时间序列中异常值检测的负向选择算法

NEGATIVE SELECTED ALGORITHM FOR ANOMALY DETECTION IN TIME SERIES DATA

针对转子振动时间序列中异常数据的检测问题,采用欧氏距离进行匹配计算,在实数域实现了负向选择算法。通过对抗体库中元素增加一个描述其覆盖半径的参数,可更有效地发挥每个抗体元素的检测作用,显著提高了抗体库对异常数据集合的覆盖范围。计算结果表明,这种算法可有效地检测出时间序列中的异常值,且抗体库中元素数量少而可望用于信号的在线监测。

For the anomaly detection in the vibration time series of the rotor system, a real-valued negative selection algorithm based on Euclidean distance has been implemented. By means of adding the corresponding coverage radius to each antibody elements, the detection efficiency of each antibody element is increased. The coverage scope of the antibody set is significantly enlarged for the anomaly data set. The calculation results indicate that the algorithm can efficiently detect the anomaly in time series data. Moreover, the number of detectors in antibody set is less enough for potential application in online signal monitoring.