JWSS - Journal of Water and Soil Science

Modeling of Kaboodval Dam using Plaxis software has been used for the Mouher-Columb behavior model. The effect of two continuities of embankment and watering operations on the meeting was considered. The body structure of the dam was increased from the side of the faces to the middle sections, and the maximum seating was recorded at 25-25 and at about 2200 mm. By examining at different intervals, the largest meeting was in the range of 180 to 185. That is, the level of the embankment was found to be critical in these numbers. Most concerns were regarding the middle of the dam, which had a weaker position. According to the analysis of different parts of Kaboudvall Dam, the materials forming the right wing of the dam in the middle and left wings of the dam were better. In the case of the 19th Module, besides the Mouher-Columb model, the dam could be modeled with hardening and hardening models. Here, the hardening model created a better fit. The hardening model, as it could get more data from the soil, is likely to better model the behavior of the soil dams. Due to the fact that, during the construction, the first sessions usually occur, the hardening model can have a better performance.

Accurate prediction of pore water pressure in the body of earth dams during construction with accurate methods is one of the most important components in managing the stability of earth dams. The main objective of this research is to develop hybrid models based on fuzzy neural inference systems and meta-heuristic optimization algorithms. In this regard, the fuzzy neural inference system and optimizing meta-heuristic algorithms including genetic algorithms (GA), particle swarm optimization algorithm (PSO), differential evolution algorithm (DE), ant colony optimization algorithm (ACOR), harmony search algorithm (HS), imperialist competitive algorithm (ICA), firefly algorithm (FA), and grey wolf optimizer algorithm (GWO) were used to improve training system. Three features including fill level, dam construction time, and reservoir level (dewatering) obtained from the dam instrumentation were selected as the inputs of hybrid models. The results showed that the hybrid model of the genetic algorithm in the test period had the best performance compared to other optimization algorithms with values of R2, RMSE, NRMSE, and MAE equal to 0.9540, 0.0866, 0.1232, and 0.0345, respectively. Also, ANFIS-GA, ANFIS-PSO, ANFIS-ICA, and ANFIS-HS hybrid algorithms performed better than ANFIS-GWO, ANFIS-FA, ANFIS-ACORE, and ANFIS-DE in improving ANFIS network training and predicting pore water pressure in the body earthen dams at the time of construction.