摘要
针对现有工业时间序列数据异常检测算法并未充分考虑时序数据在时间相关性方面的研究问题,提出了一种改进的HTM(Hierarchical Temporal Memory)-Attention算法。该算法结合了HTM算法和Attention机制,能学习数据之间的时间依赖关系,并在单变量和多变量时序数据上得到验证。同时,通过引入Attention机制,算法可以关注输入数据中的重要部分,进一步提高了异常检测的效率和准确性。实验结果表明,该算法对不同类型的时间序列异常数据能进行有效地检测,并且比其他常用的无监督异常检测算法具有更高的准确率和更低的运行时间。该算法在工业时间序列数据异常检测的应用中具有较大的潜力。
Existing industrial time series data anomaly detection algorithms do not fully consider the temporal data on time dependence.An improved HTM(Hierarchical Temporal Memory)-Attention algorithm is proposed to address this problem.The algorithm combines the HTM algorithm with the attention mechanism to learn the temporal dependencies between data.It is validated on both univariate and multivariate time series data.By introducing the attention mechanism,the algorithm can focus on the important parts of the input data,further improving the efficiency and accuracy of anomaly detection.Experimental results show that the proposed algorithm can effectively detect various types of time series anomalies and has higher accuracy and lower running time than other commonly used unsupervised anomaly detection algorithms.This algorithm has great potential in the application of industrial time series data anomaly detection.
作者
张晨林
张素莉
陈冠宇
王福德
孙启涵
ZHANG Chenlin;ZHANG Suli;CHEN Guanyu;WANG Fude;SUN Qihan(School of Computer Science and Engineering,Changchun University of Technology,Changchun 130012,China;School of Computer Technology and Engineering,Changchun Institute of Technology,Changchun 130103,China;Department of Technology,Jilin Haicheng Technology Company Limited,Changchun 130119,China;College of Big Data and Information Engineering,Guizhou University,Guiyang 550025,China)
出处
《吉林大学学报（信息科学版）》
CAS
2024年第3期457-464,共8页
Journal of Jilin University（Information Science Edition）
基金
吉林省科技厅基金资助项目(20200301045RQ)
吉林省发改委基金资助项目(2020C004)。
关键词
层级时序记忆
注意力机制
时序数据
异常检测
hierarchical temporal memory
attention mechanism
temporal data
anomaly detection
