Earthwork Volume Optimization Using Imperialistic Competitive Algorithm to Minimize Energy Consumption of Agricultural Land Leveling
محورهای موضوعی : Data Envelopment Analysis
1 - Department of Surveying and Geometric Eng., Engineering Faculty, University of Tehran, Iran
کلید واژه: Optimization, energy, Land leveling, Imperialistic Competitive Algorithm, Earthwork, Cut-Fill Volume (V),
چکیده مقاله :
Land leveling is one of the most important steps in soil preparation for consequent objectives. Parallel policies need to take both energy and environmental subjects into the account as well as certain financial development and eco-friendly protection. Energy is one of the most important elements in agricultural sector. Nevertheless, pollution is linked with the usage of fossil fuels (particularly gasoline) as an energy source. Earthwork optimization plays an important role in reducing the total cost of highway projects. In this research, ICA has been followed to optimize earthwork volume for minimizing energy consumption of agricultural land leveling compared to minimum least squares, genetic algorithm, particle swarm optimization (PSO) have been employed for developing of optimization the energy related and other parameters. The study was specified based on the proposed land leveling project in district of Ahwaz, Iran. The study farm was a 70 ha area and located in the west of Iran. Topography of the farm was mapped in the scale of mapping as fine as 1:500. The outputs of the plan were length, width and height of points (coordinates of x, y and z) and the grid size in the region was 20 m×20 m. The aim of this work was use of new techniques and specifically optimization methods such as Imperialist competitive algorithm, genetic algorithms and PSO in modeling the leveling plane to minimize cut and fill volume and consequently the amount of energy consumption of leveling operations. It has been assumed that soil cut and fill volumes are equal and no need to move/ remove excessive soil. Therefore, there is no need to define a cut/fill variable in the model based on ICA. The results indicated that ICA offers a plan of earthwork, minimizing energy consumption of land leveling more efficiently than minimum least squares, genetic algorithm and PSO.
Land leveling is one of the most important steps in soil preparation for consequent objectives. Parallel policies need to take both energy and environmental subjects into the account as well as certain financial development and eco-friendly protection. Energy is one of the most important elements in agricultural sector. Nevertheless, pollution is linked with the usage of fossil fuels (particularly gasoline) as an energy source. Earthwork optimization plays an important role in reducing the total cost of highway projects. In this research, ICA has been followed to optimize earthwork volume for minimizing energy consumption of agricultural land leveling compared to minimum least squares, genetic algorithm, particle swarm optimization (PSO) have been employed for developing of optimization the energy related and other parameters. The study was specified based on the proposed land leveling project in district of Ahwaz, Iran. The study farm was a 70 ha area and located in the west of Iran. Topography of the farm was mapped in the scale of mapping as fine as 1:500. The outputs of the plan were length, width and height of points (coordinates of x, y and z) and the grid size in the region was 20 m×20 m. The aim of this work was use of new techniques and specifically optimization methods such as Imperialist competitive algorithm, genetic algorithms and PSO in modeling the leveling plane to minimize cut and fill volume and consequently the amount of energy consumption of leveling operations. It has been assumed that soil cut and fill volumes are equal and no need to move/ remove excessive soil. Therefore, there is no need to define a cut/fill variable in the model based on ICA. The results indicated that ICA offers a plan of earthwork, minimizing energy consumption of land leveling more efficiently than minimum least squares, genetic algorithm and PSO.
