Aircraft skin assembly quality detection method based on digital twinning

Abstract

The invention discloses a digital twinning-based aircraft skin assembly quality detection method, which comprises an information acquisition stage, an image detection stage, an information tracing stage and a parameter correction stage, and specifically comprises the following steps of: adjusting the position and parameters of a camera to ensure that an acquired detected part image is clear and the position is accurate; carrying out image acquisition on the detected part by using an industrial camera; identifying and classifying the images by using a residual network ResNet-50; the recognition result is input into an RFID chip, so that the riveting parameter of each detection part corresponds to the detection result; the relation between riveting parameters and detection results is analyzed, and information tracing is conducted on unqualified parts; re-determining riveting parameters according to an information tracing result, constructing a virtual workshop, and performing virtual simulation by using new parameters to determine the feasibility of the virtual workshop; and guiding parameter correction of a real workshop according to a simulation result, and carrying out subsequent skin assembly. According to the method, the skin assembly quality detection efficiency is improved, and the skin assembly quality is improved.

Description

technical field [0001] The invention relates to the field of assembly quality inspection, and more particularly to a digital twin-based aircraft skin assembly quality inspection method. Background technique [0002] The aircraft wing is an important part of the aircraft. The skin forms the surface of the wing, and its function is to maintain the shape of the wing and directly bear the aerodynamic load. Skin assembly is an important step in the aircraft assembly process, and the assembly quality of the skin determines the final quality of the wing to a large extent. At present, the skin and other structural parts are usually riveted in the domestic aircraft assembly process, mainly relying on manual assembly by workers. In skin assembly quality inspection, surface quality inspection mainly relies on the experience of workers and uses naked eye inspection. The inspection efficiency is low, and it is difficult to detect small cracks and depressions, which seriously affects the...

AI Technical Summary

Problems solved by technology

This method uses a traditional convolutional neural network for model training, which not only requires a large number of samples, but also has low training efficiency, and it is difficult to extract deep features, which affects the accuracy of the final detection result; 3) Patent (CN102928435A) aircraft based on fusion of image and ultrasonic information Skin damage recognition method and device, by extracting aircraft skin images of known damage categories and texture features and ultrasonic echo signals of ultrasonic echo signals, applying the extracted features to classifier training, using the trained classification The device classifies and judges the input images and signals to identify skin damage

The device simultaneously uses images and ultrasonic echo signals to identify the quality of the skin. After quality judgment and classification, it is impossible to find out the parameters that affect the quality of the skin and guide the subsequent assembly work, and cannot improve the assembly quality of the skin.

[0004] In summary, although the existing research results and methods can realize the assembly quality inspection of aircraft skin to a certain extent, it is difficult to ensure the accuracy of inspection due to the existence of many defects. Assembly requirements

Images