Print ISSN: 1681-6900

Online ISSN: 2412-0758

Keywords : genetic algorithm


Design a System to Estimate the Road Construction Project Preliminary Equipment Requirements in the Design Stage

Raid S. Abd Ali; Tareq A. khaleel; Shealan H. Ameen

Engineering and Technology Journal, 2016, Volume 34, Issue 13, Pages 554-565

Road construction projects in Iraq require a developmental study of the planning process toward building computerized management systems. In this thesis, a management system has been built, based on artificial neural networks and genetic algorithms. The proposed software estimates the optimal number of equipment, machineries, and relevance instruments required according to progress table of the work during the proposed implementation period of the project. Artificial neural network systems have been adopted to build models to predict the productivity of the equipment used in road construction projects, based on the factors that affecting the productivity of these mechanisms. By implementing the system and simulating at road project, several conclusions have been conducted. One of the most important conclusions is that the optimal distribution of the numbers and types of machineries used in road construction has a significant impact on the time of implementation of project.

Genetic Based Method for Mining Association Rules

Bushra Khireibut Jassim

Engineering and Technology Journal, 2013, Volume 31, Issue 3, Pages 325-331

In this paper genetic based method proposed for mining association rule, the benefit of this method it mining association rule in one step and it does not require the user-specified threshold of minimum support and minimum confidence deciding suitable threshold values of support and confidence is critical to the quality of association rule technology. Specific mechanisms for crossover operators have been designed to extract interesting rules from a transaction database.
The method proposed in this paper is successfully applied to real-world database. The results demonstrate that the proposed algorithm is a practical method for mining association rules.

Optimum Design of Composite Laminated Plate Using Genetic Algorithm and RSM

Ammar Ali Hussein Al-filfily

Engineering and Technology Journal, 2011, Volume 29, Issue 5, Pages 1002-1020

The paper is focused on the application of the response surface method (RSM)
in structural optimization. Applications of the response surface method in the
design of composite laminated plate have been discussed. The response surface
method consists of two stages. In the first stage, the random variables is selected in
order to perform a deterministic computer simulation (finite element solution) in
the sample points. In the second stage, the approximation of the function (which
represent the buckling load) is performed in order to obtain response surfaces
using PDS module included in the ANSYS Program. This response surface is
incorporated into a genetic algorithm (GAs) for optimization of random input
variables to obtain maximum buckling load for composite laminated plate
subjected to both mechanical and thermal loading. GAs are stochastic optimization
algorithms based on natural selection and genetics. In contrast to traditional
gradient-based methods, GAs work on populations of solutions which evolve
typically over hundreds of generations. Four and five different variable
formulations are examined. It was found that for SSSS boundary condition and two
layer laminate the optimum values of buckling load for all thermal loading occur at
q1=33o, q2=59o, t1=1.23 mm and t2= 1.25 mm, also it can observe that the
significant random variable are t1 and t3 (in the case of five independent variables)
since the value of buckling load effected with t1 and t3 more than for t2.