Predictive Modeling and Optimization of Cutting Forces Through RSM and Taguchi Techniques in the Turning of ASTM B574 (Hastelloy C-22)

In this chapter, the impact of cutting parameters (depth of cut, cutting speed, feed, flow, rake angle, lead angle) on cutting forces in the turning process with regard to ASTM B574 (Hastelloy C-22) material has been investigated. Variance analysis has been applied in order to determine the factors affecting the cutting forces. The optimization of the parameters affecting the surface roughness has been obtained using response surface methodology (RSM) based on the Taguchi orthogonal experimental design. The accuracy of the developed models required for the estimation of the force values (Fx, Fy, Fz) is quite successful. In this study, where the R2 value has been used as the criterion/measure, accuracy values of 93.35%, 95.03%, and 95.09% have been achieved for Fx, Fy, and Fz, respectively. As a result of the ANOVA analysis, the most effective parameters for Fx at a 95% confidence interval are depth of cut, feed rate, flow, and rake angle. The most effective parameter for Fy is depth of cut, while the most effective parameters for Fz are depth of cut, feed rate, and flow, respectively.

Optimum Design of Reinforced Concrete Retaining Walls

Methodologies based on metaheuristic algorithms such as particle swarm optimization, harmony search algorithm, and teaching-learning-based optimization are proposed for optimum design of reinforced concrete cantilever retaining walls. The objective function of optimization is to find a design providing minimum cost, including material and construction costs. For this purpose, the best combination of 11 design variables (heel and toe projections, stem thickness at the top and bottom of a wall, slab thickness and rebar diameters, and spacing between the bars) that satisfy 29 design constraints including stability (overturning, sliding, and bearing) and reinforced concrete design of the wall are searched during the optimization process. The rules of ACI 318 14 (building code requirements for structural concrete) are used for the reinforced concrete design. In order to determine the strengths and weaknesses of algorithms, several different cases are investigated. As conclusions, some suggestions have been obtained that will lead to future work in this field.

Multi-Performance Optimization in Friction Stir Welding of Aluminum Alloy Using Response Surface Methodology

This chapter presents the friction stir welding (FSW) of aluminum alloy AA-5083-O using vertical milling machine. In present FSW experimentation, effects of different process parameter namely tool rotation speed, welding speed, tool geometry, and tool shoulder diameter have been determined on welding quality of two pieces of AA-5083-O using response surface methodology (RSM). The optimal sets of process parameters have been determined for weld quality characteristics namely tensile strength (UTS) and percentage elongation (%EL). In present experimentations, a specially designed tool made of high carbon steel with different shoulder diameters (15mm, 17.5mm, and 20 mm) having constant pin length (6 mm) were used for FSW of two pieces of aluminum alloy. The ANOVA and pooled ANOVA were used to study the effect of FSW parameters on UTS and %EL. Multi response optimization has been carried out using desirability function in conjunction with RSM to obtain the optimal setting of process parameters for higher UTS and lower %EL.

Improvement of RSM Prediction and Optimization by Using Box-Cox Transformation

Electrocoagulation can be effectively used in the elimination of the colloids from the tailings of the mineral industries. Owing to the numerous operational parameters of this physicochemical process, the best engineering technique for the characterization of the process is RSM. In this chapter, a non-transformed quadratic model is firstly formed considering the supernatant turbidity of the electrocoagulation experiments as a function of temperature, pH, and electrical current. Then, the non-normality and the heteroscedasticity of this initial model was indicated. These drawbacks were improved by using the Box-Cox transformation with λ of -0.32 and a new model with a perfect normality and homoscedasticity was obtained. The R2 value increased from 81.60% to 99.48% and adjusted R2 increased from 48.48% to 99.22% upon the transformation. According to the confirmed optimization results of the Box-Cox transformed model, the maximum desirability was obtained at pH of 5, temperature of 85°C, and electrical current of 0.25A, and the supernatant turbidity decreased down to 2.25 NTU.

Implementation of Genetic-Algorithm-Based Forecasting Model to Power System Problems

Power system includes many types of markets. Such markets are generally cleared at certain times, whereas market participators have to determine their operational plans before meeting the actual conditions. Therefore, forecasting methods can assist market players. Forecasting methods are applied to forecast electricity demand. The unknown conditions in the power system are increased by integration of renewable generation units. Forecasting methods, which are used for the load forecasting, are updated because the output power of renewable generation units such as wind farms and photovoltaic (PV) panels have more deviation than power demand. The pool market can be introduced as other parameter that is forecasted by market players. In this chapter, the authors investigate a mathematical model for forecasting of wind. Then, the forecasting model is proposed. Genetic algorithm is applied as an optimization method to handle delay associated with wind forecasting.

Usage of Differential Evolution Algorithm in the Calibration of Parametric Rainfall-Runoff Modeling

In recent years, global optimization algorithms are used in many engineering applications. Calibration of certain parameters at conceptualization of hydrological models is one example of these. An important issue in interpreting the effects of climate change on the basin depends on selecting an appropriate hydrological model. Not only climate change impact assessment studies, but also many water resources planning studies refer to such modeling applications. In order to obtain reliable results from these hydrological models, calibration phase of the models needs to be done well. Hence, global optimization methods are utilized in the calibration process. In this chapter, the differential evolution algorithm (DEA), which has rare application in the hydrological modeling literature, was explained. As an application, the use of the DEA algorithm in the hydrological model calibration phase was mentioned. DYNWBM, a lumped model with five parameters, was selected as the hydrological model. The calibration and then validation period performances of the DEA based DYNWBM model were tested and also compared with other global optimization algorithms. According to the results derived from the study, hydrological model appropriately reflects the rainfall-runoff relation of basin for both periods.

Robust Design of Helicopter Rotor Flaps Using Bat Algorithm

The objective of this chapter is to determine an optimal trailing edge flap configuration and flap location to achieve minimum hub vibration levels and flap actuation power simultaneously. An aeroelastic analysis of a soft in-plane four-bladed rotor is performed in conjunction with optimal control. A second-order polynomial response surface based on an orthogonal array (OA) with 3-level design describes both the objectives adequately. Two new orthogonal arrays called MGB2P-OA and MGB4P-OA are proposed to generate nonlinear response surfaces with all interaction terms for two and four parameters, respectively. A multi-objective bat algorithm (MOBA) approach is used to obtain the optimal design point for the mutually conflicting objectives. MOBA is a recently developed nature-inspired metaheuristic optimization algorithm that is based on the echolocation behaviour of bats. It is found that MOBA inspired Pareto optimal trailing edge flap design reduces vibration levels by 73% and flap actuation power by 27% in comparison with the baseline design.

Predicting Human Actions Using a Hybrid of ReliefF Feature Selection and Kernel-Based Extreme Learning Machine

Human activity recognition (HAR) is a growing field that provides valuable information about a person. Sensor-equipped smartwatches stand out in these studies in terms of their portability and cost. HAR systems usually preprocess raw signals, decompose signals, and then extract attributes to be used in the classifier. Attribute selection is an important step to reduce data size and provide appropriate parameters. In this chapter, classification of eight different actions (brushing teeth, walking, running, vacuuming, writing on the board, writing on paper, using the keyboard, and stationary) has been performed with smartwatch motion sensor data. Forty-two different features have been extracted from the motion sensor signals and the feature selection has been performed with the ReliefF algorithm. After that, performance evaluation has been performed with four different machine learning methods. With this study in which the best results have been obtained with the kernel-based extreme learning machine (KELM) algorithm, estimation of human action has been performed with high accuracy.

Optimization of Pile Groups Under Vertical Loads Using Metaheuristic Algorithms

Construction of foundations on soft/loose soil deposits causes some big problems in geotechnical engineering. The vertical loads can cause failure and/or extreme settlement in soft/loose soil deposit. Constructing piles under foundations to transfer the loads to stiff soil layer is one of the widely used solutions to prevent these problems. The interaction between the piles in a group of piles is described as “group efficiency” and this interaction causes the reduction in the load-bearing capacity of the piles. For a safe and economical design, optimization must be done to estimate the optimum number of piles in the group. This chapter aims to investigate the robustness of commonly used optimization algorithms and determine the most efficient algorithms for pile group optimization problems. Consequently, the proposed methods are going to help engineers to make fast, safe, and economical designs for pile groups under vertical foundation loads. In this chapter, bearing capacities and optimization of bored pile groups constructed in soft soils are discussed.

Flood Forecasting and Uncertainty Assessment Using Wavelet- and Bootstrap-Based Neural Networks

Accurate and reliable forecasting of flood is inevitable for flood control planning and rehabilitation. There are several models available for flood forecasting, but as far as accuracy, reliability, and data scarcity are concerned, soft computing techniques (e.g., artificial neural networks) have been found to achieve the target. A wavelet-, bootstrap-, and neural-network-based framework (BWANN) is presented here for flood forecasting. Performance comparison of the proposed BWANN model is presented with wavelet-based ANN (WANN), wavelet-based MLR (WMLR), bootstrap- and wavelet-analysis-based multiple linear regression models (BWMLR), traditional ANN, and traditional multiple linear regression (MLR) models for flood forecasting. For development of WANN models, original time series data is decomposed using wavelet transformation, and wavelet sub-time series are considered to develop WANN model. A comparative analysis is carried out among different approaches of WANN model development using wavelet sub-time series.