Skip to main content

Advertisement

Fault diagnosis using deep neural networks for industrial alarm sequence clustering

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Significant progress has been made in the field of industrial alarm management systems (AMS) in terms of diagnostic and prognostic accuracy. However, persistent challenges, such as poorly configured alarm setups and floods, contribute to an increased number of false alarms, consequently reducing the efficiency of the monitoring system. In addition, more sophisticated models and interactive visualization tools are needed to support supervisors and maintenance operators. This paper proposes a novel approach based on deep learning that combines autoencoder and self-organizing maps to extract valuable features and a clustering algorithm to identify related alarm groups. This bi-level methodology is applied to real manufacturing system datasets, demonstrating its effectiveness in identifying false alarms, reducing alarm sequence interpretation time, enhancing understanding of alarm interrelationships, and providing a basis for causal analysis and root cause identification. The approach also compares favorably with the classical methods in the literature, laying the foundation for improved industrial safety management. The system also offers maintenance recommendations to decision makers, further validating alarm sequences.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Algorithm 1
Fig. 4
Fig. 5
Fig. 6
Algorithm 2
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data Availability

The datasets utilized and/or examined in the present study can be accessed through the following reference [31].

References

  1. Belahcene M, Chouchane A, Benatia MA, et al (2014) 3d and 2d face recognition based on image segmentation. In: 2014 International Workshop on Computational Intelligence for Multimedia Understanding (IWCIM). IEEE, pp 1–5

  2. Benatia M, Louis A, Baudry D (2020) Alarm correlation to improve industrial fault management. IFAC-PapersOnLine 53(2):10485–10492

    Article  Google Scholar 

  3. Brik B, Messaadia M, Sahnoun M et al (2022) Fog-supported low-latency monitoring of system disruptions in industry 4.0: a federated learning approach. ACM Trans Cyber-Phys Syst 6(2):1–23

    Article  Google Scholar 

  4. Cai S, Palazoglu A, Zhang L et al (2019) Process alarm prediction using deep learning and word embedding methods. ISA Trans 85:274–283

    Article  Google Scholar 

  5. Chabane AN, Islam N, Zerr B (2017) Incremental clustering of sonar images using self-organizing maps combined with fuzzy adaptive resonance theory. Ocean Eng 142:133–144. https://doi.org/10.1016/j.oceaneng.2017.06.061

    Article  Google Scholar 

  6. Charbonnier S, Bouchair N, Gayet P (2016) Fault template extraction to assist operators during industrial alarm floods. Eng Appl Artif Intell 50:32–44

    Article  Google Scholar 

  7. Equipment E, Association M, Equipment E, et al (2015) Alarm systems: a guide to design, management and procurement. Alarm systems: a guide to design management and procurement. EEMUA, London, UK

  8. Faker O, Dogdu E (2019) Intrusion detection using big data and deep learning techniques. In: Proceedings of the 2019 ACM Southeast conference. pp 86–93

  9. Fernandes M, Corchado JM, Marreiros G (2022) Machine learning techniques applied to mechanical fault diagnosis and fault prognosis in the context of real industrial manufacturing use-cases: a systematic literature review. Appl Intell 52(12):14246–14280

    Article  Google Scholar 

  10. Forest F, Lebbah M, Azzag H et al (2021) Deep embedded self-organizing maps for joint representation learning and topology-preserving clustering. Neural Comput Appl 33(24):17439–17469

    Article  Google Scholar 

  11. ISA A (2009) Isa-18.2: Management of alarm systems for the process industries. International Society of Automation Durham, NC, USA

  12. Jia J, Feng C, Zhang T, et al (2020) Deep fault prediction with flexible weighted mining based alarm correlation analysis of communication networks. In: 2020 IEEE 20th International Conference on Communication Technology (ICCT). IEEE, pp 173–177

  13. Johnson SJ, Murty MR, Navakanth I (2023) A detailed review on word embedding techniques with emphasis on word2vec. Multimed Tools Appl 1–29

  14. Khorram A, Khalooei M, Rezghi M (2021) End-to-end cnn+ lstm deep learning approach for bearing fault diagnosis. Appl Intell 51:736–751

    Article  Google Scholar 

  15. Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biol Cybern 43(1):59–69

    Article  Google Scholar 

  16. Lai S, Chen T (2017) A method for pattern mining in multiple alarm flood sequences. Chem Eng Res Des 117:831–839

    Article  Google Scholar 

  17. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444

    Article  Google Scholar 

  18. Liu Y (2019) Zhu L (2019) A new intrusion detection and alarm correlation technology based on neural network. EURASIP J Wirel Commun Netw 1:1–10

  19. Messaadia M, Baudry D, Louis A et al (2016) Plm adoption in smes context. Comput-Aided Des Appl 13(5):618–627

    Article  Google Scholar 

  20. Mustafa FE, Ahmed I, Basit A et al (2023) A review on effective alarm management systems for industrial process control: barriers and opportunities. Int J Crit Infrastruc Protect 100599

  21. Nait Chabane A, Zerr B, Le Chenadec G (2012) Range-independent segmentation of sidescan sonar images with unsupervised SOFM Algorithm (Self-Organizing Feature Maps). Proc Meetings Acoust 17(1):070005. https://doi.org/10.1121/1.4764505

    Article  Google Scholar 

  22. Peng B, Xia H, Lv X et al (2022) An intelligent fault diagnosis method for rotating machinery based on data fusion and deep residual neural network. Appl Intell 52(3):3051–3065

    Article  Google Scholar 

  23. Perdisci R, Giacinto G, Roli F (2006) Alarm clustering for intrusion detection systems in computer networks. Eng Appl Artif Intell 19(4):429–438

    Article  Google Scholar 

  24. Pulido B, Zamarreño JM, Merino A et al (2019) State space neural networks and model-decomposition methods for fault diagnosis of complex industrial systems. Eng Appl Artif Intell 79:67–86

    Article  Google Scholar 

  25. Remadna A, Benatia A, Louis A et al (2018) A predictive analysis data-based for additive manufacturing. In: Press IOS (ed) Advances in manufacturing technology XXXII. Amsterdam, The, Netherlands, pp 125–130

    Google Scholar 

  26. Rouvellou I, Hart GW (1995) Automatic alarm correlation for fault identification. In: Proceedings of INFOCOM’95. IEEE, pp 553–561

  27. Sarkar J, Saha S, Sarkar S (2022) Efficient anomaly identification in temporal and non-temporal industrial data using tree based approaches. Appl Intell 1–34

  28. Serradilla O, Zugasti E, Rodriguez J et al (2022) Deep learning models for predictive maintenance: a survey, comparison, challenges and prospects. Appl Intell 52(10):10934–10964

    Article  Google Scholar 

  29. Shirkhorshidi AS, Aghabozorgi S, Wah TY (2015) A comparison study on similarity and dissimilarity measures in clustering continuous data. PLoS ONE 10(12):e0144059

    Article  Google Scholar 

  30. Stauffer T, Sands N, Dunn D (2010) Alarm management and isa-18–a journey, not a destination. In: Texas A &M instrumentation symposium

  31. Tosato D, Dalle Pezze D, Masiero C et al (2020) Alarm logs in packaging industry (ALPI). IEEE Dataport. https://doi.org/10.21227/nfv6-k750

  32. Zhao B, Luo G (2016) An alarm correlation algorithm based on similarity distance and deep network. In: International conference on intelligent computing. Springer, pp 359–368

Download references

Author information

Authors and Affiliations

Authors

Contributions

Each author has contributed equally to the research and writing of this article. All authors have participated in study design, data analysis, and manuscript preparation. In addition, each author has read and approved the final manuscript.

Corresponding author

Correspondence to M’hammed Sahnoun.

Ethics declarations

Competing Interests

The authors declare that they have no competing interests.

Ethical and Informed Consent for Data Used

The research presented in this paper does not involve any human or animal subjects. All data used in this study are publicly available. Therefore, no ethical approval or informed consent was required for this research.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file 1 (zip 18848 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Benatia, M.A., Chabane, A.N., Sahnoun, M. et al. Fault diagnosis using deep neural networks for industrial alarm sequence clustering. Appl Intell 55, 220 (2025). https://doi.org/10.1007/s10489-024-06161-y

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10489-024-06161-y

Keywords