R. Kazemi, M. Abdollahzade,
Volume 5, Issue 1 (3-2015)
Abstract
Car following process is time-varying in essence, due to the involvement of human actions. This paper develops an adaptive technique for car following modeling in a traffic flow. The proposed technique includes an online fuzzy neural network (OFNN) which is able to adapt its rule-consequent parameters to the time-varying processes. The proposed OFNN is first trained by an growing binary tree learning algorithm in offline mode, which produces favorable extrapolation performance, and then, is adapted to the stream of car following data, e.g. velocity and acceleration of the target vehicle, using an adaptive least squares estimation. The proposed approach is validated by means of real-world car following data sets. Simulation results confirm the satisfactory performance of the OFNN for adaptive car following modeling application.
Masoud Afrousheh, Javad Marzbanrad, Sanaz Abdollahzadeh,
Volume 9, Issue 4 (12-2019)
Abstract
Thin-walled structures play an important role in absorbing the energy in a low impact crash of vehicles up to saving lives from high impact Injury. In this paper, the thin-walled columns by using a hybrid Design of Experiments (DOE) and Ant Colony Algorithm (ACO) has been optimized. The analysis of the behavior of the nonlinear models under bending load is done using finite-element software Abaqus. The objective is to study the performance geometrically parameters of the columns using DOE-ACO approach.
DOE method is being applied to determine the effects of cross-sections, material, and thickness on the energy absorption; and the ACO method is used for finding more accurate thickness on energy absorption. Four types of thin-walled cross-sections, i.e., circle, ellipse, hexagon, and square are used in this study. The optimized results of DOE method show that aluminum alloy (Al-6061) and high strength low alloy steel (HSLA) square columns have a higher energy absorption in comparison with the other cross-sections. However, the amount of absorbed energy in two types of columns is equal but, 50 percent weight reduction may be seen in Al-6061 columns. The columns are re-optimized by ACO to find the best thickness in the last step.
In the following, by topology optimization participation, a new plan is proposed by the same thickness and 50% less weight, that has a higher crashworthiness efficiency by increasing SAE more than 70%. As a result of this plan is bridging the gap between standard topological design and multi-criteria optimization.