Abstract
Fault detection plays an important role in safe operation and equipment maintenance of process industries. With the boom of online monitoring systems in process industries, the high availability of multi-channel measurement data motivates research into data-driven fault detection methods. Semi-supervised learning is a machine learning framework that trains on a small amount of labeled data and a large amount of unlabeled data, efficiently utilizing unlabeled raw data while leveraging critical label information to achieve detection accuracy. A novel semi-supervised fault detection method using self-adaptive training is proposed in this paper. By constantly calibrating target labels during the training process, most of the unlabeled samples can be correctly labeled. Experiments on the Tennessee Eastman Process (TEP) benchmark dataset is conducted to examine its performance. It achieves high detection accuracy using only partially labeled training data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chong, Y., et al.: Graph-based semi-supervised learning: a review. Neurocomputing 408, 216–230 (2020)
Pang, G., et al.: Deep learning for anomaly detection: a review. ACM Comput. Surv. (CSUR) 54(2), 1–38 (2021)
Mao, W., et al.: Online detection of bearing incipient fault with semi-supervised architecture and deep feature representation. J. Manuf. Syst. 55, 179–198 (2020)
de Sá, F.P.G., et al.: Wind turbine fault detection: a semi-supervised learning approach with automatic evolutionary feature selection. In: 2020 International Conference on Systems, Signals and Image Processing (IWSSIP). IEEE (2020)
Zhai, L., Jia, Q.: Simultaneous fault detection and isolation using semi-supervised kernel nonnegative matrix factorization. Can. J. Chem. Eng. 97(12), 3025–3034 (2019)
Fan, C., et al.: A study on semi-supervised learning in enhancing performance of AHU unseen fault detection with limited labeled data. Sustain. Cities Soc. 70, 102874 (2021)
Huang, L., Zhang, C., Zhang, H.: Self-adaptive training: beyond empirical risk minimization. Adv. Neural. Inf. Process. Syst. 33, 19365–19376 (2020)
Melo, A., et al.: Open benchmarks for assessment of process monitoring and fault diagnosis techniques: a review and critical analysis. Comput. Chem. Eng. 107964 (2022)
Downs, J.J., Vogel, E.F.: A plant-wide industrial process control problem. Comput. Chem. Eng. 17(3), 245–255 (1993)
Quiñones-Grueiro, M., et al.: Data-driven monitoring of multimode continuous processes: a review. Chemom. Intell. Lab. Syst. 189, 56–71 (2019)
Rieth, C.A., et al.: Issues and advances in anomaly detection evaluation for joint human-automated systems. In: Proceedings of the AHFE 2017 International Conference on Human Factors in Robots and Unmanned Systems. Advances in Human Factors in Robots and Unmanned Systems, 17–21 July 2017
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Song, K., Liu, C., Jiang, D. (2024). Semi-supervised Anomaly Detection on Industrial Process Data Using Self-adaptive Training. In: Ball, A.D., Ouyang, H., Sinha, J.K., Wang, Z. (eds) Proceedings of the UNIfied Conference of DAMAS, IncoME and TEPEN Conferences (UNIfied 2023). TEPEN IncoME-V DAMAS 2023 2023 2023. Mechanisms and Machine Science, vol 152. Springer, Cham. https://doi.org/10.1007/978-3-031-49421-5_74
Download citation
DOI: https://doi.org/10.1007/978-3-031-49421-5_74
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-49420-8
Online ISBN: 978-3-031-49421-5
eBook Packages: EngineeringEngineering (R0)