Journal of Intelligent Manufacturing

, Volume 25, Issue 5, pp 1167–1180 | Cite as

An approach to monitoring quality in manufacturing using supervised machine learning on product state data

  • Thorsten Wuest
  • Christopher Irgens
  • Klaus-Dieter Thoben


Increasing market demand towards higher product and process quality and efficiency forces companies to think of new and innovative ways to optimize their production. In the area of high-tech manufacturing products, even slight variations of the product state during production can lead to costly and time-consuming rework or even scrapage. Describing an individual product’s state along the entire manufacturing programme, including all relevant information involved for utilization, e.g., in-process adjustments of process parameters, can be one way to meet the quality requirements and stay competitive. Ideally, the gathered information can be directly analyzed and in case of an identified critical trend or event, adequate action, such as an alarm, can be triggered. Traditional methods based on modelling of cause-effect relations reaches its limits due to the fast increasing complexity and high-dimensionality of modern manufacturing programmes. There is a need for new approaches that are able to cope with this complexity and high-dimensionality which, at the same time, are able to generate applicable results with reasonable effort. Within this paper, the possibility to generate such a system by applying a combination of Cluster Analysis and Supervised Machine Learning on product state data along the manufacturing programme will be presented. After elaborating on the different key aspects of the approach, the applicability on the identified problem in industrial environment will be discussed briefly.


Product state Data Manufacturing  Process Quality monitoring Cluster analysis  Supervised machine learning 



The authors would like to thank the “Deutsche Forschungsgemeinschaft” for financial support via the funded project “Informationssystem für werkstoffwissenschaftliche Forschungsdaten”.


  1. Albino, V., Pontrandolfo, P., & Scozzi, B. (2002). Analysis of information flows to enhance the coordination of production processes. International Journal of Production Economics, 75, 7–19.CrossRefGoogle Scholar
  2. Apley, D., & Shi, J. (2001). A factor-analysis method for diagnosing variability in mulitvariate manufacturing processes. Technometrics, 43(1), 84–95.CrossRefGoogle Scholar
  3. Babiceanu, R., & Chen, F. (2006). Development and applications of holonic manufacturing systems: A survey. Journal of Intelligent Manufacturing, 17(1), 111–131.CrossRefGoogle Scholar
  4. Borror, C., Montgomery, D., & Runger, G. (1999). Robustness of the EWMA control chart to non-normality. Journal of Quality Technology, 31(3), 309–316.Google Scholar
  5. Boon-itt, S. (2010). An empirical model of the relationship between manufacturing capabilities: Evidence from the Thai automotive industry. NIDA Development Journal, 59(2), 19–45.Google Scholar
  6. Brinksmeier, E. (1991). Prozeß- und Werkstückqualität in der Feinbearbeitung. Fortschritt-Berichte VDI Reihe2: Fertigungstechnik Nr. 234. Düsseldorf: VDI Verlag.Google Scholar
  7. Chinnam, R. B. (2002). Support vector machines for recognizing shifts in correlated and other manufacturing processes. International Journal of Production Research, 40(17), 4449–4466.CrossRefGoogle Scholar
  8. Chou, Y., Polansky, A., & Mason, R. (1998). Transforming non-normal data to normality in statistical process control. Journal of Quality Technology, 30(2), 133–141.Google Scholar
  9. Choudhary, A. K., Harding, J. A., & Tiwari, M. K. (2009). Data mining in manufacturing: A review based on the kind of knowledge. Journal of Intelligent Manufacturing, 20(5), 501–521.CrossRefGoogle Scholar
  10. Clausen, B., Frerichs, F., Goch, G., Klein, D., Lübben, Th, Nowag, L., et al. (2006). Verzugsentstehung von Wälzlagerringen—Eine prozesskettenübergreifende Analyse. HTM Z. Werkst. Wärmebeh. Fertigung, 6(61), 309–319.Google Scholar
  11. de Groot, P. J., Postma, G. J., Melssen, W. J., & Buydens, L. M. C. (1999). Selecting a representative training set for the classification of demolition waste using remote NIR sensing. Analytica Chimica Acta, 392(1999), 67–75.CrossRefGoogle Scholar
  12. Ding, Y., Ceglarek, D., & Shi, J. (2002). Fault diagnosis of multistage manufacturing processes by using state space approach. Journal of Manufacturing Science and Engineering, 124(2), 313–322. doi: 10.1115/1.1445155.Google Scholar
  13. Du, R., Elbestawi, M. A., & Wu, S. M. (1995). Automated monitoring of manufacturing processes, part 1: Monitoring methods. Journal of Engineering for Industry, 117(2), 121–132.CrossRefGoogle Scholar
  14. Fischer, D., & Breitenbach, J. (Eds.). (2009). Die Pharmaindustrie: Einblick, Durchblick, Perspektiven. Heidelberg: Spektrum Akademischer Verlag.Google Scholar
  15. Giebel, M., Essmann, H., Du Preez, N., & Jochem, R. (2009). Improved innovation through the integration of quality gates into the enterprise and product lifecycle roadmaps. CIRP Journal of Manufacturing Science and Technology, 1(3), 199–205.CrossRefGoogle Scholar
  16. Gogouvitis, S., Konstanteli, K., Waldschmidt, S., Kousiouris, G., Katsaros, G., Menychtas, A., et al. (2012). Workflow management for soft real-time interactive applications in virtualized environments. Future Generation Computer Systems, 28(1), 193–209.CrossRefGoogle Scholar
  17. Hamel, L. (2009). Knowledge discovery with support vector machines. Hoboken: Wiley, ISBN 978-0-470-37192-3.Google Scholar
  18. Hicks, B. J., Culley, S. J., & McMohan, C. A. (2006). A study of issues relating to information management across engineering SMEs. International Journal of Information Management, 26, 267–289.CrossRefGoogle Scholar
  19. Holcomb, M. C. (1994). Customer service measurement: A methodology for increasing customer value through utilization of the Taguchi strategy. Journal of Business Logistics, 15(1), 29–52.Google Scholar
  20. Jacob, J., & Petrick, K. (2007). Qualitätsmanagement und Normung. In R. Schmitt & T. Pfeifer (Eds.), Masing Handbuch Qualitätsmanagement (pp. 101–121). München: Carl Hanser Verlag.Google Scholar
  21. Jansen-Vullers, M. H., van Drop, C. A., & Beulens, A. J. M. (2003). Managing traceability information in manufacture. International Journal of Information Management, 23, 395–413.CrossRefGoogle Scholar
  22. Jenab, K., & Ahi, P. (2010). Fuzzy quality feature monitoring model. International Journal of Production Research, 48(17), 5021–5030.CrossRefGoogle Scholar
  23. Jiang, P., Jia, F., Wang, Y., & Zheng, M. (2012). Real-time quality monitoring and predicting model based on error propagation networks for multistage machining processes. Journal of Intelligent Manufacturing (online first-2012).Google Scholar
  24. Kalpakjian, S., & Schmid, S. R. (2009). Manufacturing engineering and technology. New Jersey: Prentice Hall.Google Scholar
  25. Kessler, O., Prinz, Ch., Sackmann, T., Nowag, L., Surm, H., Frerichs, F., et al. (2006). Experimental study of distortion phenomena in manufacturing lines. Materialwissenschaft und Werkstofftechnik, 37(1), 11–18.CrossRefGoogle Scholar
  26. Koufteros, X. A., Vonderembse, M. A., & Doll, W. J. (2002). Examine the competitive capabilities of manufacturing firms. Structural Equation Modelling, 9(2), 256–282.CrossRefGoogle Scholar
  27. Kovacic, M., & Sarler, B. (2009). Application of the genetic programming for increasing the soft annealing productivity in steel industry. Materials and Manufacturing Processes, 24, 369–374.CrossRefGoogle Scholar
  28. Manning, C. D., Raghavan, P., & Schütze, H. (2009). An introduction to information retrieval. Cambridge, UK: Cambridge University Press.Google Scholar
  29. Megahed, F. M., & Camelio, J. A. (2010). Real-time fault detection in manufacturing environments using face recognition techniques. Journal of Intelligent Manufacturing, 23(3), 393–408.CrossRefGoogle Scholar
  30. Merali, Y., & Bennet, Z. (2011). Web 2.0 and Network Intelligence. In P. Warren, J. Davies, & E. Simperl (Eds.), Context and semantics for knowledge management (pp. 11–26). Heidelberg: Springer.CrossRefGoogle Scholar
  31. Mizuyama, H. (2004). Directing quality improvement efforts in a multi-stage production process through observational data analysis. In Proceedings of the 8th international conference on manufacturing and management, pp. 414–421.Google Scholar
  32. Mizuyama, H. (2006). it Artificial-neural-network-based MSQIM for exploratory analysis of manufacturing data. In Proceedings of the 7th Asia-Pacific industrial engineering and management systems conference.Google Scholar
  33. Mohanty, P. P. (2004). An agent-oriented approach to resolve the production planning complexities for a modern steel manufacturing system. International Journal of Advanced Manufacturing Technology, 24, 199–205.CrossRefGoogle Scholar
  34. Monostori, L., Váncza, J., & Kumara, S. R. T. (2006). Agent-based systems for manufacturing. CIRP Annals-Manufacturing Technology, 55(2), 697–720.CrossRefGoogle Scholar
  35. Pavletic, D., & Sokovic, M. (2009). Quality improvement model at the manufacturing process preparation level. International Journal of Quality Research, 3(4), 309–315.Google Scholar
  36. Robinson, C. J., & Malhotra, M. K. (2005). Defining the concept of supply chain quality management and its relevance to academic and industrial practice. International Journal of Production Economics, 96(3), 315–337.CrossRefGoogle Scholar
  37. Scheidat, T., Leich, M., Alexander, M., & Vielhauer, C. (2009). Support vector machines for dynamic biometric handwriting classification. In Proceedings of AIAI Workshops, pp. 118–125.Google Scholar
  38. Seifert, M. (2009). Collaboration formation in virtual organisations by applying prospective performance measurement. Bremer Schriften zur Integrierten Produkt- und Prozessentwicklung: Dissertation at the University of Bremen.Google Scholar
  39. Sha, L., Abdelzaher, T., Arzen, K.-E., Cervin, A., Baker, T., Burns, A., et al. (2004). Real-time scheduling theory: A historical perspective. Real-Time Systems, 28(2–3), 101–155.CrossRefGoogle Scholar
  40. Shukla, C. S., & Frank Chen, F. (1996). The state of the art in intelligent real-time FMS control: A comprehensive survey. Journal of Intelligent Manufacturing, 7(6), 441–455.CrossRefGoogle Scholar
  41. Silva, R. G. (2009). Condition monitoring of the cutting process using a self-organizing spiking neural network map. Journal of Intelligent Manufacturing, 21(6), 823–829. Google Scholar
  42. Siyasiya, C., van Rooyen, G. T., & Stumpf, W. E. (2005). Metallurgical factors that affect the strand width during continuous casting of DIN 1.4003 stainless steel. The Journal of The South African Institute of Mining and Metallurgy, 105, 473–481.Google Scholar
  43. Spath, D., Scharer, M., Landwehr, R., Förster, H., & Schneider, W. (2001). Tore öffnen—Quality-Gate-Konzept für den Produktentstehungsprozess. QZ Qualität und Zuverlässigkeit, 46(12), 1544–1549.Google Scholar
  44. Stoumbos, Z., & Sullivan, J. (2002). Robustness to non-normality of the multivariate EWMA control chart. Journal of Quality Technology, 34(3), 260–276.Google Scholar
  45. Sukchotrat, T., Kim, S. B., & Tsung, F. (2009). One-class classification-based control charts for multivariate process monitoring. IIE Transactions, 42(2), 107–120.CrossRefGoogle Scholar
  46. Vapnik, V. (1998). Statistical learning theory. Hoboken: Wiley.Google Scholar
  47. Wang, K., & Tsung, F. (2007). Run-to-run process adjustment using categorical observations. Journal of Quality Technology, 39(4), 312–325.Google Scholar
  48. Wuest, T., Irgens, C. & Thoben, K.-D. (2012). Analysis of manufacturing process sequences, using machine learning on intermediate product states (as process proxy data). In C. Emmanouilidis, M. Taisch, & D. Kiritsis (Eds.), Competitive manufacturing for innovative products and services. In Proceedings of the APMS 2012 international conference of advances in production management systems, September 24–26, 2012, Rhodes Island, Greece. (to be published by Springer).Google Scholar
  49. Wuest, T., Klein, D., & Thoben, K.-D. (2011). State of steel products in industrial production processes. Procedia Engineering, 10, 2220–2225.CrossRefGoogle Scholar
  50. Yu, T. & Wang, G. (2009). The process quality control of single-piece and small-batch products in advanced manufacturing environment. In Proceedings of the 16th international conference on industrial engineering and engineering management. (IE &EM ’09), October 21–23, 2009, Beijing, China, pp. 306–310.Google Scholar
  51. Zantek, P. F., Wright, G. P., & Plante, R. D. (2006). A self-starting procedure for monitoring process quality in multistage manufacturing systems. IIE Transactions, 38(4), 293–308.CrossRefGoogle Scholar
  52. Zhang, J., & Wang, H. (2009). A minimized zero mean entropy approach to networked control systems. In Proceedings of the 48th IEEE Conference on Decision and Control (CDC) held jointly with 2009 28th Chinese Control Conference (pp. 6876–6881). Shanghai, China: IEEE. doi: 10.1109/CDC.2009.5400679.
  53. Zoch, H.-W. & Lübben, Th. (2011). Verzugsbeherrschung—Systemorientierter Ansatz als wesentliche Voraussetzung für den Erfolg. Tagungsband zum 26. Aachener Stahlkolloquium, Verlagshaus Mainz.Google Scholar
  54. Zoch, H.-W. (2012). Distortion engineering-interim results after one decade research within the Collaborative Research Center. Materialwissenschaft und Werkstofftechnik, 43(1–2), 9–15.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • Thorsten Wuest
    • 1
  • Christopher Irgens
    • 2
  • Klaus-Dieter Thoben
    • 1
  1. 1.Applied Information and Communication Technology for ProductionBIBA – Bremer Institut für Produktion und Logistik GmbHBremenGermany
  2. 2.Design, Manufacture and Engineering ManagementUniversity of StrathclydeGlasgowUK

Personalised recommendations