多元随机过程的剩余寿命预测

Residual life prediction for multivariate stochastic processes

为了探究复杂系统的实际退化过程和剩余寿命,将采用一种新的权重计算方法融合多维性能指标退化过程,并利用马尔科夫蒙特卡洛方法在线更新模型参数,进而得出系统剩余寿命概率密度函数。通过裂纹增长实验的验证分析,结果表明所提方法能够有效地预测系统剩余寿命,并相较于一元随机过程预测模型,所提方法具有更好的预测精度且随着退化数据的增加,系统剩余寿命预测结果更加精确。

In order to explore the actual degradation process and residual life of complex systems,a new weight calculation method was adopted to integrate the multidimensional performance index degradation process,and markov Monte Carlo method was used to update the model parameters online,and then the system residual life probability density function was obtained.The results of crack growth experiments showed that the proposed method can effectively predict the residual life of the system,and the proposed method has better prediction accuracy compared with the prediction model of monadic random process,and the prediction results of the residual life of the system had more accurate with the increasing of degradation data.