加工中心故障分布规律及其研究方法

Failure distribution law of a machining center and its study

数控机床的平均故障间隔时间是一项重要的可靠性指标,然而作为该指标计算理论基础的故障分布规律却未得到充分研究。基于Ⅰ型截尾似然函数理论,结合加工中心试验数据,对加工中心故障间隔时间进行了威布尔分布模型的拟合,然后用Hollander Proschan方法进行了拟合优度检验,最后证明该加工中心故障间隔时间服从威布尔分布。对这类有替换定时截尾数据,用截尾似然函数理论进行拟合,并且用Hollander Proschan方法进行拟合优度检验,是非常有效的。

The reliability study for numerical control (NC) machine tool is of significance to increase the market share of the NC machine tool. The mean time between failures (MTBF) of NC machine tool is an important reliability criterion; however, the failure distribution law, as the basis for calculating the MTBF, has not been adequately studied. Based on Type-Ⅰcensored likelihood function and actual timing censored data of the machining center, the fitting of weibull model is made for time between failures of machining center, then goodness-of-fit test is performed by the Hollander-Proschan's method. In the end it is proved that the time between failures of the machining center follows Weibull distribution. It is very effective to make fitting with censored likelihood function and goodness-of-fit with Hollander-Proschan's method for these censored data.