Rockfill dams are economical and fast tools for flood detention and control purposes. Artificial intelligence approaches may provide user-friendly alternatives to very complex and time-consuming numerical methods such as finite volume and finite element for predicting flow through rockfill dam. Therefore, this paper examines the potential of coactive neuro-fuzzy inference system (CANFIS) for estimation of flow through trapezoidal and rectangular rockfill dams. The results showed that accurate flow predictions can be achieved with a CANFIS with the Takagi-Sugeno-Kang (TSK) fuzzy model and the Bell membership function for both trapezoidal and rectangular rockfill dams. Furthermore, LevenbergMarquardt and Delta-Bar-Delta were the best algorithms for training the network in order to estimate flow through rectangular and trapezoidal rockfill dams, respectively. Overall, the results of this study suggest the possibility for using CANFIS for prediction of flow through rockfill dam.
Numerical simulation of groundwater flow used for the estimation of hydraulic and hydrologic parameters which is an important tool for the management of aquifers. This study presents the results of a mathematical model developed for the simulation of groundwater flow in Nahavand plain aquifer in the southwest Hamadan province. For this purpose Groundwater Modeling Software (GMS) was used which supports the MODFLOW-2000 code. After gathering required data such as the hydrological, hydrogeological and topography maps, a 3D hydrogeological model of plain was constructed with borehole and surface elevation data. Then MODFLOW was used for simulation of flow. After initial simulation of the flow, the model was calibrated in steady state with trial-and-error and parameter estimation methods the observed head of groundwater table monitoring data of 1997. Results of calibration show that error between observed head and computed head is in allowable range. Also results of computed head with model show that groundwater flow is in the direction of the dominate slope (southeast to northwest). Finally MODPATH code which simulates advective transport of particles was used for estimation of flow path and source of contaminants.
This article investigates a fault detection system of MF285 Tractor gearbox empirically. After designing and constructing the laboratory set up, the vibration signals obtained using a Piezoelectric accelerometer which has been installed on the Bearing housings are related to rotary gear number 1 in two directions perpendicular to the shaft and in line with the shaft. The vector data were conducted in three different speeds of shaft 1500, 1000 and 2000 rpm and 130 repetitions were performed for each data vector state to increase the precision of neural network by using more data. Data captured were transformed to frequency domain for analyzing and input to the neural network by Fourier transform. To do neural network analysis, significant features were selected using a genetic algorithm and compatible neural network was designed with data captured. According to the results of the best output mode for each position of the sensor network in 1000, 1500 and 2000 rpm, totally for the six output models, all function parameters for MATLAB Software quality content calculated to evaluate network performance. These experiments showed that the overall mean correlation coefficient of the network to adapt to the mechanism of defect detection and classification system is equal to 99.9%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.