基于多域空间状态特征的高端装备运行可靠性评价

发布时间：2018-03-15 08:19

本文选题：运行可靠性　切入点：状态特征　出处：《仪器仪表学报》2016年04期 　论文类型：期刊论文

【摘要】：机械设备运行可靠性对设备状态监测及故障诊断具有重要意义。传统可靠性评估方法依赖于大量故障样本,运用在单台设备可靠性评估上的实际意义有限。本文提出一种基于设备状态特征空间的运行可靠性评价方法。采集设备运行过程中的振动信号,获取时频域信息特征;采用小波包分解提取能量分布特征,构建高维特征空间。应用流形学习优化算法进行降维,获得其低维敏感特征空间,计算当前状态与正常状态的特征子空间的夹角,建立其映射关系,表征设备的当前运行可靠性。将该方法应用于不同状态下的转子实验台和滚动轴承实验台振动数据,实验结果表明:该方法对设备进行运行可靠性评价合理有效,具有很好的工程应用价值。
[Abstract]:The operational reliability of mechanical equipment is of great significance to equipment condition monitoring and fault diagnosis. The traditional reliability evaluation method depends on a large number of fault samples. In this paper, a method of reliability evaluation based on the equipment state feature space is presented. The vibration signals are collected during the operation of the equipment, and the time-frequency domain information features are obtained. The wavelet packet decomposition is used to extract the energy distribution feature and to construct the high dimensional feature space. Using manifold learning optimization algorithm to reduce the dimension, the low dimensional sensitive feature space is obtained, and the angle between the feature subspace of the current state and the normal state is calculated. The mapping relation is established to characterize the reliability of the equipment at present. The method is applied to the vibration data of the rotor test table and the rolling bearing test table in different states. The experimental results show that the method is reasonable and effective for the reliability evaluation of the equipment and has good engineering application value.
【作者单位】：北京信息科技大学机电工程学院;北京信息科技大学现代测控技术教育部重点实验室;北京信息科技大学机电系统测控北京市重点实验室;
【基金】：国家自然科学基金资助项目(51575055) "高档数控机床与基础制造装备"科技重大专项(2015ZX04001002)项目资助
【分类号】：TH17

【参考文献】