Autonomous anomaly detection in multivariate time-series is essential for ensuring safety in industrial and aerospace systems, yet is hindered by high-dimensional signals and limited fault samples. This paper proposes a self-supervised autoencoder that integrates multi-scale convolutions (kernel sizes 3/5/7) with a Transformer encoder augmented by T5-style relative position bias, enabling joint modeling of local transient patterns and long-range temporal dependencies. To enhance representation learning under scarce anomaly labels, we leverage SimCLR-based contrastive pretraining to refine normal-data feature distributions. To address fragmented detections, we design an event-level aggregation strategy that merges window-level reconstruction errors via Top-k peak averaging and rule-based filtering. Evaluated on the SMAP benchmark and our in-house industrial dataset, named CAFUC2, our method achieves event-level F1 of 0.97 and 0.83, respectively outperforming traditional baseline methods and demonstrating robust generalization to real-world flight anomalies.
AudibertJ.MichiardiP.GuyardF.MartiS.ZuluagaM. A. (2020). Usad: Unsupervised anomaly detection on multivariate time series. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 3395–3404).
ChenT.KornblithS.NorouziM.HintonG. (2020). A simple framework for contrastive learning of visual representations. In Proceedings of the International Conference on Machine Learning (ICML) (pp. 1597–1607).
4.
ChevtchenkoS.RochaE. D. S.SantosM. C. M. D.MotaR. L.VieiraD. M.De AndradeE. C.De AraújoD. R. B. (2023). Anomaly detection in industrial machinery using IoT devices and machine learning: A systematic mapping. IEEE Access, 11, 128288–128305. https://doi.org/10.1109/ACCESS.2023.3333242
5.
ElíaI.PagolaM. (2024). Anomaly detection in smart-manufacturing era: a review. Available at SSRN 4815859.
6.
FejjariA.DelavaultA.CamilleriR.ValentinoG. (2025). A review of anomaly detection in spacecraft telemetry data. Applied Sciences, 15(10), 5653. https://doi.org/10.3390/app15105653
7.
GuanS.HeZ.MaS.GaoM. (2023). Conditional normalizing flow for multivariate time series anomaly detection. ISA Transactions, 143, 231–243. https://doi.org/10.1016/j.isatra.2023.09.002
8.
HilalW.GadsdenS. A.YawneyJ. (2022). Financial fraud: A review of anomaly detection techniques and recent advances. Expert Systems With Applications, 193, 116429. https://doi.org/10.1016/j.eswa.2021.116429
9.
HundmanK.ConstantinouV.LaporteC.ColwellI.SoderstromT. (2018). Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD) (pp. 387–395).
10.
KimS.ChungE.KangP. (2023). FEAT: A general framework for feature-aware multivariate time-series representation learning. Knowledge-Based Systems, 277, 110790. https://doi.org/10.1016/j.knosys.2023.110790
11.
LiD.ChenD.JinB.ShiL.GohJ.NgS.-K. (2019). MAD-GAN: Multivariate anomaly detection for time series data with generative adversarial networks. In Proceedings of the International Conference on Artificial Neural Networks (ICANN) (pp. 703–716).
12.
LiuW.YanL.MaN.WangG.MaX.LiuP.TangR. (2024). Unsupervised deep anomaly detection for industrial multivariate time series data. Applied Sciences, 14(2), 774. https://doi.org/10.3390/app14020774
13.
ParkD.HoshiY.KempC. C. (2018). A multimodal anomaly detector for robot-assisted feeding using an LSTM-based variational autoencoder. IEEE Robotics and Automation Letters, 3(3), 1544–1551. https://doi.org/10.1109/LRA.2018.2801475
14.
RuffL.VandermeulenR.GoernitzN.DeeckeL.SiddiquiS. A.BinderA.MüllerE.KloftM. (2018). Deep one-class classification. In Proceedings of the International Conference on Machine Learning (ICML) (pp. 4393–4402).
15.
SuY.ZhaoY.NiuC.LiuR.SunW.PeiD. (2019). Robust anomaly detection for multivariate time series through stochastic recurrent neural network. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (pp. 2828–2837).
16.
VaswaniA.ShazeerN.ParmarN.UszkoreitJ.JonesL.GomezA. N.KaiserŁPolosukhinI. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30, 5998–6008. https://doi.org/10.48550/arXiv.1706.03762
17.
VishwasB. V. K.MacharlaS. (2025). TimeGPT: The first foundation model for time series. In Time series forecasting using generative AI: Leveraging AI for precision forecasting (pp. 169–182). Springer.
18.
WangD.ChengM.LiuZ.LiuQ.ChenE. (2024). Diffusion auto-regressive transformer for effective self-supervised time series forecasting.
19.
WangF.JiangY.ZhangR.WeiA.XieJ.PangX. (2025). A survey of deep anomaly detection in multivariate time series: Taxonomy, applications, and directions. Sensors (Basel, Switzerland), 25(1), 190. https://doi.org/10.3390/s25010190
20.
XuJ.WuH.WangJ.LongM. (2021). Anomaly transformer: Time series anomaly detection with association discrepancy. arXiv preprint arXiv:2110.02642.
21.
YueZ.WangY.DuanJ.YangT.HuangC.TongY.XuB. (2022). TS2Vec: Towards universal representation of time series. Proceedings of the AAAI Conference on Artificial Intelligence, 36(8), 8980–8987. https://doi.org/10.1609/aaai.v36i8.20881
22.
ZongB.SongQ.MinM. R.ChengW.LumezanuC.ChoD.ChenH. (2018). Deep autoencoding Gaussian mixture model for unsupervised anomaly detection. Proceedings of the International Conference on Learning Representations (ICLR).
