Failures Prediction in the Cold Forging Process Using Machine Learning Methods

详细信息    查看全文

• 作者：Tomasz ?abiński (23)
  Tomasz M?czka (23)
  Jacek Kluska (23)
  Maciej Kusy (23)
  Zbigniew Hajduk (23)
  S?awomir Prucnal (24)
  
• 关键词：cold headed fasteners ; cold forging process ; computational intelligence methods ; accuracy ; sensitivity ; specificity
• 刊名：Lecture Notes in Computer Science
• 出版年：2014
• 出版时间：2014
• 年：2014
• 卷：8467
• 期：1
• 页码：622-633
• 参考文献：1. Gawe? Zak?ad Produkcji ?rub, http://www.gzps.pl/
  2. M?czka, T., ?abiński, T., Kluska, J.: Computational Intelligence application in fasteners manufacturing. In: Proceedings of 13th IEEE International Symposium on Computational Intelligence and Informatics (CINTI), Budapest, pp. 335-40 (2012)
  3. ?abiński, T., M?czka, T.: Implementation of Human-System Interface for Manufacturing Organizations. In: Hippe, Z.S., Kulikowski, J.L., Mroczek, T. (eds.) Human -Computer Systems Interaction: Backgrounds and Applications 2. AISC, vol.?98, pp. 13-1. Springer, Heidelberg (2012)
  4. M?czka, T., ?abiński, T.: Platform for Intelligent Manufacturing Systems with elements of knowledge discovery. In: Manufacturing System, pp. 183-04. InTech, Croatia (2012)
  5. Kong, L.X., Nahavandi, S.: On-line tool condition monitoring and control system in forging process. Journal of Materials Processing Technology?125-126, 464-70 (2002) CrossRef
  6. Rolfe, B., Frayman, Y., Hodgson, P., Webb, G.I.: Fault Detection in a Cold Forging Process Through Feature Extraction with a Neural Network. In: Proceedings of the IASTED International Conference on Artificial Intelligence and Applications (AIA), Benalmdena, Spain, pp. 155-59 (2002)
  7. Beckhoff Information System, http://infosys.beckhoff.com/
  8. Carlo Salvi 332 DL machine (1 Die 2 Blow Headers), http://www.carlosalvi.it
  9. Wu, X., Kumar, V., Quinlan, J.R., et al.: Top 10 algorithms in data mining. Knowledge Information Systems?14, 1-7 (2008) CrossRef
  10. Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and regression trees. Wadsworth, Belmont (1984)
  11. Specht, D.F.: Probabilistic neural networks. Neural Networks?3, 109-18 (1990) CrossRef
  12. Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995) CrossRef
  13. Sch?lkopf, B., Smola, A.J., Williamson, R.C., Bartlett, P.L.: New support vector algorithms. Neural Computation?12, 1207-245 (2000) CrossRef
  14. Rumelhart, D., McClelland, J.: Parallel Distributed Processing. MIT Press, Cambridge (1986)
  15. Fisher, R.A.: The Use of Multiple Measurements in Taxonomic Problems. Annals of Eugenics?7(2), 179-88 (1936) CrossRef
  16. Hartigan, J.A., Wong, M.A.: A k-means clustering algorithm. Journal of the Royal Statistical Society - Series C (Applied Statistics)?1, 100-08 (1979)
  17. Sherrod, P.H.: DTREG predictive modelling software, http://www.dtreg.com
  
• 作者单位：Tomasz ?abiński (23)
  Tomasz M?czka (23)
  Jacek Kluska (23)
  Maciej Kusy (23)
  Zbigniew Hajduk (23)
  S?awomir Prucnal (24)
  
  23. Faculty of Electrical and Computer Engineering, Rzeszów University of Technology, 35-959, Rzeszów, Powstańców Warszawy 12, Poland
  24. Faculty of Mechanical Engineering and Aeronautics, Rzeszów University of Technology, 35-959, Rzeszów, Powstańców Warszawy 12, Poland
  
• ISSN：1611-3349

文摘

In this paper, single correct and three defective states for the cold headed fasteners production technological process are detected. Computational intelligence methods are used for this purpose: single decision tree, probabilistic neural network, support vector machine, multilayer perceptron, linear discriminant analysis and K–Means clustering. The predictor variables are taken in time and frequency domain. The row data sets consist of sampled signals of the real process collected in fasteners manufacturing company. The prediction ability determined by 10-fold cross validation is investigated by means of accuracy, sensitivity and specificity. The results show the superiority of probabilistic neural network and support vector machine classifiers. The average accuracy is over 98%.