摘要
在复杂工业系统因传感器数量急剧增加,产生了高维噪声和随机干扰,严重影响多元时间序列的数据连续性和控制精度。然而现有对多元时间序列存在随时间变化的时序不一致性、空间矢量的偏差性以及时空图模型的冗余度等问题。本文提出了一种新的多元时间序列异常检测方法STGAD。首先,从高分辨率的粒度级别上,引入门控机制改进多尺度卷积网络,控制特征间的信息交互过程。然后,设计了两种图结构,剔除了冗余的时空依赖关系,利用GAT有效地学习时空相关性。此外,提出了一种基于注意力机制的GRU模块,来捕获变量在不同时间窗口上的重要性。最后,联合优化预测和重构的模块。在三个公开数据集上进行广泛的实验,结果表明所提出模型的平均F1分数高于0.94,在高维数据集上明显优于其他基准模型。
In complex industrial systems due to the dramatic increase in the number of sensors,high-dimensional noise and random disturbances are generated,which seriously affect the data continuity and control accuracy of multivariate time series.However,the existing pairs of multivariate time series have the problems of temporal inconsistency over time,deviation of space vectors,and redundancy of spatio-temporal graphical models.In this paper,a new multivariate time series anomaly detection method STGAD is proposed.First,a gating mechanism is introduced to improve the multiscale convolutional network from a high-resolution granularity level to control the process of information interaction between features.Then,two graph structures are designed to eliminate redundant spatio-temporal dependencies,enabling GAT to effectively learn spatio-temporal correlations.In addition,an attention mechanism-based GRU module is proposed to capture the importance of variables over different time windows.Finally,modules for joint optimization prediction and reconstruction.Extensive experiments on three publicly available datasets show that the average F1-score of the proposed model is higher than 0.94,which significantly outperforms other benchmark models on high-dimensional datasets.
作者
杨晨龙
孙晔
刘晓悦
Yang Chenlong;Sun Ye;Liu Xiaoyue(College of Electrical Engineering,North China University of Science and Technology,Tangshan 063210,China;China Academy of Information and Communications Technology,Beijing 100191,China)
出处
《电子测量技术》
北大核心
2024年第17期38-46,共9页
Electronic Measurement Technology
基金
国家自然科学基金(42274056)
河北省自然科学基金(SJMYF202401)项目资助。
关键词
多元时间序列
异常检测
图注意力网络
门控机制
注意力机制
multivariate time-series
anomaly detection
graph attention network
gated mechanism
attention mechanism