Skip to main content
SpringerLink
Log in

A Density-based Clustering Approach for Monitoring of Injection Moulding Machine

  • Robot and Applications
  • Published:
International Journal of Control, Automation and Systems Aims and scope Submit manuscript

Abstract

Fault Detection and Isolation (FDI) is a crucial and challenging problem in many industrial applications and continues to be an on-going research issue in the control community. In the literature, model-based techniques are mostly employed to generate residuals for diagnosis and decision-making. In this paper, we focus on FDI problem using a novel based-clustering approach. The key idea is to restrict each fault to be a data cluster with high-density gathering the most similar objects. In this way, the algorithm does not require prior analytic models to start. It uses rather a density measurement to detect and isolate cluster’s regions. The overall algorithm is expanded around two fundamental steps: cluster domain description and density-based clustering. To address properly the requirements of system control and monitoring, the algorithm is designed to work in real-time as observations are acquired and it is endowed with specific tools for data mining and feature extraction. A study case is proposed consisting of a plastic Injection Molding Machine (IMM) to prove the effectiveness of the method.

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.

Similar content being viewed by others

References

  1. M. Thirumarimurugan, N. Bagyalakshmi, and P. Paarkavi, “Comparison of fault detection and isolation methods: A review,” Proc. of 10th International Conference on Intelligent Systems and Control, pp. 1–6, January 2016.

  2. F. Theljani, K. Lasbidi, S. Zidi, and M. Ksouri, “Tennessee Eastman process diagnosis based on dynamic classification with SVDD,” Journal of Dynamic Systems, Measurement and Control, vol. 137, no. 9, pp. 1–10, September 2015.

    Article  Google Scholar 

  3. F. Theljani, K. Lasbidi, S. Zidi, and M. Ksouri, “An efficient density-based algorithm for data clustering,” International Journal on Artificial Intelligence Tools, vol. 26, no. 4, pp. 1–21, January 2017.

    Article  Google Scholar 

  4. Y.-J. Yoo, “Fault detection method using multi-mode principal component analysis based on Gaussian mixture model for sewage source heat pump system,” International Journal of Control, Automation and Systems, vol. 17, pp. 2125–2134, May 2019.

    Article  Google Scholar 

  5. X. Liu, Y. Wu, Y. Zhang, and S. Xiao, “A control method to make LQR robust: A planes cluster approaching mode,” International Journal of Control, Automation and Systems, vol. 12, pp. 302–308, April 2014.

    Article  Google Scholar 

  6. X. Hua and S. Ding, “Incremental learning algorithm for support vector data description,” Journal of Software, vol. 6, no. 7, pp. 1166–1173, July 2011.

    Article  Google Scholar 

  7. R-R. Sillito and R-B. Fisher, “Incremental one-class learning with bounded computational complexity,” Proc. of 17th International Conference on Artificial Neural Networks, Berlin 2007.

  8. E. Vanem and A. Brandsaeter, “Cluster-based anomaly detection in condition monitoring of a marine engine system,” Proc. of Prognostics and System Health Management Conference, pp. 20–31, Chongqing, 2018.

  9. F. Theljani, K. Laabidi, S. Zidi, and M. Ksouri, “Convex hull based clustering algorithm,” International Journal of Artificial Intelligence, vol.10, no. 13, pp. 51–70, March 2013.

    Google Scholar 

  10. J. Xu, “Constructing a fast algorithm for multi-label classification with support vector data description,” Proc. of the 10th IEEE International Conference on Granular Computing, pp. 817–821, August 2010.

  11. P. Liu, D. Zhou, and N. Wu, “VDBSCAN: Varied density based spatial clustering of application with noise,” Proc. of the International Conference on Service Systems and Service Management, pp. 1–4, June 2007.

  12. A. Ram, S. Jalal, A-S. Jalal, and M. Kumar, “A density based algorithm for discovery density varied cluster in large spatial databases,” International Journal of Computer Application, vol. 3, no. 6, pp. 1–4, June 2010.

    Article  Google Scholar 

  13. D. Birant and A. Kut, “ST-DBSCAN: An algorithm for clustering spatial-temporal data,” Data and Knowledge Engineering vol. 60, no. 01, pp. 208–221, January 2007.

    Article  Google Scholar 

  14. D. T. Pham, S-S. Dimov, and C.-D. Nguyen, “An incremental k-means algorithm,” Proc. of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, vol. 218, no. 7, pp. 783–795, July 2004.

    Google Scholar 

  15. G.-Y. Tang, “A discrete version of Green’s theorem,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. PAMI-4, pp. 242–249, March 1982.

    Article  Google Scholar 

  16. X.-Z. Wang, Data Mining and Knowledge Discovery for Process Monitoring and Control, Springer-Verlag, London, 1999.

    Book  Google Scholar 

  17. A. Belkadi and P. Billaudel, “Real-time adaptive fault detection and isolation on a high-speed multi-injection molding machine,” Proc. of the 4th Conference on Control and Fault Tolerant Systems, pp. 62–67, September 2019.

  18. B. Zhou and H. Ye, “A study of polynomial fit-based methods for qualitative trend analysis,” Journal of Process Control, vol. 37, pp. 21–33, January 2016.

    Article  Google Scholar 

  19. J. Colomer, J. Melendez, and F-I. Gamero, “A qualitative case-based approach for situation assessment in dynamic systems: Application in a two tank system,” IFAC Proceedings Volumes, vol. 36, no. 5, pp. 669–674, 2003.

    Article  Google Scholar 

  20. J. Colomer and J. Melendez, “A family of FIR differentiators based on a polynomial least squares estimation,” Proc. of the European Control Conference, pp. 2802–2807, September 2001.

  21. B. Ribeiro, “Support vector machines for quality monitoring in a plastic injection molding process,” IEEE Trans. on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 35, no. 3, pp. 401–410, August 2005.

    Article  Google Scholar 

  22. O. Ogorodnyk and K. Martinsen, “Monitoring and control for thermoplastics injection molding a review,” Procedia CIRP, vol. 67, pp. 380–385, 2018.

    Article  Google Scholar 

  23. N. Costa and B. Ribeiro, “A neural prediction model for monitoring and fault diagnosis of a plastic injection moulding process,” Proc. of the European Control Conference, pp. 2381–2385, August 1999.

  24. R. Dubay, B. Pramujati, J. Han, and F. Strohmaie, “An investigation on the application of predictive control for controlling screw position and velocity on an injection molding machine,” Polymer Engineering and Science, vol. 47, no. 4, pp. 390–399, March 2007.

    Article  Google Scholar 

  25. F. Theljani, K. Laabidi, M. Ksouri, and S. Zidi, “New approach for systems monitoring based on semi-supervised classification,” Proc. of International Conference on Communications, Computing and Control Applications, pp. 1–6, March 2011.

  26. U.-V. Luxburg, “A tutorial on spectral clustering,” Statistics and Computing, vol. 17, pp. 395–416, August 2007.

    Article  MathSciNet  Google Scholar 

  27. A.-M. Bakr, N.-M. Ghanem, and M.-A. Ismail, “Efficient incremental density-based algorithm for clustering large datasets,” Alexandria Engineering Journal, vol. 54, no. 4, pp. 1147–1154, December 2015.

    Article  Google Scholar 

  28. S. Sarkar, V. Melnykov, and R. Zheng, “Gaussian mixture modeling and model-based clustering under measurement inconsistency,” Advances in Data Analysis and Classification, vol. 14, pp. 379–413, May 2020.

    Article  MathSciNet  Google Scholar 

  29. J. Wang, W. Zhang, and J. Zhou, “Fault detection with data imbalance conditions based on the improved bilayer convolutional neural network,” Industrial and Engineering Chemistry Research, vol. 59, pp. 5891–5904, March 2020.

    Article  Google Scholar 

  30. R. Wang, J. Wang, J. Zhou, and H. Wu, “Fault diagnosis based on the integration of exponential discriminant analysis and local linear embedding,” The Canadian Journal of Chemical Engineering., vol. 96, pp. 463–483, June 2018.

    Article  Google Scholar 

  31. F. Theljani, K. Laabidi, S. Zidi, and M. Ksouri, “Tennessee Eastman process diagnosis based on dynamic classification with SVDD,” Journal of Dynamic Systems, Measurement, and Control, vol. 137, no. 9, p. 091006, September 2015.

    Article  Google Scholar 

  32. X. Chen, J. Wang, and J.-L. Zhou, “Probability density estimation and Bayesian causal analysis based fault detection and root identification,” Industrial and Engineering Chemistry Research, vol. 57, no. 43, pp. 14656–14664, October 2018.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. The STIC Research Centre (CReSTIC, EA 3804), research unit attached to the University of Reims Champagne-Ardenne, BP 1039, 51687, Reims Cedex, France

    Foued Theljani, Adel Belkadi & Patrice Billaudel

Authors
  1. Foued Theljani
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Adel Belkadi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Patrice Billaudel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Foued Theljani.

Additional information

This work is carried out as part of the Smart Alternative Injection project co-financed by the European union and the region of Grand-Est (France) with the collaboration of the University of Reims Champagne-Ardenne and a locally based industrial collaborator.

Foued Theljani received his Ph.D. degree in electrical engineering and automation in 2013 and his M.S. degree in electronics in 2009 from the University of Tunis El-Manar, Tunisia. In 2015, he became an assistant professor at the University of Carthage. In 2019, he joined the university of Reims Champagne-Ardenne, France as a full researcher. Since January 2020, he is a R&D manager of Artificial Intelligence service at AISA Automation Indusrielle SA, Switzerland. His research interests are in the areas of machine learning and statistical approaches applied for prediction and decision-making problems. The goal is the adaption/development of new algorithms and methods to solve important real life issues including the industrial field (systems monitoring and fault detection) and healthcare field (data/image analysis, clinical decision support systems and bio-informatics.

Adel Belkadi received his Ph.D. degree in automatic control from Lorraine-University, Nancy, France, in 2017. Since September 2017, he is a Temporary Teacher and Researcher at the Engineering School in Industrial and Digital Sciences (EiSINe), of the University of Reims Champagne-Ardenne. He was born in Algeria, on February 21, 1989. He received his B.S. degree in electronics engineering from university of Houari Boumediene (USTHB), Algers, in 2010 and his M.S. degree in robotics in 2012. He obtained another M.S. degree in complex system and intelligence control from the University of Paris 12, Creteil, France in 2014. His research interests cover control theory and application, artificial intelligence and machine learning, multi-agent systems, fault detection and isolation and fault tolerant control.

Patrice Billaudel obtained his Ph.D. degree in 1990 and became Associated Professor in automation at the Engineering School in Industrial and Digital Sciences (EiSINe) of the University of Reims Champagne-Ardenne. He is a Full Professor there since he obtained his Accreditation to Direct Research in 1999. He is in charge of the engineering degree in Materials and Process Engineering and in charge of pedagogy for the school. He is working in the STIC Research Center (CReSTIC). He supervised Master and Ph.D. theses in the field of biomedical sensors, signal processing, monitoring and diagnosis. He published about 100 journal and conference papers and he is a reviewer for journals and conferences.

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

Theljani, F., Belkadi, A. & Billaudel, P. A Density-based Clustering Approach for Monitoring of Injection Moulding Machine. Int. J. Control Autom. Syst. 19, 2583–2595 (2021). https://doi.org/10.1007/s12555-020-0160-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12555-020-0160-z

Keywords

Search

Navigation