Improving Rainfall Forecasting Efficiency Using Modified Adaptive Neuro-Fuzzy Inference System (MANFIS)

Rainfall is one of the most complicated effective hydrologic processes in runoff prediction and water management. The adaptive neuro-fuzzy inference system (ANFIS) has been widely used for modeling different kinds of nonlinear systems including rainfall forecasting. Adaptive Neuro-Fuzzy Inference Systems (ANFIS) combines the capabilities of Artificial Neural Networks (ANN) and Fuzzy Inference Systems (FIS) to solve different kinds of problems, especially efficient in rainfall prediction. This paper after reconsidering conventional ANFIS architecture brings up a modified ANFlS (MANFlS) structure developed with attention to making ANFIS technique more efficient regarding to Root Mean Square Error (RMSE), Correlation Coefficient (R ²), Root Mean Absolute Error (RMAE), Signal to Noise Ratio (SNR) and computing epoch. The modified ANFIS (MANFIS) architecture is simpler than conventional ANFIS with nearly the same performance for modeling nonlinear systems. In this study, two scenarios were introduced; in the first scenario, monthly rainfall was used solely as an input in different time delays from the time (t) to the time (t-4) to conventional ANFIS, second scenario used the modified ANFIS to improve the rainfall forecasting efficiency. The result showed that the model based Modified ANFIS performed higher rainfall forecasting accuracy; low errors and lower computational complexity (total number of fitting parameters and convergence epochs) compared with the conventional ANFIS model.     

Improving the quality of surface in the polishing process with the magnetic abrasive powder polishing using a high-frequency induction heating source on CNC table

In this research, polishing flat surfaces has been done by using a completely new and innovative method. In this method, rotary magnetic tool that carry magnetic abrasive powders, is placed in a very strong thermal induction field, and magnetic rotary tool frequently change its direction from clockwise (CW) to counterclockwise (CCW) and CCW to CW. The frequency of changing rotation direction is an important parameter of this innovation method. The intended pieces for polishing operations have been placed on a synchronic two-axis Cartesian CNC table, and the gap between rotary magnetic tool and the sheet surface can be controlled by a power transmission screw operating in the direction of the vertical axis. Several experiments have proved high performance of the new proposed method in the process of polishing.     

Estimating process capability indices of multivariate nonnormal processes

The capability analysis of production processes where there are more than one correlated quality variables is a complicated task. The problem becomes even more difficult when these variables exhibit nonnormal characteristics. In this paper, a new methodology is proposed to estimate process capability indices (PCIs) of multivariate nonnormal processes. In the proposed methodology, the skewness of the marginal probability distributions of the variables is first diminished by a root transformation technique. Then, a Monte Carlo simulation method is employed to estimate the process proportion of nonconformities (PNC). Next, the relationship between PNC and PCI is found, and finally, PCI is estimated using PNC. Several multivariate nonnormal distributions such as Beta, Weibull, and Gamma are taken into account in simulation experiments. A real-world problem is also given to demonstrate the application of the proposed procedure. The results obtained from both the simulation studies and the real-world problem show that the proposed method performs well and is able to estimate PCI properly.     

A solidification model for prediction of castability in the precipitation-strengthened nickel-based superalloys

The Scheil equation was used to model the solidification path, microsegregation of alloying elements in the interdendritic regions, solidification temperature ranges, and to predict the formation of secondary structures and the castability behavior of as-cast superalloys. 4 experimental alloys with pre-specified γ-Ti,Nb,Al,Mo composition containing different Nb, Ti and Al contents were designed using vacuum induction melting furnace. The produced as-cast superalloys were characterized using optical and scanning electron microscopy equipped with energy dispersive X-ray spectrometer and TG–DSC analysis. The experiments showed logic conformity to the modeling results. The model and experiment confirmed the highest segregation behavior for Ti and Nb. All the experimental superalloys indicated the remarkable tendency to form secondary eutectic structures at the last stages of solidification. Superalloy with chemical composition of γ-3.5%Mo,1.8%Al,4%Ti,2.9%Nb showed the shorter solidification temperature range and the best castability.     

The effect of pH and calcium ion on rheological behaviour of β‐lactoglobulin‐basil seed gum mixed gels

Effect of pH (4.5–7.5) and Ca²⁺ (0.01–0.5 m ) on gelation of single and mixed systems of 10% β‐lactoglobulin (BLG) and 1% basil seed gum (BSG) was investigated. The gelling point of BLG and BSG gels was strongly pH‐dependent, and stiffer gels formed at higher pH. The BLG gels were formed upon heating to 90 °C and reinforced on cooling to 20 °C; however, the gelation of BSG occurred at temperatures below 70 °C. By increasing Ca²⁺ concentration, storage modulus of BLG and BSG gels were increased, although pH had a greater effect than Ca²⁺. In contrast, mixed systems showed two distinct types of behaviour: BLG gel formation and BSG network, suggesting that phase‐separated gels were formed. In addition, higher strength was obtained for BLG‐BSG mixture at higher Ca²⁺ concentration.     

Osmotic and activity coefficients in the solutions of 1- and 2-naphthol in methanol and ethanol at 298.15 K

The osmotic coefficient of the solution, activity of the solvent and activity coefficient of the solute in solutions of 1- and 2-naphthol in methanol and ethanol have been measured by the isopiestic method. The experimental osmotic coefficient data were correlated using the Non-Random Two Liquid model (NRTL), the Non-Random Factor model (NRF), the two suffix Margules equation and a polynomial in terms of the molality of the solute. The models give reliable results for the correlation of the osmotic coefficient data. The activity coefficients of 1- and 2-naphthol were evaluated according to the considered methods using the parameters obtained by the correlation of osmotic coefficients.