Title :
Based on image pixel gray value feature extraction of PHM research
Author :
Kong Fansheng ; Wang Zhulin
Author_Institution :
Ordnance Eng. Coll., Shijiazhuang, China
Abstract :
A certain type of the internal examination system combination generated simulation background target image signal, goniometer acquisition target signal, realizes the goniometer simulation training, training application detection system, it is concluded that the performance parameters of goniometer. In view of the target image, by simulating the goniometer view transformation system, the integrity of off the target image signal acquisition, based on the rule of fault prediction and health management (PHM), an improved fuzzy c-means clustering algorithm for image segmentation and pixel quantitative processing, error of grey value standards, extract does not meet the standard of pixels, for subsequent electric circuit according to the target image predicting combination of lay the foundation.
Keywords :
fault diagnosis; feature extraction; fuzzy set theory; goniometers; image colour analysis; image segmentation; interpolation; maintenance engineering; object detection; pattern clustering; PHM research; background target image signal acquisition; fault prediction and health management; fuzzy c-means clustering algorithm; goniometer acquisition target signal; goniometer simulation training; goniometer view transformation system; grey value standards; image interpolation; image pixel gray value feature extraction; image segmentation; internal examination system; pixel quantitative processing; testing combination electric circuit fault prediction; training application detection system; Algorithm design and analysis; Circuit faults; Clustering algorithms; Feature extraction; Image segmentation; Interpolation; Transforms; Field transform; The clustering algorithm; The gey value extraction; The pixel;
Conference_Titel :
Guidance, Navigation and Control Conference (CGNCC), 2014 IEEE Chinese
Conference_Location :
Yantai
Print_ISBN :
978-1-4799-4700-3
DOI :
10.1109/CGNCC.2014.7007293