Determination of brake force using artificial neural network

Koca A., Bayrakceken H., Altiparmak D.

JOURNAL OF SCIENTIFIC & INDUSTRIAL RESEARCH, vol.66, no.6, pp.425-430, 2007 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 66 Issue: 6
  • Publication Date: 2007
  • Journal Name: JOURNAL OF SCIENTIFIC & INDUSTRIAL RESEARCH
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.425-430
  • Gazi University Affiliated: No

Abstract

Brake forces for different conditions have been used to create an artificial neural network (ANN) model. A mathematical formulation is obtained by considering effective factors of brake force (slip, tread depth, road surface, turn angle, tread profile, tire pressure and Toe of the wheel). There is a good agreemnet between experimental data and ANN model. The best appraoch with minimum errors is performed using LM algorithm with 4 neurons on hidden layers. Statistical coefficient of multiple determinations (R-2 value) is obtained as 0,999699 for training data and 0,999178 for testing data.