基于概率密度空间划分的符号化时间序列分析及其在异常诊断中的应用

Anomaly detection using symbolic time series analysis based on probability density space partitioning

提前诊断出机械系统中的异常信息对于防止生产事故的产生非常重要。在各种诊断方法中,符号化时间序列分析(STSA,Symbolic time series analysis)是一种常用的异常诊断方法,然而它的诊断效果和符号化时间序列的形成紧密相关。在对之前方法总结分析的基础上,提出了一种高效实用的符号化方法——基于概率密度空间划分的符号化方法。在该方法中,首先对时间序列进行概率密度统计分析,进而确定若干个概率相等的区间,然后对属于特定区间的值赋予一个特定的符号。为了检验该方法的效果,将基于概率密度空间划分的符号化时间序列分析方法用于轴承疲劳实验的异常诊断当中。通过对比实验表明:概率密度符号化方法相比于传统的空间划分方法对异常更加敏感,能够更早诊断出轴承的异常。

Early detection of anomalies in machine system is essential for prevention of production accidents.Among various anomaly detection methods,symbolic time series analysis has been widely used.The effectiveness of this method is heavily dependent on the procedure of symbol sequence generation.This paper presents a novel partitioning method called probability density space partitioning for the symbol sequence generation.In this partitioning approach,a time series is divided into several equal-sized regions based on the probability density distribution and each region is represented by a symbol.To verify the effectiveness of the symbolic time series analysis which is based on probability density space partitioning,the test-to-fatigue experiments are conducted.The experimental results indicate that probability-density-based method is more sensitive to detect bearing anomaly than the traditional partition based methods.