Comparing ANFIS and integrating algorithm models (ICA-ANN, PSO-ANN, and GA-ANN) for prediction of energy consumption for irrigation land leveling. Issue 2 (4th March 2018)

• Record Type: Journal Article
• Authors: Alzoubi, Isham; Delavar, Mahmoud R.; Mirzaei, Farhad; Nadjar Arrabi, Babak
• Is Part Of: Geosystem engineering. Volume 21:Issue 2(2018)
• Page Start: 81
• Page End: 94
• Publication Date: 2018-03-04
• Subjects: Land levelling -- energy -- environmental indicators -- artificial intelligence techniques; Mining engineering -- Periodicals; Petroleum engineering -- Periodicals; Gas engineering -- Periodicals; Geology, Economic -- Periodicals; 620
• DOI: 10.1080/12269328.2017.1372225
• Languages: English
• ISSNs: 1226-9328

Abstract

Abstract: 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. The objective of this research was to develop the five methods of GA-ANN, ICA-ANN, PSO-ANN, sensitivity analysis, and ANFIS to predict the environmental indicators for land leveling. In this study, several soil properties such as soil, cut/fill volume, soil compressibility factor, specific gravity, moisture content, slope, sand percent, and soil swelling index were investigated that are the main affecting parameters in energy consumption through land leveling. A total of 90 samples were prepared from three land areas. Acquired data were used to develop accurate models for Labor, LE (Labor Energy), FE (Fuel Energy), TMC (Total Machinery Cost), and TME (Total Machinery Energy). Results of sensitivity analysis showed that only three parameters of soil compressibility, density of soil, and cut/fill volume had significant effects on energy consumption. The results showed among the mentioned methods for estimating the amount of energy required in different parts such as labor, fuel, and machinery, GA-ANN and ICA-ANN methods were more precise than others. The sensitivity analysis method was the least accurate. Finally, it was concluded that the GA-ANN method was the best due to its high R 2 and low RMSE values.