基于时间序列数据挖掘的旋转机械故障预报  

Fault Prediction for Rotating Machinery Based on Time Series Data Mining

作　　者：苏圣超[1] 张正道[1] 朱大奇[1] 

机构地区：[1]江南大学控制科学与工程研究中心,无锡214122

出　　处：《南京航空航天大学学报》2006年第B07期120-123,共4页Journal of Nanjing University of Aeronautics & Astronautics

基　　金：江苏省自然科学基金(BK2004021)资助项目;教育部科学技术研究(105088)资助项目。

摘　　要：提出一种基于时间序列数据挖掘的故障预报新方法。把故障前兆因子作为一种暂态,根据旋转机械轴承振动的实验数据建立时间序列．利用时延嵌入的方法重构状态空间,在状态空间中使用遗传算法搜寻最优暂态束．组成暂态集。用暂态集对旋转机械轴承振动的测试数据进行分析．判断是否为故障前兆因子．从而实现故障预报。A new fault prediction method based on time series data mining is proposed. Fault symptoms are regarded as a sort of temporal patterns hidden in the time series formed by rotating machinery bearing vibration data. The time series is embedded into a reconstructed phase space with time-delay. In this phase space; genetic algorithms are used to search optimal temporal pattern clusters. The optimal collection is comprised of temporal pattern clusters and then is used to test the other bearing vibration data of the rotating machinery. Once the symptom is detected, the fault is forecasted.

关 键 词：时间序列 数据挖掘 旋转机械 故障预报 

分 类 号：TP206.3[自动化与计算机技术—检测技术与自动化装置]