Fatih AYDIN, Mustafa TİMUR

105

Anticipating the friction coe cient of friction materials used in automobiles by means of machine learning without using a test instrument

Anticipating the friction coe cient of friction materials used in automobiles by means of machine learning without using a test instrument

The most important factor for designs in which friction materials are used is the coe cient of friction. The coe cient of friction has been determined taking such variants as velocity, temperature, and pressure into account, which arise from various factors in friction materials, and by analyzing the e ects of these variants on friction materials. Many test instruments have been produced in order to determine the coe cient of friction. In this article, a study about the use of machine learning algorithms instead of test instruments in order to determine the coe cient of friction is presented. Isotonic regression was selected as the machine learning method in determining the coe cient of friction. The correlation coe cient between the results of isotonic regression algorithms and the results taken from the test instruments was measured as 0.9999 and the root mean squared error was 0.0014 in the experiments conducted. Selection of the number of optimum samples was enabled by taking bias-variance tradeo into account, and this increased the performance of the classi er in use. The target of this study was to prevent the practice of time-consuming test activities by using machine learning methods instead of test instruments in determining the friction coe cient. This presents a solution for decreasing the factors of time and cost.
PDF

___

  • [1] D. Halliday, R. Resnick, Fizigin Temelleri, Ayrm Yaynlar, Ankara, 1986 (Turkish translation from English: Fundamentals of Physics, Wiley).
  • [2] F. Ylmaz, Sürtünme ve asnma", 9. UluslararasMetalurji ve Malzeme Kongresi, _Istanbul, pp. 229-247, 1997 (in Turkish).
  • [3] M. Ashby, R.H.D. Jones, Friction and Wear Engineering Materials, Cambridge University Press, Cambridge, 1996.
  • [4] F.P. Bowden, D. Tabor, The Friction and Lubrication of Solids, Oxford University Press, Oxford, 1964.
  • [5] C. Filikcioglu, Tast Frenlerinde Balata C esidinin Ve C alsma Sartlarnn Frenleme Performansna Etkisi, MSc, Gazi University Institute of Science, Ankara, 1998 (in Turkish).
  • [6] N. Gemalmayan, Hava kirliliginde gizli tehlike asbest", TUB_ITAK Bilim ve Teknik Dergisi, Vol. 16, pp. 32-33, 1983 (in Turkish).
  • [7] M. Timur, Otomotivde Kullanlan Surtunme Malzemelerinin Surtunme KatsaysnTespit Eden Test Cihaz Tasarmve _Imalat, MSc Thesis, Afyon Kocatepe University Institute of Science, Afyonkarahisar, 2007 (in Turkish).
  • [8] TUB_ITAK, http://www.tubitak.gov.tr, October 2007.
  • [9] M. Boz, Toz Metalurjisi ile Uretilmis Bronz EsaslFren Balata Malzemelerinin Surtunme-Asnma Davranslarnn _Incelenmesi, MSc Thesis, Gazi University Institute of Science, Ankara, 1999 (in Turkish).
  • [10] M.E. Uygur, Balata uretim teknolojisi", 1. Ulusal Toz Metalurjisi Kongresi, Bildiriler Kitapcg, Gazi University, Ankara, 1996 (in Turkish).
  • [11] N. Gemalmayan, Surtunme Malzemelerinin  Ozelliklerinin Deneysel _Incelenmesi, PhD, Gazi University Engineering and Architecture Faculty, Ankara, 1984 (in Turkish).
  • [12] E. Alpaydn, Introduction to Machine Learning, MIT Press, Boston, 2004.
  • [13] WEKA, http://www.cs.waikato.ac.nz/ml/weka/, March 2011.
  • [14] J.G. Zhang, H.W. Deng, Gene selection for classi cation of microarray data based on the Bayes error", BMC Bioinformatics, Vol. 8, p. 370, 2007.
  • [15] I.H. Witten, E. Frank, Data Mining: Practical Machine Learning Tools and Techniques, 2nd ed., Morgan Kaufmann, San Francisco, 2005.
  • [16] O. Kursun, C.O. Sakar, O. Favorov, N. Aydn, F. Gurgen, Using covariates for improving the minimum redundancy maximum relevance feature selection method", Turkish Journal of Electrical Engineering & Computer Sciences, Vol. 18, pp. 975-989, 2010.
  • [17] TS 555, Karayolu Tastlar-Fren Sistemleri-Balatalar-Surtunmeli Frenler _Icin, T.S.E., 1. Bask, Ankara, 1992 (in Turkish).
  • [18] TS 9076, Fren Balatalar-Malzeme Surtunme  Ozelliklerinin Kucuk Deney Parcalar_Ile Degerlendirilmesi", T.S.E., 1. Bask, Ankara, 1991 (in Turkish).
  • [19] R.O. Duda, Hart PE, Stork DG, Pattern Classi cation, 2nd ed., Wiley-Interscience, New York, 2001.
  • [20] R. Kohavi, F. Provost, Applications of Machine Learning and the Knowledge Discovery Process, Vol. 30, pp. 271-274, 1998.
  • [21] C.M. Bishop, Pattern Recognition and Machine Learning, Springer Science+Business Media, Singapore, 2006.
  • [22] WEKA, http://weka.sourceforge.net/doc.packages/isotonicRegression/weka/classi ers/functions/IsotonicRegression.html, October 2010.
  • [23] J. de Leeuw, Monotonic regression", in Encyclopedia of Statistics in Behavioral Science, Vol. 3, pp. 1260-1261, John Wiley & Sons, New York, 2005.
  • [24] J. de Leeuw, K. Hornik, P. Mair, Isotone optimization in R: pool-adjacent-violators algorithm (PAVA) and active set methods", Journal of Statistical Software, Vol. 32, pp. 1-24, 2009.
  • [25] I.H. Witten, E. Frank, M.A. Hall, Data Mining: Practical Machine Learning Tools and Techniques, 3rd ed., Morgan Kaufmann, San Francisco, 2011.
  • [26] H. Dagloglu, SralSecenek Hipotezlerinde Kullanlan Testler, MSc, Hacettepe University Institute of Science, 2008.
  • [27] L. Kohorn, Shoot morphology and reproduction in Jojoba: advantages of sexual dimorphism", Ecology, Vol. 75, pp. 2384-2394, 1994.
  • [28] C.E. Lance, Akaike's Criterion, Encyclopedia of Statistics in Behavioral Science, John Wiley & Sons, New York, 2005.
  • [29] WEKA, http://weka.sourceforge.net/doc.dev/weka/classi ers/functions/LinearRegression.html, April 2012.
  • [30] WEKA, http://weka.sourceforge.net/doc/weka/classi ers/functions/LeastMedSq.html, April 2012.
  • [31] P.J. Rousseeuw, Least median of squares regression", Journal of the American Statistical Association, Vol. 79, pp. 871-880, 1984.
  • [32] WEKA, http://weka.sourceforge.net/doc.dev/weka/classi ers/functions/GaussianProcesses.html, April 2012.
  • [33] WEKA, http://weka.sourceforge.net/doc/weka/classi ers/functions/PaceRegression.html, April 2012.
  • [34] WEKA, http://weka.sourceforge.net/doc/weka/classi ers/functions/SimpleLinearRegression.html, April 2012.
  • [35] S.K. Shevade, S.S. Keerthi, C. Bhattacharyya, K.R.K. Murthy, Improvements to the SMO algorithm for SVM regression", IEEE Transactions on Neural Networks, Vol. 11, pp. 1188-1193, 1999.
  • [36] A.J. Smola, B. Schoelkopf, A tutorial on support vector regression", Journal Statistics and Computing, Vol. 14, pp. 199-222, 1998.
  • [37] WEKA, http://weka.sourceforge.net/doc/weka/classi ers/functions/SMOreg.html, April 2012.
  • [38] AI ACCESS, http://www.aiaccess.net/English/Glossaries/GlosMod/e gm mean square error.htm, March 2011.
  • [39] J. Cohen, Statistical Power Analysis for the Behavioral Sciences, 2nd ed., Lawrence Erlbaum Associates, Hillsdale, NJ, USA, 1998.
  • [40] R.G.D. Steel, J.H. Torrie, Principles and Procedures of Statistics, McGraw-Hill, New York, 1960.
Turkish Journal of Electrical Engineering and Computer Sciences-Cover
  • ISSN: 1300-0632
  • Yayın Aralığı: Yılda 6 Sayı
  • Yayıncı: TÜBİTAK
Arşiv
Sayıdaki Diğer Makaleler

Anticipating the friction coe cient of friction materials used in automobiles by means of machine learning without using a test instrument

Fatih AYDIN, Mustafa TİMUR

Operational characteristics of a ltering recti er transformer for industrial power systems

LongFu LUO, JiaZhu XU, ThanhNgoc TRAN, ZhiWen ZHANG, ZhiYu ZHAO

Optimized features selection for gender classi cation using optimization algorithms

Sajid Ali KHAN, Muhammad NAZIR, Naveed RIAZ