An autonomous low-Cost infrared system for the on-line monitoring of manufacturing processes using novelty detection

Original Article

Abstract

This paper describes the implementation of a process monitoring system using a low-cost autonomous infrared imager combined with a novelty detection algorithm. The infrared imager is used to monitor the health of several manufacturing processes namely: drilling, grinding, welding and soldering. The main aim is to evaluate the use of low-cost infrared sensor technology combined with novelty detection to distinguish between normal and faulty conditions of manufacturing processes. The ultimate aim is to improve the reliability of the manufacturing operations so as to ensure high part quality and reduce inspection costs. The paper describes several case studies, which have shown that the new low-cost technology could provide an inexpensive and autonomous methodology for monitoring manufacturing processes. Novelty detection is used to compare normal and faulty conditions in order to provide an automated system for fault detection.

Keywords

Infrared condition monitoring manufacturing processes welding grinding drilling soldering novelty detection 

References

  1. 1.
    Hutton R (1996) The impact of information technology on condition monitoring. In: Proceedings of the 5th International Conference on Profitable Condition Monitoring Fluids and Machinery Performance Monitoring, Mechanical Engineering Publications Limited, UK, 3–4 December 1996, pp 23–35Google Scholar
  2. 2.
    Martin KF (1994) A review by discussion of condition monitoring and fault diagnosis in machine tools. Int J Mach Tool Manuf 4:527–551CrossRefGoogle Scholar
  3. 3.
    Jemielniak K (1999) Commercial tool condition monitoring systems. Int J Adv Manufact Technol 15(10):711–721CrossRefGoogle Scholar
  4. 4.
    Young JW, Yang M, Young Park H (1994) Detection of cutting tool fracture by dual signal measurements. Int J Mach Tools Manufact 34(4):507–525CrossRefGoogle Scholar
  5. 5.
    Al-Habaibeh A, Gindy N (2001) Self-learning algorithm for automated design of condition monitoring systems for milling operations. Int J Adv Manufact Technol 18(6):448–459CrossRefGoogle Scholar
  6. 6.
    Rajmohan B, Radhakrishnan V (1994) On the possibility of process monitoring in grinding by spark intensity measurements. J Engin Indust, Trans ASME 116(1):124–129Google Scholar
  7. 7.
    Kwak YM, Doumanidis C (1999) Geometry modeling and regulation in restorative welding of surface cavities. American Society of Mechanical Engineers, Pressure Vessels and Piping Division (Publication) PVP 396:241–248Google Scholar
  8. 8.
    Parkin RM, Coy J, Mansi M, Jackson MR, Ward N (2001) The use of infra-red sensor systems in monitoring for condition based maintenance. In: Proceedings of the International Conference on Condition Monitoring, St. Catherine's College, Oxford, UK, 25–27 June, 2001Google Scholar
  9. 9.
    Bayazitoglu Y, Ozisik MN (1988) Elements of heat transfer. McGraw-Hill, New YorkGoogle Scholar
  10. 10.
    Non-contact temperature measurement. Transactions in Measurement and Control, Vol.1, 3rd Edition, OMEGA, www.omega.com
  11. 11.
    IEE Review, The Institution of Electrical Engineers, UK, May 2001, pp 42Google Scholar
  12. 12.
    Zorriassatine F (2000) Application of neural networks for detection of special causes in multivariate statistical process control. Dissertation, University of NottinghamGoogle Scholar
  13. 13.
    Roberts SJ (2000) Extreme value statistics for novelty detection in biomedical data processing. In: IEE Proceedings: Science, Measurement and Technology 147(6):363–367Google Scholar
  14. 14.
    Albrecht S, Bush J, Kloppenburg M, Metze F, Tavan P (2000) Generalised radial basis function networks for classification and novelty detection: self-organisation of optimal bayesian decision. Neur Netw 13(10):1075–1093CrossRefGoogle Scholar
  15. 15.
    Manson G et al. (2000) Long-term stability of normal condition data for novelty detection. In: Proceedings of SPIE: The International Society for Optical Engineering 3985:323–334Google Scholar
  16. 16.
    Bishop CM (1995) Neural networks for pattern recognition. Claredon, OxfordGoogle Scholar
  17. 17.
    Fukunaga K (1990) Introduction to statistical pattern recognition, 2nd ed. Academic, Boston LondonGoogle Scholar
  18. 18.
    Parzen E (1962) Stochastic processes. Holden-Day, San FranciscoGoogle Scholar
  19. 19.
    Specht DF (1990) Probabilistic neural networks. Neur Netw 3(1):109–118CrossRefGoogle Scholar
  20. 20.
    Nabney I, Bishop CM (2000) Netlab neural network software. Neural Computing Research Group, Information Engineering, Aston University, BirminghamGoogle Scholar
  21. 21.
    Kalpakjian S, Schmid SR (2001) Manufacturing engineering and technology, 4th edition. Prentice-Hall, Upper Saddle River, NJGoogle Scholar
  22. 22.
    Guo C, Malkin S (1996) Inverse heat transfer analysis of grinding, Part 1: Methods. J Engin Indust, Trans ASME 118(1):137–142Google Scholar
  23. 23.
    Ren H, Xiurong S, Ruilian D, Binglin Z, Yuliang M, Brandon J (1992) A study of on-line identification for grinding burn. Int J Mach Tools Manufact 32(6):767–779CrossRefGoogle Scholar
  24. 24.
    Chen M, Xue BY (1999) Study on acoustic emission in the grinding process automation. American Society of Mechanical Engineers, Manufacturing Engineering Division, MED 10:499–503Google Scholar
  25. 25.
    Zitt U, Braun O (1999) Laser triangulation sensor for the measurement and evaluation of the grinding wheel topography within the machine system. Grind Abrasives http://www.abrasivesmagazine.com, Cited June/July 1999
  26. 26.
    Toenshoff HK, Karpuschewski B, Regent C (1999) Process monitoring in grinding using micromagnetic techniques. Int J Adv Manufact Technol 15(10):694–698CrossRefGoogle Scholar
  27. 27.
    Ertunc HM, Loparo KA (2001) A decision fusion algorithm for tool wear condition monitoring in drilling. Int J Mach Tools Manufact 41(9):1347–1362CrossRefGoogle Scholar
  28. 28.
    El-Wardany TI, Gao D, Elbestawi MA (1996) Tool condition monitoring in drilling using vibration signature analysis. Int J Mach Tools Manufact 36(6):687–711CrossRefGoogle Scholar
  29. 29.
    Ravishankar SR, Murthy CRL (2000) Characteristics of AE signals obtained during drilling composite laminates. NDT E Int 33(5):341–348CrossRefGoogle Scholar
  30. 30.
    Li PJ, Zhang YM (1999) Precision sensing of arc length in GTAW based on arc light spectrum. American Society of Mechanical Engineers, Manufacturing Engineering Division, MED 10:649–658Google Scholar
  31. 31.
    Saunders R (1998) Thermocouple attachment for reflow solder profiling and process development. Electron Packag Product 38(11):51–2, 54–5Google Scholar
  32. 32.
    Conway P, Whalley D, Wilkinson M, Hyslop SM (1998) Application of IR thermography to process monitoring and control of reflow soldering. Sold Surf Mt Technol 28:13–18CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2003

Authors and Affiliations

  1. 1.Mechatronics Research Centre, Wolfson School of Mechanical and Manufacturing EngineeringLoughborough UniversityUK

Personalised recommendations