Abstract

Paper Title/ Authors Name Download View

OPTIMIZATION OF TRANSPORTATION SYSTEM BASED ON COMBINED MODEL USING ARTIFICIAL NEURAL NETWORKS AND RESPONSE SURFACE METHODOLOGY

Saeid Jafarzadeh-Ghoushchi


The aim of this work is to optimize factors involving in a transportation system by using combined technique of Response Surface Methodology (RSM) and Artificial Neural Network (ANN) .The main idea of RSM is to use a set of designed experiments to obtain an optimal response. In this article ANN was used as a means to improve the estimation in the RSM for optimization of transportation system with using secondary data’s. The carry weight by this system was considered as a dependent variable and five independent variables, namely number of Van, Lorry, Truck, Labors and Fuel consumption. Using the ANN, the optimal configuration of the ANN model was found to be 7-4-1 and carry weights of each combination factors was predicted by this model. Predicted DV values from ANN were applied for RSM. The experiment was carried out based on 2-level, 5-variable Central Composite Design (CCD) in RSM and achieved optimal combination factors based on minimum cost. This approach leads to reducing the system cost. Furthermore, it is proposed to use simulated with ANN to consider high capability of carry weight prediction based on IV factors