2000 character limit reached
Diagnosis driven Anomaly Detection for CPS (2311.15924v1)
Published 27 Nov 2023 in cs.LG and cs.AI
Abstract: In Cyber-Physical Systems (CPS) research, anomaly detection (detecting abnormal behavior) and diagnosis (identifying the underlying root cause) are often treated as distinct, isolated tasks. However, diagnosis algorithms require symptoms, i.e. temporally and spatially isolated anomalies, as input. Thus, anomaly detection and diagnosis must be developed together to provide a holistic solution for diagnosis in CPS. We therefore propose a method for utilizing deep learning-based anomaly detection to generate inputs for Consistency-Based Diagnosis (CBD). We evaluate our approach on a simulated and a real-world CPS dataset, where our model demonstrates strong performance relative to other state-of-the-art models.
- Raymond Reiter. A theory of diagnosis from first principles. Artificial intelligence, 32(1):57–95, 1987.
- On residual-based diagnosis of physical systems. Engineering Applications of Artificial Intelligence, 109:104636, 2022. ISSN 0952-1976. doi:https://doi.org/10.1016/j.engappai.2021.104636.
- Combining model-based diagnosis and data-driven anomaly classifiers for fault isolation. Control Engineering Practice, 80:146–156, 2018.
- A combined diagnosis system design using model-based and data-driven methods. In Control and Fault-Tolerant Systems (SysTol), 2016 3rd Conference on, pages 177–182. IEEE, 2016.
- An evaluation of anomaly detection and diagnosis in multivariate time series. IEEE Trans Neural Netw Learn Syst, PP, August 2022.
- Diagnosing systems through approximated information. In Annual Conference of the PHM Society, volume 13, 2021.
- Learning a causal system description for diagnosing physical systems. In Proceedings of the 33rd International Workshop on Principles of Diagnosis, Toulouse, France., 2022.
- Model-based diagnosis in the real world: lessons learned and challenges remaining. In IJCAI, volume 99, pages 1393–1400. Citeseer, 1999.
- Model-based diagnosis for cyber-physical production systems based on machine learning and residual-based diagnosis models. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 2727–2735, 2019.
- Machine learning for cyber-physical systems. Digital Transformation: Core Technologies and Emerging Topics from a Computer Science Perspective, page 415, 2023.
- A dataset to support research in the design of secure water treatment systems. In Critical Information Infrastructures Security, pages 88–99. Springer International Publishing, 2017.
- Patrick Rodler. How should i compute my candidates? a taxonomy and classification of diagnosis computation algorithms. In 33rd International Workshop on Principle of Diagnosis – DX 2022, 2022.
- Catio-a framework for model-based diagnosis of cyber-physical systems. In International Symposium on Methodologies for Intelligent Systems, pages 267–276. Springer, 2020.
- Finding faults: A scoping study of fault diagnostics for industrial cyber–physical systems. Journal of systems and software, 168:110638, 2020.
- A survey of modeling for prognosis and health management of industrial equipment. Advanced Engineering Informatics, 50:101404, 2021.
- Data-driven fault diagnosis analysis and open-set classification of time-series data. Control Engineering Practice, 121:105006, 2022.
- Daniel Jung. Automated design of grey-box recurrent neural networks for fault diagnosis using structural models and causal information. In Learning for Dynamics and Control Conference, pages 8–20. PMLR, 2022.
- Deep learning for anomaly detection: A review. ACM Comput. Surv., 54(2):1–38, March 2021.
- Learning graph structures with transformer for multivariate Time-Series anomaly detection in IoT. IEEE Internet of Things Journal, 9(12):9179–9189, June 2022a.
- HS-TCN: A semi-supervised hierarchical stacking temporal convolutional network for anomaly detection in IoT. In 2019 IEEE 38th International Performance Computing and Communications Conference (IPCCC), pages 1–7, October 2019.
- Graph neural Network-Based anomaly detection in multivariate time series. AAAI, 35(5):4027–4035, May 2021.
- MAD-GAN: Multivariate anomaly detection for time series data with generative adversarial networks. In Artificial Neural Networks and Machine Learning – ICANN 2019: Text and Time Series, pages 703–716. Springer International Publishing, 2019.
- A GAN approach for anomaly detection in spacecraft telemetries. In 17th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2022), pages 393–402. Springer Nature Switzerland, 2023.
- Semisupervised anomaly detection of multivariate time series based on a variational autoencoder. Appl. Intell., July 2022b.
- Anomaly detection for time series using VAE-LSTM hybrid model. In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 4322–4326, May 2020.
- Data-Driven correlation of cyber and physical anomalies for holistic system health monitoring. IEEE Access, 9:163138–163150, 2021.
- beta-vae: Learning basic visual concepts with a constrained variational framework. In ICLR, 2017.
- An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. urlhttp://arxiv.org/abs/1803.01271v2, 2018.
- A Time Convolutional Network Based Outlier Detection for Multidimensional Time Series in Cyber-Physical-Social Systems. IEEE Access, 8:74933–74942, 2020. ISSN 2169-3536. doi:10.1109/ACCESS.2020.2988797.