Adaptive neuro-fuzzy inference system multi-objective optimization using the genetic algorithm/singular value decomposition method for modelling the discharge coefficient in rectangular sharp-crested side weirs

In the present article, the adaptive neuro-fuzzy inference system (ANFIS) is employed to model the discharge coefficient in rectangular sharp-crested side weirs. The genetic algorithm (GA) is used for the optimum selection of membership functions, while the singular value decomposition (SVD) method helps in computing the linear parameters of the ANFIS results section (GA/SVD-ANFIS). The effect of each dimensionless parameter on discharge coefficient prediction is examined in five different models to conduct sensitivity analysis by applying the above-mentioned dimensionless parameters. Two different sets of experimental data are utilized to examine the models and obtain the best model. The study results indicate that the model designed through GA/SVD-ANFIS predicts the discharge coefficient with a good level of accuracy (mean absolute percentage error?=?3.362 and root mean square error?=?0.027). Moreover, comparing this method with existing equations and the multi-layer perceptron–artificial neural network (MLP-ANN) indicates that the GA/SVD-ANFIS method has superior performance in simulating the discharge coefficient of side weirs.     

Comparison of genetic programming and radial basis function neural network for open-channel junction velocity field prediction

In this paper, a new fuzzy adaptive artificial physics optimization (FAAPO) algorithm is used to solve security-constrained optimal power flow (SCOPF) problem with wind and thermal power generators. The stochastic nature of wind speed is modeled as a Weibull probability density function. The production cost is modeled with the overestimation and underestimation of available wind energy and included in the conventional SCOPF. Wind generation cost model comprises two components, viz. reserve capacity cost for wind power surplus and penalty cost for wind power shortage. The selection of optimal gravitational constant (G) is a tedious process in conventional artificial physics optimization (APO) method. To overcome this limitation, the gravitational constant (G) is fuzzified in this work. Therefore, based upon the requirement, the gravitational constant changes adaptively. Hence, production cost is reduced, settles at optimum point and takes less number of iterations. The proposed algorithm is tested on IEEE 30-bus system and Indian 75-bus practical system, including wind power in both the test systems. It is observed that FAAPO can outperform BAT algorithm and APO algorithm. Hence, the proposed algorithm can be used for integration of wind power with thermal power generators.

     

Estimating shear stress in a rectangular channel with rough boundaries using an optimized SVM method

Neural Computing and Applications - The accurate simulation of wall and bed shear stresses in rectangular channels is one of the most important topics in hydraulic engineering. In this study, the...     

Flexible RollScann-design of one-tooth-roll-master and simulations for data acquisition

The recent improvements in the design and production of gears are not matched by the improvements in the development of measuring techniques and evaluation standards which can, in short time, give precise information about the quality of the produced gear. The inspection of gears with tooth flank modifications is still conducted by measuring of the profile and flank lines, pitch and concentricity. Furthermore topographical measurement on the coordinate measuring machine is an expensive and lasting process. This paper presents the development of a new, flexible gear-measuring machine called RollScan, which can measure the entire gear topography in a few minutes and can be introduced directly into the production line. For this, a machine with four axes and the control, a new one tooth roll master and evaluation software is designed, which makes the machine flexible and enables a variety of gear measurements without any special mechanical adjustments. The investigations described in this paper were sponsored by InnoNet from BMWi (16IN0276).     

A comparison of artificial intelligence-based classification techniques in predicting flow variables in sharp curved channels

Engineering with Computers - Due to the complexity of variable distributions, it is essential to evaluate the flow patterns in sharp curved channels with different angles. It has recently become...     

Advancing Freshwater Lake Level Forecast Using King’s Castle Optimization with Training Sample Adaption and Adaptive Neuro-Fuzzy Inference System

Water Resources Management - This study presents a novel method for more accurate forecasting freshwater Lake Levels with complex fluctuation patterns due to multiple anthropogenic demands and...     

New radial basis function network method based on decision trees to predict flow variables in a curved channel

Neural Computing and Applications - Open channel bends have fascinated engineers and scientists for decades while providing water for domestic, irrigation and industrial consumption. The presence...     

Efficient shear stress distribution detection in circular channels using Extreme Learning Machines and the M5 model tree algorithm

With the aid of 174 laboratory data sets, Extreme Learning Machine (ELM) and decision tree (M5) models were investigated in predicting the shear stress distribution in circular channels. To evaluate the sensitivity of the input variables, 15 different input combinations were applied to each model. The calculation results show that the Re and y/P parameter values greatly affect ELM method performance, while y/P and h/D are sensitive to shear stress distribution modeling with M5. The best models among ELM and M5 were compared with an equation based on the Shannon entropy. According to the comparison results, the two proposed models outperform the Shannon entropy equation. Moreover, the ELM method’s function is superior in estimating the shear stress distribution and more adapted to experimental data with average Root Mean Square Error (RMSE) of 0.0236 compared to the M5 method with RMSE of 0.0364.