Neural network model for temperature sensitivity of emulsified asphalt mixtures


Oruc S.

INDIAN JOURNAL OF ENGINEERING AND MATERIALS SCIENCES, cilt.17, sa.6, ss.438-448, 2010 (SCI İndekslerine Giren Dergi) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 17 Konu: 6
  • Basım Tarihi: 2010
  • Dergi Adı: INDIAN JOURNAL OF ENGINEERING AND MATERIALS SCIENCES
  • Sayfa Sayıları: ss.438-448

Özet

This study intends to investigate temperature sensitivity of emulsified asphalt mixtures (cold-mix) and to establish a methodology that would provide an economic and rapid means for future experimental researches. Temperature sensitivity of the mixtures is investigated for 0 degrees C, 5 degrees C. 15 degrees C, 25 degrees C and 40 degrees C. The samples are prepared for three residual asphalt contents (4.2%, 5.2% and 6.2%). Portland cement is substituted for mineral filler in different ratios from 1% to 6%. A neural network (NN) model is developed for predicting, with sufficient approximation, relationship between the factors affecting resilient modulus (inputs; temperature, cement and asphalt content) and the resilient modulus (output) of emulsified asphalt mixture. A backpropagation neural network of three layers is employed. First resilient modulus data is obtained by conducting laboratory resilient modulus tests on emulsified asphalt samples, and then the results are used to train the neural network. The effectiveness of different neural network configurations is investigated. Effect of parameters such as temperature, cement addition level and residual asphalt content that influence the resilient modulus is explored. The prediction capability of the NN model is also compared to the traditional regression approach. Results indicate that NN predicts the resilient modulus with high accuracy. It is also demonstrated that NN is an excellent method that can reduce time consumed and can be used as an important tool in evaluating the factors affecting, resilient modulus of the mixtures for the design process.