Skip to main content
SpringerLink
Log in

Trace induction for complete manufacturing process model discovery

  • ORIGINAL ARTICLE
  • Published:
The International Journal of Advanced Manufacturing Technology Aims and scope Submit manuscript

Abstract

In industrial automation, there are numerous use cases for a model representing the equipment’s sequence of operations. Not only can such a model be used as a debugging aid, allowing users to observe the current state of the machinery at a glance, but it also can serve as a foundation for process improvements. Annotated process models can help pinpoint bottlenecks within the system, and a combination of models obtained from identical machines can be used to create a best-case baseline to which the devices can be optimised. Typically, the models used for such activities have been created during the equipment’s design phase, which means that many of the changes made during commissioning, start-up, and production are not reflected. The research domain of process mining suggests that an accurate model can be obtained from an activity log. Since most industrial processes are controlled by Programmable Logic Controllers (PLCs), which offer the capability of external access through Open Platform Communications (OPC), such a log can be created automatically. The theory is that process mining algorithms can then be used to discover the desired model from the data recorded. Unfortunately, it turns out that this whole procedure is a game of chance. The quality of the discovered models strongly depends on the logged data. Not only can the records be flawed, but also the information needed to discover a complete model might not have been observed at all. To better judge the quality of the discovered models, numerous quality metrics have been proposed, which in the authors’ opinion are a good guess at best. The industrial automation domain demands complete models, which cannot be guaranteed by any process mining algorithm unless it is known that the log contains all the data needed. This paper shows that for industrial equipment, it is possible to reason through the evaluation of a single recorded case, which case traces are required to guarantee that the discovered model will be complete. In the next step, the authors then introduced the concept of ‘trace induction’, which takes advantage of the fact that a PLC controls the observed processes. A minor change within the PLC’s logic is used to force the process to execute the desired traces on demand. The resulting, minimalistic log can then be analysed by the αLC-algorithm to create a guaranteed complete, model.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23

Similar content being viewed by others

References

  1. Kalenkova AA, Van Der Aalst WMP, Lomazova IA, Rubin VA (2017) Process mining using Bpmn: relating event logs and process models. Softw Syst Model 16:1019–1048. https://doi.org/10.1007/s10270-015-0502-0

    Article  Google Scholar 

  2. Browning TR (2002) Process integration using the design structure matrix. Syst Eng 5:180–193. https://doi.org/10.1002/sys.10023

    Article  Google Scholar 

  3. Lee J (2003) E-manufacturing—fundamental, tools, and transformation. Robotics and computer-integrated manufacturing. Robot Comput Integr Manuf 19:501–507. https://doi.org/10.1016/S0736-5845(03)00060-7

    Article  Google Scholar 

  4. Qi Q, Tao F (2018) Digital twin and big data towards smart manufacturing and Industry 4.0: 360 degree comparison. IEEE Access 6:3585–3593. https://doi.org/10.1109/ACCESS.2018.2793265

    Article  Google Scholar 

  5. Jaber AA, Bicker R (2014) The state of the art in research into the condition monitoring of industrial machinery. Int J Curr Eng Technol 4:1986–2001

    Google Scholar 

  6. Banerjee TP, Das S (2012) Multi-sensor data fusion using support vector machine for motor fault detection. Inf Sci 217:96–107. https://doi.org/10.1016/j.ins.2012.06.016

    Article  Google Scholar 

  7. Van Der Aalst W, Adriansyah A, De Medeiros AKA, Arcieri F, Baier T, Blickle T, Bose JC, Van Den Brand P, Brandtjen R, Buijs J, Burattin A (2011) Process mining manifesto, business process management workshops. Bpm 2011. Lect Notes Bus Inf Process 99:169–194. https://doi.org/10.1007/978-3-642-28108-2_19

    Article  Google Scholar 

  8. Van Der Aalst WMP (2018) Relating process models and event logs-21 conformance propositions. In: Ceur Workshop Proceedings, Aachen, Germany, pp 56–74

  9. Leemans SJJ, Fahland D, Van Der Aalst WMP (2018) Scalable process discovery and conformance checking. Softw Syst Model 17:599–631. https://doi.org/10.1007/s10270-016-0545-x

    Article  Google Scholar 

  10. De Weerdt J, De Backer M, Vanthienen J, Baesens B (2011) A robust f-measure for evaluating discovered process models. In: 2011 IEEE Symposium on Computational Intelligence and Data Mining (Cidm), Paris, France, pp 148–155

  11. Li C, Reichert M, Wombacher A (2008) Mining process variants: goals and issues. In: 2008 IEEE International Conference on Services Computing, Honolulu, USA, pp 573–576

  12. Günther CW, Rozinat A (2012) Disco: discover your processes. In: Demonstration Track of the 10th International Conference on Business Process Management (Bpm 2012), Tallin, Estonia, pp 40–44

  13. Wen L, Wang J, Van Der Aalst WMP, Huang B (2009) A novel approach for process mining based on event types. J Intell Inf Syst 32:163–190. https://doi.org/10.1007/s10844-007-0052-1

    Article  Google Scholar 

  14. Burattin A (2015) Heuristics miner for time interval. In: Process mining techniques in business environments, process mining techniques in business environments, pp 85–95, DOI https://doi.org/10.1007/978-3-319-17482-2_11, (to appear in print)

  15. Hu H, Li Z, Wang A (2006) Mining of flexible manufacturing system using work event logs and petri nets. In: International Conference on Advanced Data Mining and Applications Adma 2006, Xian, China, pp 360–387

  16. Son S, Yahya BN, Song M, Choi S, Hyeon J, Lee B, Jang Y, Sung N (2014) Process mining for manufacturing process analysis: a case study. In: Proceeding of 2nd Asia Pacific Conference on Business Process Management, Brisbane, Australia

  17. Yahya BN (2014) The development of manufacturing process analysis: lesson learned from process mining. Jurnal Teknik Industri 16:97–107. https://doi.org/10.9744/jti.16.2.95-106

    Article  Google Scholar 

  18. Farooqui A, Bengtsson K, Falkman P, Fabian M (2018) From factory floor to process models: a data gathering approach to generate, transform, and visualize manufacturing processes. CIRP J Manuf Sci Technol 24:6–16. https://doi.org/10.1016/j.cirpj.2018.12.002

    Article  Google Scholar 

  19. Nowaczyk S, Sant’Anna A, Calikus E, Fan Y (2018) Monitoring equipment operation through model and event discovery. In: Intelligent data engineering and automated learning – Ideal 2019, Madrid, Spain, pp 41–53

  20. Steward DS (1981) The design structure system: a method for managing the design of complex systems. IEEE Trans Eng Manag EM-28:71–74. https://doi.org/10.1109/TEM.1981.6448589

    Article  Google Scholar 

  21. Eppinger SD, Browning TR (2012) Design structure matrix methods and applications. In: Design structure matrix methods and applications. MIT Press, Cambridge

  22. Browning TR (2001) Applying the design structure matrix to system decomposition and integration problems: a review and new directions. IEEE Trans Eng Manag 48:292–306. https://doi.org/10.1109/17.946528

    Article  Google Scholar 

  23. Van Der Aalst W, Mining Process (2016) Data science in action. In: Process mining: data science in action, edition 1. Springer, Berlin, Heidelberg, pp 3–23

  24. Sommer M (2012) Zeitliche Darstellung Und Modellierung Von Prozessen Mit Hilfe Von Gantt-Diagrammen, M.S. thesis, University of Ulm, Ulm, Germany

  25. Koehler W, Jing Y (2018) Automated, nomenclature based data point selection for industrial event log generation. In: Intelligent data engineering and automated learning – Ideal 2018, Cham, Switzerland, pp 31–40

  26. Shimm G (2004) Mining exact models of concurrent workflows. Comput Ind 53:265–281. https://doi.org/10.1016/j.compind.2003.10.003

    Article  Google Scholar 

Download references

Acknowledgements

The authors would like to thank Opel Automobile GmbH and Vauxhall for sponsoring this research, and providing the equipment and workforce necessary for the evaluation trials.

Author information

Authors and Affiliations

  1. Coventry University, Priory St, Coventry, CV1 5FB, UK

    Wolfgang Koehler & Yanguo Jing

Authors
  1. Wolfgang Koehler
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yanguo Jing
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wolfgang Koehler.

Additional information

Publisher’s note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Koehler, W., Jing, Y. Trace induction for complete manufacturing process model discovery. Int J Adv Manuf Technol 110, 29–43 (2020). https://doi.org/10.1007/s00170-020-05747-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00170-020-05747-3

Keywords

Search

Navigation