多台数控机床的时间截尾可靠性评估

Reliability evaluation of multiple NC machine tools with time truncation

为了评估数控(NC)机床的可靠性,提出了用AIC、BIC信息准则选择多台NC机床故障间隔时间的分布模型和模型参数的方法.用Fisher信息矩阵法(FM)给出了模型参数和机床平均寿命的可靠度及可靠度为90%时的工作保证时间的区间估计,用Monte Carlo(MC)仿真法扩大少样本数据的样本容量,提高了区间估计的精度.结果表明,平均寿命的可靠度及可靠度为90%时的工作保证时间的区间估计长度分别减少了93%、95%.

To evaluate the reliability of NC machine tools, based on AIC and BIC information criteria, a method of model selection and parameter estimation for time-between-failures of multiple NC machine tools with time truncation is proposed. The confidence intervals of model parameters, the reliability given MTBF （mean time between failures） and the warranty time with 90% reliability are all given by Fisher Information Matrix method. At last, Monte Carlo simulation method is used to enlarge sample size of small-sample data to improve the precision of interval estimation. The results show that the interval length of reliability given MTBF and warranty time with 90% reliability are both reduce by 95% and 93% respectively.