International Journal of Applied Science and Engineering
Published by Chaoyang University of Technology

Kuang-Han Hsieha and C. Alec Changb*

a Department of Management Science, Chinese Military Academy, Fengshan, Kaohsiung 830, Taiwan, R.O.C.
b Department of Industrial and Manufacturing Systems Engineering, University of Missouri-Columbia, E3437 Engineering Building East, Columbia, MO 65211, U. S. A.

 

Download Citation: |
Download PDF


ABSTRACT

Existing approaches for conducting a control task for components machining generally include three methods: dimensional measurement, tolerance verification and equipment monitoring.However, spatial parameters from direct measurement present limited information about geometric features.Thus, many process monitoring systems must rely on acoustic information, torque and force sensors, vibration sensors, or an analysis of collected chips from a production process.These sensors can only detect problems caused by abnormal contact conditions between process tools and workpieces but not geometric deformations of industrial components produced in normal machining.  
Frequency parameters that directly utilize coordinate data from an object can identify more detailed geometric features for the purpose of industrial process monitoring.Accordingly, many more process anomalies about manufacturing facilities can be revealed using neural networks to map geometric anomalies.This paper develops shape-scales extracted from Fourier descriptors from incoming part scans.  By using these shape-scales, a pattern vector can be formed and fed into a feedforward neural network to identify error patterns.Also, using control charts, the identification of a process resetting point with shape-scales can be monitored.Since roundness is a recurring geometric form of industrial components, the monitoring of circular shape is used as an implementation example to illustrate the proposed system.This proposed system offers an alternative to obtain more process information through processed products in addition to hardware sensors.


Keywords: process monitoring; Fourier descriptor; feedforward neural networks; error pattern identification.


Share this article with your colleagues

 


REFERENCES

  1. [1] Reynolds, M. R. Jr. and Stoumbos, Z. G. 1998. SPRT chart for monitoring a proportion.  IIE Transactions, 30: 545-561.

  2. [2] Gultekin, M., Elsayed, E. A., English, J. R., and Hauksdottir, A. S. 2002. Monitoring automatically controlled processes using staticstical control charts.  International Journal of Production Research, 40: 2303-2320.

  3. [3] Elasayed, E. A. and Chen, A. 2000. An alternative mean estimator for processes monitored by SPC charts.  International Journal of Production Research, 38:3093-3109.

  4. [4] Granlund, G. H. 1972.  Fourier processing for hand printed character recognition.  IEEE Transactions on Computers, 21: 195-201.

  5. [5] Zahn, C. T. and Roskies, R. Z. 1972.  Fourier descriptors for plane closed crves.  IEEE Transactions on Computers, 21: 269-281.

  6. [6] Kuhl, F. P. and Giardina, C. R. 1982.  Elliptic Fourier features of a closed contour.  Computer Graphics and Image Processing, 18: 236-258.

  7. [7] Lin, C. S. and Hwang, C. L. 1987.  New forms of shape invariants from elliptic Fourier descriptors.  Pattern Recognition, 20: 535-545.

  8. [8] Tien, F. C. and Chang, C. A. 1999.  Using neural networks for 3d measurement in stereo vision inspection systems.  International Journal of Production Research, 37: 1935-1948.

  9. [9] Rice, J. A. and Wu, S. M. 1994.  Acoustic emission source and transmission path characterization through homomorphic processing.  Journal of Engineering for Industry, 116: 32-41.

  10. [10] Rajmohan, B. and Radhakrishnan, V. 1994. On the possibility of process monitoring in grinding by spark inten- sity measurements.  Journal of Engineering for Industry, 116: 124-129.

  11. [11] Lee, J. 1995. Modern computer-aided maintenance of manufacturing equipment and systems: review and perspective. Computers & Industrial Engineering, 28: 793-811.

  12. [12] Yang, M. Y. and Kwon, O. D. 1998. A tool condition recognition system using image processing. Control Engineering Practice, 6: 1389-1395.

  13. [13] Kumar, S. A., Ravindra, H. V., and Srinivasa, Y. G. 1997. In process toll wear monitoring through time series modeling and pattern recognition. International Journal of Production Research, 35: 739-751.

  14. [14] Choudhury, S. K., Jain, V. K., and Rao, R. 1999. On-line monitoring of tool wear in turning using a neural network. International Journal of Machine Tools & Manufacture, 39: 489-504.

  15. [15] Ghasempoor, A., Moore, T. N., and Jeswiet, J. 1998. On-line wear estimation using neural networks. Journal of Engineering Manufacture, 212: 105-112.

  16. [16] Sick, B. 2002. Fusion of hard and soft computing techniques in indirect, online tool wear monitoring. IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews, 32: 80-91.

  17. [17] Purushothaman, S. and Srinivasa, Y. G. 1998. A procedure for training and artificial neural network with application to tool wear monitoring. International Journal of Production Research, 36: 635-651.

  18. [18] Li, X. 2002. A brief review: acoustic emission method for tool wear monitoring during turning. International Journal of Machine Tools and Manufacture, 42: 157-165.

  19. [19] Everson, C. E. and Hoessein, C. S. 1999. The application of acoustic emission for precision drilling process monitoring. International Journal of Machine Tools & Manufacture, 39: 371-387.

  20. [20] Sheikh, A. K. 1999. Optimal tool replacement and resetting strategies in automated manufacturing systems. International Journal of Production Research, 37: 917-937.

  21. [21] Kuo, R. J. and Cohen, P. H. 1999. Multi-sensor integration for on-line tool wear estimation through radial basis function networks and fuzzy neural network. Neural Networks, 12: 355-370.

  22. [22] Sarma, S. E. and Wright, P. K. 1996. Algorithms for the minimization of setups and tool changes in “simply fixturable” components in milling. Journal of Manufacturing Systems, 15: 95-112.

  23. [23] Lin, S. and Jungthirapanich, C. 1990. Invariants of three-dimensional contours.  Pattern Recognition, 23: 833-842.

  24. [24] Leou, J. J. and Tsai, W. H. 1987. Automatic rotational symmetry determination for shape analysis. Pattern Recognition, 20: 571-582.

  25. [25] Yip, R. K. K., Tam, P. K. S., and Leung, D. N. K. 1994. Application of elliptic fourier descriptors to symmetry detection under parallel projection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16: 277-286.

  26. [26] Chang, C. A., Lo, C. C., and Hsieh, K. H. 1997. Neural networks and fourier descriptors for part positioning using bar code features in material handling systems. Computers Ind. Engng, 32: 467476.

  27. [27] Mitchell, O. R., Kim, H. S., Grogan, T. A., and Kuhl, F. P. 1991. Fourier descriptor based generic shape recognition. Technical Paper ACSM-ASPRS Annual Convention (Baltimore, MD.), 5: 279278.

  28. [28] Grogan, T. A. and Mitchell, O. R. 1983. Shape recognition and description: a comparative study. “Technical Report TR-EE 83-22”, School of Electrical Engineering, Purdue University.

  29. [29] Kourti, T., Nomikos P., and MacGregor, J. F. 1995. Analysis, monitoring and fault diagnosis of batch processes using multi-block and multiway PLS. Journal of Process Control, 5: 277-284.

  30. [30] Kourti, T. and MacGregor, J. F. 1996. Multivariate SPC methods for process and product monitoring. Journal of Quality Technology, 28: 409-428.

  31. [31] Lee, J. 1996. Measurement of machine performance degradation using a neural network model. Computers in Industry, 30: 193-209.

  32. [32] Lennox, B., Montague, G. A., Frith, A. M., Gent, C., and Bevan, V. 2001. Industrial application of neural networks- an investigation. Journal of Process Control, 11: 497-507.

  33. [33] Chang, C. A. and Su, C. T. 1995. A comparison of statistical regression and neural network methods in modeling measurement errors for computer vision inspection systems. Computers & Industrial Engineering, 28: 593-603.

  34. [34] Farago, F. T., 1982. “Handbook of dimensional measurements”. 2nd Ed., Industrial Press, New York.

  35. [35] Yeralan, S. and Ventura, J. A. 1988. Computerized roundness inspection. International Journal of Production Research, 26: 1921-1935.

  36. [36] Chen, J. M. and Ventura, J. A. 1995. Vision-based shaped recognition and analysis of machined parts. International Journal of Production Research, 33: 101-135.

  37. [37] Etesami, F. and Qiao, H. 1990. Analysis of two-dimensional measurement data for automated inspection. Journal of Manufacturing systems, 9: 21-34.

  38. [38] Roy, U. and Zhang, X. 1994. Development and application of voronoi diagrams in the assessment of roundness error in an industrial environment. Computers & Industrial Engineering, 26: 1126.

  39. [39] Roy, U. 1995. Computational methodologies for evaluating form and positional tolerances in a computer integrated manufacturing system. International Journal of Advanced Manufacturing Technology, 10: 110-117.

  40. [40] Car, K. and Ferreira, P. 1995. Verification of form tolerances part II: cylindric- ity and straightness of a median line.  Precision Engineering, 17: 144-156.

  41. [41] Kurfess, T. R. and Banks, D. L. 1995. Statistical verification of conformance to geometric tolerance. Computer Aided Design, 27: 353-361.

  42. [42] Drozda, T. J. and Wick, C., 1983. “Tool and manufacturing engineers handbook”. 4th Ed., Society of Manufacturing Engineers, Dearborn MI.


ARTICLE INFORMATION



Accepted: 2002-12-28
Available Online: 2020-12-18


Cite this article:

Hsieh, K.-H., Chang, C.A. 2003. Process-monitoring using part shape-scales with neural networks: a circular-component case, International Journal of Applied Science and Engineering, 1, 30–44. https://doi.org/10.6703/IJASE.2003.1(1).30

Other people also read ...

doaj logo

 

2.3
2022CiteScore
 
 
48th percentile
Powered by  Scopus
 
 

SCImago Journal & Country Rank

IJASE - Most Read Articles

IJASE - Most popular articles