杨柳,薛晨兴,闻毓民,刘恒

• 1:西南交通大学信息科学与技术学院
• 2:西南交通大学土木工程学院

摘要(Abstract)：

时序异常检测是工业监控与智能运维领域的重要技术，也是人工智能与数据挖掘课程的核心实验内容。针对教学实验中周期性特征利用不足、关联模式刻画不充分等问题，设计了基于频域增强与关联差异的时序异常检测实验模型FreqAT。该模型以Anomaly Transformer为基础，通过频域特征增强、频域感知关联差异和自适应归一化3个模块，提升对周期性异常的检测能力。在SMD等公开数据集上，F_1分数相比次优方法平均提升约2.1%。该实验设计有助于学生进一步理解频域特征建模与关联差异机制，并可为相关课程实践教学提供参考。

关键词(KeyWords)： 时序异常检测;频域特征;关联差异;自适应归一化;Transformer

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金铁路基础研究联合基金项目(U2468201);; 四川省科技厅省院省校合作项目(2026YFHZ0225);; 2024-2026年四川省高等教育人才培养质量和教学改革项目(JG2024-0320);; 2025年四川省研究生优质教育教学资源建设项目(YJGXM25-C036);; 西南交通大学2024年本科教育教学研究与改革项目(JG2024018);; 西南交通大学2025年学位与研究生教育教学改革项目(YJG6-2025-Y015)

作者(Author): 杨柳,薛晨兴,闻毓民,刘恒

DOI: 10.19927/j.cnki.syyt.2026.10.007

参考文献(References)：

• [1]Xu J,Wu H,Wang J,et al. Anomaly transformer:Time series anomaly detection with association discrepancy[C]∥International Conference on Learning Representations(ICLR). Online:OpenReview,2022.
• [2]Zhou T,Ma Z,Wen Q,et al. FEDformer:Frequency enhanced decomposed transformer for long-term series forecasting[C]∥International Conference on Machine Learning(ICML). Baltimore,MD,USA:PMLR,2022:27268-27286.
• [3]Wu H, Xu J, Wang J, et al. Autoformer:Decomposition transformers with auto-correlation for long-term series forecasting[C]∥Advances in Neural Information Processing Systems 34(Neur IPS). Online:Curran Associates,2021:22419-22430.
• [4]Kim T,Kim J,Tae Y,et al. Reversible instance normalization for accurate time-series forecasting against distribution shift[C]∥International Conference on Learning Representations(ICLR).Online:OpenReview,2022.
• [5]Lv J,Wang Y,Chen S. Adaptive multivariate time-series anomaly detection[J]. Information Processing&Management,2023,60(4):103383.
• [6]Zhou H Y,Zhang S H,Peng J Q,et al. Informer:Beyond efficient transformer for long sequence time-series forecasting[C]∥Proceedings of the AAAI Conference on Artificial Intelligence.Online:AAAI Press,2021,35(12):11106-11115.
• [7]李岳，程春雨，吴振宇．信号失真度测量装置设计[J]．实验室研究与探索，2023,42(10):89-93.
• [8]Vaswani A,Shazeer N,Parmar N,et al. Attention is all you need[C]//Advances in Neural Information Processing Systems 30(Neur IPS). NY,USA:Curran Associates,Inc. 2017:5998-6008.
• [9]Kullback S,Leibler R A. On information and sufficiency[J]. The Annals of Mathematical Statistics,1951,22(1):79-86.
• [10]邱鹏，刘汉忠，黄晓华．基于混合深度神经网络的异常检测方法[J]．实验室研究与探索，2023,42(9):73-77.
• [11]Su Y, Zhao Y, Niu C, et al. Robust anomaly detection for multivariate time series through stochastic recurrent neural network[C]∥Proceedings of the 25 th ACM SIGKDD International Conference on Knowledge Discovery&Data Mining(KDD).Anchorage,AK,USA:ACM,2019:2828-2837.
• [12]Hundman K,Constantinou V,Laporte C,et al. Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding[C]∥Proceedings of the 24 th ACM SIGKDD International Conference on Knowledge Discovery&Data Mining(KDD). London,United Kingdom:ACM,2018:387-395.
• [13]Abdulaal A,Lancewicki T. Real-time synchronization in neural networks for multivariate time series anomaly detection[C]∥2021IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP). Toronto, ON, Canada:IEEE, 2021:3570-3574.
• [14]Mathur A P,Tippenhauer N O. SWaT:A water treatment testbed for research and training on ICS security[C]∥2016 International Workshop on Cyber-Physical Systems for Smart Water Networks(CySWater). Vienna,Austria:IEEE,2016:31-36.
• [15]李丹，卢琰，吴佩珊，等．基于改进随机森林集成模型的疾病风险预测[J]．实验室研究与探索，2023,42(9):95-99.
• [16]Zhou B,Liu S,Hooi B,et al. BeatGAN:Anomalous rhythm detection using adversarially generated time series[C]∥Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. Macao,China:I J CAI,2019:4433-4439.
• [17]Shen L,Li Z,Kwok J. Timeseries anomaly detection using temporal hierarchical one-class network[C]∥Advances in Neural Information Processing Systems 33(Neur IPS). Online:Curran Associates,2020:13016-13026.