Operation Reliability Evaluation of NC Cutting Tool Based on Degradation Feature Under Censored Data
In the process of modern industry,the run-to-failure operating status information of device is difficult to be acquired.How to estimate operation reliability of device by using the censored data becomes vital.This paper proposes an estimation method of operation reliability that can carry out the estimation of instantaneous reliability and the prediction of remained useful life by means of the censored data.The key technology is to build an estimation model of instantaneous reliability.The three steps of modeling are as follows: Firstly,acquiring the operating status information.Second,considering only censored data,Gaussian process for machine learning is employed to predict samples` life and theirs life feature values at the time of failure,and their probability density functions are obtained through distribution hypotheses and testing.Third,the Bayes theorem is used to obtain the instantaneous reliability model.Finally,a CNC cutting tests shows the plausibility and effectiveness of the proposed method.
reliability prediction remained useful life cutting tool degradation feature
Wenrong Xiao Yanyang Zi Zhengjia He
State Key Laboratory for Manufacturing Systems Engineering,Xian Jiaotong University,Xian 710049,China
国际会议
南京
英文
1-4
2013-08-20（万方平台首次上网日期，不代表论文的发表时间）