Title :
Reliability assessement method based on SVDD and SVR with multiple performances degradation data for chassis system
Author :
Lixia Zhang;Fuzhou Feng;Mingguang Bi
Author_Institution :
Department of Mechanical Engineering, Academy of Armored Force Engineering, Beijing, China
Abstract :
For the long life, small samples, non-failure and high costs of equipments, the reliability assessment is very difficult, which is limited by the number of samples data, so the paper puts forword to study the methods of reliability assessment and prediction based on multi-parameter performance degradation. For the multi-parameters characteristics, the paper proposes the data fusion technique based on the algorithm of support vector data description(SVDD) to form a comprehensive performance parameter, and then forecasts the trend of the comprehensive performance parameter based on the algorithm of support vector regression (SVR). The experiment shows that the methods can estimate correctly the reliability of the specified system.
Keywords :
"Reliability","Degradation","Data integration","Decision support systems","Prediction algorithms","Support vector machines","Market research"
Conference_Titel :
Reliability Systems Engineering (ICRSE), 2015 First International Conference on
DOI :
10.1109/ICRSE.2015.7366455