Fuselage surface damage defect automatic detection method and system based on deep learning

Abstract

The invention discloses a fuselage surface damage defect automatic detection method and system based on deep learning, and the method comprises the following steps: A, building a defect sample model: collecting airplane fuselage defect sample data, and building the defect sample model according to the defect sample data; B, employing a multi-angle camera combined shooting system for shooting and collecting fuselage actual image data of the to-be-detected aircraft fuselage, and obtaining a fuselage actual three-dimensional scene model through corresponding three-dimensional synthesis of a fuselage three-dimensional synthesis system; according to the fuselage defect information of the defect sample model, performing one-by-one target comparison detection on the fuselage actual three-dimensional scene model to obtain fuselage actual scene defect data, wherein the fuselage actual scene defect data comprises defect position information, defect types, defect ranges and defect numbers. According to the invention, aircraft fuselage surface detection can be comprehensively, accurately and efficiently realized, the defect position, the defect type and the defect size can be accurately positioned, the labor intensity is reduced, and the inspection and maintenance efficiency is improved.

Description

technical field [0001] The invention relates to the field of defect detection of civil aviation aircraft fuselage, in particular to a method and system for automatic detection of damage defects on the surface of the fuselage based on deep learning. Background technique [0002] The fuselage inspection of civil aviation airliners is an important part of the daily maintenance work of the aircraft. The traditional aircraft fuselage inspection mainly adopts the manual visual inspection method. Due to the large structure of the aircraft fuselage (including the wings), this brings more problems to the daily defect detection. It is very difficult, especially the inspection of the top of the fuselage, which usually requires other mechanical auxiliary equipment, and there are problems such as inconvenient inspection, heavy workload, and long inspection cycle. In recent years, with the vigorous development of civil aviation and the wide application of artificial intelligence technolog...

AI Technical Summary

Problems solved by technology

[0002] The fuselage inspection of civil aviation passenger aircraft is an important part of the daily maintenance work of the aircraft. The traditional aircraft fuselage inspection mainly uses manual visual inspection methods. Due to the large structure of the aircraft fuselage (including the wings), this brings more problems to the daily defect detection. It is very difficult, especially the inspection on the top of the fuselage, which usually requires other mechanical auxiliary equipment, and there are problems such as inconvenient inspection, heavy workload, and long inspection cycle

In recent years, with the vigorous development of civil aviation and the wide application of artificial intelligence technology, the traditional manual visual inspection method can no longer meet the requirements of rapid inspection of aircraft fuselage

Images