数控机床寿命预测技术是数控机床健康管理和维修维护的关键技术，面向数控机床研究基于性能退化的剩余寿命预测方法。在分析了剩余寿命与性能退化规律和性能阈值分布有关的基础上，建立单性能退化的维纳过程模型和融合多性能退化的维纳过程模型，从而得到数控机床的多性能退化量分布模型。依据失效原则，得到数控机床的性能阈值分布模型。由此，建立基于阈值分布的剩余寿命预测模型得到剩余寿命概率密度函数。在数控机床进给系统试验平台上进行试验，验证了融合多性能退化的维纳过程模型和剩余寿命预测方法的正确性和有效性。
Life prediction technology is the key technology to the healthy management and the maintenance of the NC machine tool. It is aimed at the NC machine tool to study residual life prediction method based on the performance degradation. Firstly, the relationship between residual life and performance degradation and performance threshold distribution is analysed. A Wiener process model is established to describe the single performance degradation, and the Wiener process to the fusion of multi performance Wiener process is put forward to predict the performance degradation parameter in multi performance condition for NC machine tool. Then, a performance threshold distribution model is built according to failure principle. The probability density function of residual life is obtained by establishing a life prediction model based on the threshold distribution. Finally,the experiment is carried out on the test platform for feed system of CNC machine tools, so that the fusion of multi performance Wiener processanalysis and the residual life prediction method are verified.
[1] 张小丽,陈雪峰,李兵,等. 机械重大装备寿命预测综述[J]. 机械工程学报,2011,47(11):100-116. ZHANG Xiaoli,CHEN Xuefeng,LI Bing,et al. Review of life prediction for mechanical major equipment[J]. Journal of Mechanical Engineering,2011,47(11):100-116.
[2] MALHI A,YAN Ruiqiang,ROBERT X G. Prognosis of defect propagation based on recurrent neural networks[J]. IEEE Transactions on Instrumentation & Measurement,2011,60(3):703-711.
[3] ZHAO Wei,TAO Tao,DING Zhushu,et al. A dynamic particle filter-support vector regression method for reliability prediction[J]. Reliability Engineering System Safety,2013,119:109-116.
[4] 申中杰,陈雪峰,何正嘉,等. 基于相对特征和多变量支持矢量机的滚动轴承剩余寿命预测[J]. 机械工程学报,2013,49(2):183-189. SHEN Zhongjie,CHEN Xuefeng,HE Zhengjia,et al. Remaining life predictions of rolling bearing based on relative features and multivariable support vector machine[J]. Journal of Mechanical Engineering,2013,49(2):183-189.
[5] 李媛媛,陈捷,洪荣晶,等. 基于模糊C均值的转盘轴承剩余寿命预测[J]. 轴承,2017(3):50-55. LI Yuanyuan,CHEN Jie,HONG Rongjing,et al. Residual life predication of slewing bearing based on fuzzy C-means[J]. Bearing,2017(3):50-55.
[6] CHENG Zhe,HU Niaoqing. Residual useful life prediction of planetary gear set based on modified grey model[J]. Journal of Grey System,2012,24(2):157-164.
[7] CHEN Chaochao,VACHTSEVANOS G,ORCHARD M E. Machine remaining useful life prediction:an integrated adaptive neuro-fuzzy and high-order particle filtering approach[J]. Mechanical Systems & Signal Processing,2012,28:597-607.
[8] HUANG Jinbo,KONG Dejing,CUI Lirong. Bayesian reliability assessment and degradation modeling with calibrations and random failure threshold[J]. Journal of Shanghai Jiao Tong University,2016,21(4):478-483.
[9] JIANG R. A multivariate CBM model with a random and time-dependent failure threshold[J]. Reliability Engineering System Safety,2013,119:178-185.
[10] ZHAO Zeqi,LIANG Bin,WANG Xueqian,et al. Remaining useful life prediction of aircraft engine based on degradation pattern learning[J]. Reliability Engineering and System Safety,2017,164(2):74-83.
[11] HUANG Zeyi,XU Zhengguo,KE Xiaojie,et al. Remaining useful life prediction for an adaptive skew-Wiener process model[J]. Mechanical Systems and Signal Processing,2017,87(3):294-306.
[12] TANG Shengjin,YU Chuanqiang,FEN Yonbao,et al. Remaining useful life estimation based on Wiener degradation processes with random failure threshold[J]. Journal of Central South University,2016,23(9):2230-2241.
