Reliability Assessment Methods of Complicated Mechanical Productbased on Statistical Learning Theory
As the reliability test data of complicated mechanical products is rare in quantity on thesystem-level and difficult to determine the accurate composition of the life distribution unit as well,the traditional reliability evaluation method based on evolutionary theory has been of little use.Andthe Statistical Learning Theory begins to be widely focused on as a novel small sample statisticmethod,which has been mostly applied to pattern recognition,fault detection,time series predictionand so on.This paper creates a new method for reliability evaluation derived from Statistical LearningTheory.By constructing Support Vector Machine with analog reasoning,and solving linear operatorequation,the probability density of product can be evaluated directly and then the product reliabilityindex can be obtained.Compared with the traditional way,this method can apparently increase theaccuracy and generalization ability of reliability evaluation within limited samples.Finally,this paperpresents the bridge of a certain heavy special vehicle as an example to testify the efficiency of thismethod,and uses the accelerated life test of the vehicle bridge to estimate its reliability.
Complicated Mechanical Product Reliability Assessment SLT SVM
X.Y.Shao J.Wu Y.Q.Lv C.Deng
School of Mechanical Science and Engineering,Huazhong University of Science and Technology
国际会议
成都
英文
2008-08-04（万方平台首次上网日期，不代表论文的发表时间）