Design, Integration and Evaluation of an Artificial Intelligence-Based Control System for the Improvement of the Monitoring and Quality Control Process in the Manufacturing of Metal Casting Components

  • Emma L. Mares
  • Jerry H. Sokolowski
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2774)


An Artificial Intelligence-Based Control System (AIBCS) combined with Thermal Analysis (TA) is applied in this research on the manufacturing of aluminum casting components. The AIBCS comprises three interrelated IT’s based on statistical quality control techniques and Artificial Intelligence concepts. The IT’s integrated in the AIBCS are a Real-Time Data Acquisition System (RTDAS), a Statistical Process Control System (SPCS) and a Knowledge-Based System (KBS). Laboratory experiments and assessment of the AIBCS’s performance in terms of accuracy, reliability and timeliness showed superior monitoring and quality control of the casting process than traditional techniques.


Control Chart Casting Process Exponentially Weight Move Average Casting Property Exponentially Weight Move Average Control 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Santner, J., Overfelt, T.: The Metalcasting Industry and Future Research on the International Space Station. In: Space Technology and Applications International Forum. American Institute of Physics, New York (2000)Google Scholar
  2. 2.
    Kolodner, J.: Case-Based Reasoning. Morgan Kaufmann Publichers, Inc., U.S.A (1993)Google Scholar
  3. 3.
    Riesbeck, C.K.: Inside Case-Based Reasoning. The Institute for the Learning Sciences. Northwestern University, Evanston, Illinois. Laurence Erlbaum Associates, Mahwah (1980)Google Scholar
  4. 4.
    Watson, I.: Applying Case-Based Reasoning: Techniques for Enterprise Systems. Morgan Kauffman Publishers Inc., San Francisco (1997)Google Scholar
  5. 5.
    Caspian the Case-based Reasoner. Caspian and CASL Manuals,
  6. 6.
    Ali, Y.M., Zhung, L.C.: Estimation of Residual Stresses Induced by Griding Using a Fuzzy Logic Approach. Journal of Materials Processing Technology, 875–880 (1997)Google Scholar
  7. 7.
    Wang, G.: Application of Artificial Neural Networks in Foundry Industry. Material Science and Engineering, 424-431 (1998)Google Scholar
  8. 8.
    Er, A., Sweeney, V., Kondic, V.: Knowledge-Based System for Casting Process Selection. Transactions of the American Foundrymen’s Society 104, 363–370 (1996)Google Scholar
  9. 9.
    Er, A., Kondic, V.: Knowledge-Based System and their Applications in Casting Defects Control. Int. Journal of Cast Metals Research 9, 163–173 (1996)Google Scholar
  10. 10.
    Kierkus, W., Mackay, R., Sokolowski, J.: Metallurgical Characterization of the 319 Alloy Solidification Process Utilizing the Aluminum Thermal Analysis System (AlTAS). Industrial Research Chair in Light Casting Technology. University of Windsor (2000)Google Scholar
  11. 11.
    Li, D., Liu, Y., Zhang, Y., Feng, M.: Study on Thermal Analysis Models Used in Gray Cast Iron Quality Prediction. Int. Journal of Cast Metals Research 11, 391–394 (1999)Google Scholar
  12. 12.
    Nelson, L.S.: The Schewhart Control Chart – Test for Special Cases. Journal of Quality Technology 16 (1984)Google Scholar
  13. 13.
    Hunter, J.S.: The Exponentially Weighted Moving Average. Journal of Quality Technology 18, 203–209 (1986)Google Scholar
  14. 14.
    Lucas, J.M., Saccuci, M.S.: Exponentially Weighted Moving Average Control Schemes: Properties and EnhancementsGoogle Scholar
  15. 15.
    Western Electric Statistical Quality Control Handbook. Western Electric Corporation, Indianapolis, Ind. (1956)Google Scholar
  16. 16.
    Lenz, M.: Case-Based Reasoning Technology. From Foundations to Applications. LNAI, Vol. 400. Springer, Berlin(1998) Google Scholar
  17. 17.
    Pelayo, G.: Development of A Knowledge-Based System for the Control of 319-Al Melt Quality and Casting Characteristics in a Sand Casting Process. In: Industrial Research Chair in Light Metal Casting Technology, Ontario, Canada (2000)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Emma L. Mares
    • 1
  • Jerry H. Sokolowski
    • 2
  1. 1.Information Systems Department AguascalientesAutonomous University of AguascalientesMéxico
  2. 2.Ford Industrial Chair in Light Metal Casting TechnologyUniversity of WindsorOntarioCanada

Personalised recommendations