Selection of best neural network for estimating properties of diesel-biodiesel blends

  • Authors:

  • Jatinder Kumar;Ajay Bansal

  • Affiliations:

  • Department of Chemical and Bio Engineering, Dr. B. R. Ambedkar National Institute of Technology, Jalandhar, Punjab, India;Department of Chemical and Bio Engineering, Dr. B. R. Ambedkar National Institute of Technology, Jalandhar, Punjab, India

  • Venue:
  • AIKED'07 Proceedings of the 6th Conference on 6th WSEAS Int. Conf. on Artificial Intelligence, Knowledge Engineering and Data Bases - Volume 6
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Soybean oil was transesterified with methanol in the presence of alkaline catalyst to produce methyl esters commonly known as biodiesel. Biodiesel and diesel blends were prepared and tested in laboratory for flash point, fire point, viscosity and density. Seven neural network architectures, three training algorithms along with ten different sets of weight and biases were examined to predict the above-mentioned properties of diesel and biodiesel blends. The best suited neural network and training algorithm were selected and further generalized to improve its performance by using early stopping technique. The results showed that the neural network having an architecture 2-7-4 with Levernberg-Marquardt algorithm gave the best estimate for the properties of diesel-biodiesel blends.