, determining at least one current image of the aircraft representative of the current control station, displaying, on a screen of the portable electronic terminal, the at least one current image, displaying at least one graphic interface component in overlay on the at least one current image, selecting a result relating to an inspection of at least one component on the portable electronic terminal and storing it in a memory, the result corresponding to a validated state or a non-validated state of the at least one inspected component.

A method and a system for controlling a plurality of control stations of an aircraft. The control method comprises determining a current position of a portable electronic terminal in relation to the aircraft, identifying a current control station, determining at least one current image of the aircraft representative of the current control station, displaying, on a screen of the portable electronic terminal, the at least one current image, displaying at least one graphic interface component in overlay on the at least one current image, selecting a result relating to an inspection of at least one component on the portable electronic terminal and storing it in a memory, the result corresponding to a validated state or a non-validated state of the at least one inspected component.

The present disclosure relates to the technical field of aerospace, and provides a machining method for an ultra-high strength steel high-aspect-ratio wind tunnel test model part. The machining method includes the following steps: a) selecting a material; b) performing preliminary treatment, such as forging and solid solution heat treatment, on the material; c) performing rough milling to obtain a wing main body profile, process reference blocks, and grooves and holes with large sizes on a molded surface; d) performing finish milling on all machining features of a wing main body; e) removing all process reference blocks except the first process reference block; f) performing aging strengthening treatment when the wing main body is lifted; h) removing a process reference block at a wing main body root; and h) performing shaping treatment on the wing main body.

Training an encoder is provided. The method comprises inputting a current state of a number of aircraft into a recurrent layer of a neural network, wherein the current state comprises a reduced state in which a value of a specified parameter is missing. An action applied to the aircraft is input into the recurrent layer concurrently with the current state. The recurrent layer learns a value for the parameter missing from current state, and the output of the recurrent layer is input into a number of fully connected hidden layers. The hidden layers, according to the current state, learned value, and current action, determine a residual output that comprises an incremental difference in the state of the aircraft resulting from the current action.

Training an encoder is provided. The method comprises inputting a current state of a number of aircraft into a recurrent layer of a neural network, wherein the current state comprises a reduced state in which a value of a specified parameter is missing. An action applied to the aircraft is input into the recurrent layer concurrently with the current state. The recurrent layer learns a value for the parameter missing from current state, and the output of the recurrent layer is input into a number of fully connected hidden layers. The hidden layers, according to the current state, learned value, and current action, determine a residual output that comprises an incremental difference in the state of the aircraft resulting from the current action.

A system for monitoring the degradation status of refueling hoses on air includes a device with at least one sensor adapted to produce data about the external surface of the refueling hose. The method for monitoring the degradation status of refueling hoses on air includes moving a device with at least one sensor along a refueling hose or moving a refueling hose with respect to the device, producing data about the external surface of the refueling hose from the at least one sensor, and analyzing the data for monitoring the degradation status of the refueling hose. It allows providing a system and method for monitoring the degradation status of refueling hoses on air that reduces the risk of personal injury associated to hose damage inspection and is cost saving.