The Method Investigation Of 3D Measurement, Visual Re-construction And Recognition Applied In Engine Fault Images

As the heart of the modern aerocraft, the excellent running condition and reliability of aerial engine effectively assures the safety of civil aviation and high-efficient airfight of warplanes. At present, the common techniques of engine fault diagnosis technology by image information include endoscopy and ferrograhpy. They play the important roles to aerial engine in maintenance of the outfield and condition monitoring and fault diagnosing of the infield. Quantificational measurement and qualitative analysis to the objects are the common requirement of the endoscopy and ferrograhpy. So the investigating thought based on computer vision technology is presented in the dissertation, and the 3D measurement and reconstruction of fault image of engine accessories or parts are realized. At the same time, for the debris within the engine lubricant oil, the method realizes the 3D measurement of its sizes and symbolizes its character of 3D surface features. The investigation accelerates the development of endoscopy and ferrograhpy.The research work in this dissertation aim to apply the advanced technique in practice, that ramifies three parts: at first, the basic study of the computer vision, especially the stereo vision, include their technical mechanisms, methods and algorithms resolves the same technical problems of endoscopy and ferrograhpy based on stereo vision. Secondly, the endoscopy of engine fault inspection based on stereovision is researched and the system faced to this application is developed, thus the problems of stereovision applied to macroscopical images such as endoscopic images are resolved in method and computation. In addition, inside scenes are reconstructed and typical damages of engine inside are analyzed. Thirdly, the investigations of system formation, methods applied and algorithms study of debris analysis based on stereovision is carried out. Thus the problems of stereovision applied in debris analysis are resolved mainly. Furthermore, the integrated method combine with 3D symbolic parameters is studied and discussed for the recognition of debris configuration in pilot.The content of this paper comes down to several technologies, such as endoscopy, ferrograhpy, image processing, computer vision and optical imaging, etc. So the field of investigation is widely. At the same time, the thoughts and methods is so novel that the correlative work is seldom inland, so there are certain innovative value and academic significance. The thoughts has the actual meaning in accelerating the development of engine condition monitoring and fault diagnosing technique based on fault images information and spreading the application computer vision in engineering.