Abstract
Alarm systems are important assets for plant safety and efficiency in a variety of industries, including power and utility, process and manufacturing, oil and gas, and communications. Especially in the process-based industry, alarm systems collect a huge amount of data in the field that requires operators to take action carefully. However, existing industrial alarm systems suffer from poor performance, mostly with alarm overloading and alarm flooding. Therefore, this problem creates an opportunity to implement machine learning models in order to predict upcoming alarms in the industry. In this way, the operators can take the necessary actions automatically while they are using their capacity for other unpredicted alarms. This study provides an overview of alarm prediction methods used in industrial alarm systems with the context of their classification types. In addition, a comparative analysis was conducted between two state-of-the-art deep learning models, namely Long Short-Term Memory (LSTM) and Transformer, through a benchmarking process. The experimental results of both models were evaluated and contrasted to identify their respective strengths and weaknesses. Moreover, this study identifies research gaps in alarm prediction, which can guide future research for better alarm management systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Goel, P., Datta, A., Mannan, M.S.: Industrial alarm systems: challenges and opportunities. J. Loss Prev. Process Ind. 50, 23–36 (2017)
ANSI/ISA, “Management of alarm systems for the process industries,” (2016)
EEMUA, “Alarm systems: Guide to design, management and procurement,” EEMUA Publication 191 Digital, vol. 3, pp. 23–36 (1999)
Beebe, D., Ferrer, S., Logerot, D.: Alarm floods and plant incidents. vol. 17 (2012)
PCC, T.: The explosion and fires at the Texaco refinery, Milford haven (1994)
Wang, J., Yang, F., Chen, T., Shah, S.L.: An overview of industrial alarm systems: main causes for alarm overloading, research status, and open problems. IEEE Trans. Autom. Sci. Eng. 13(2), 1045–1061 (2016)
Goutte, C., Gaussier, E.: A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. In: Losada, D.E., Fernández-Luna, J.M. (eds.) ECIR 2005. LNCS, vol. 3408, pp. 345–359. Springer, Heidelberg (2005). https://doi.org/10.1007/978-3-540-31865-1_25
Pezze, D.D., Masiero, C., Tosato, D., Beghi, A., Susto, G.A.: Formula: a deep learning approach for rare alarms predictions in industrial equipment. IEEE Trans. Autom. Sci. Eng. 1–12 (2021)
Holmbacka, S., et al.: Alarm prediction in LTE networks. In: 2018 25th International Conference on Telecommunications (ICT), pp. 341–345 (2018)
Boldt, M., Ickin, S., Borg, A., Kulyk, V., Gustafsson, J.: Alarm prediction in cellular base stations using data-driven methods. IEEE Trans. Netw. Serv. Manag. 18(2), 1925–1933 (2021)
Tamascelli, N., Paltrinieri, N., Cozzani, V.: Predicting chattering alarms: a machine learning approach. Comput. Chem. Eng. 143, 107122 (2020)
Dix, M., et al.: An AI-based alarm prediction in industrial process control systems. In: 2022 IEEE International Conference on Big Data and Smart Computing (BigComp), pp. 242–245 (2022)
Zhuang, H., Zhao, Y., Yu, X., Li, Y., Wang, Y., Zhang, J.: Machine-learning-based alarm prediction with GANs-based self-optimizing data augmentation in large-scale optical transport networks. In: International Conference on Computing, Networking and Communications (ICNC), pp. 294–298 (2020)
Cai, S., Palazoglu, A., Zhang, L., Hu, J.: Process alarm prediction using deep learning and word embedding methods. ISA Trans. 85, 274–283 (2019)
Wang, X., Liang, D.: LSTM-based alarm prediction in the mobile communication network. In: IEEE 6th International Conference on Computer and Communications (ICCC), pp. 561–567 (2020)
Chatterjee, J., Dethlefs, N.: A dual transformer model for intelligent decision support for maintenance of wind turbines. In: International Joint Conference on Neural Networks (IJCNN), pp. 1–10 (2020)
Xing, X., Zhao, Y., Li, Y., Zhang, J.: Knowledge-based collective self-learning for alarm prediction in real multi-domain autonomous optical networks. In: 16th International Conference on the Design of Reliable Communication Networks DRCN 2020, pp. 1–5 (2020)
Silva, M., Carvalho, R., Almeida, T.: Evaluation of a sliding window mechanism as data augmentation over emotion detection on speech. Acad. J. Comput. Eng. Appl. Math. 2, 11–18 (2021)
Kondaveeti, S.R., Izadi, I., Shah, S.L., Shook, D.S., Kadali, R., Chen, T.: Quantification of alarm chatter based on run length distributions. Chem. Eng. Res. Des. 91(12), 2550–2558 (2013)
Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need (2017)
Acknowledgement
This research was partially funded by Koç University - Tüpras Energy Research Center (KUTEM) and the TUBITAK 2247-A Award (Project No. 121C338). We thank Tüpraş team for the oil refinery alarm data and useful feedback.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Görgülü, H., Özkasap, Ö. (2023). Machine Learning Methods for Alarm Prediction in Industrial Informatics: Review and Benchmark. In: Jove, E., Zayas-Gato, F., Michelena, Á., Calvo-Rolle, J.L. (eds) Distributed Computing and Artificial Intelligence, Special Sessions II - Intelligent Systems Applications, 20th International Conference. DCAI 2023. Lecture Notes in Networks and Systems, vol 742. Springer, Cham. https://doi.org/10.1007/978-3-031-38616-9_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-38616-9_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-38615-2
Online ISBN: 978-3-031-38616-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)