This chapter presents an over view of the current store of evolutionary algorithms and their applications. An attempt is also made to study the present applications of evolutionary algorithms in machining processes.
Boguslaw Pytlak [1] presented in his paper, the results of multi-criteria optimization of hard finish turning operation parameters of hardened 18CrMo4 steel in view of chosen parameters of surface roughness. The cutting parameters subjected to the optimization were taken as: cutting speed, feed and depth of cut (vc, f and a), while as optimization criteria were assumed for selected parameters of surface roughness: Ra, Rz and Rmax. The research was done with the help of the Modified Distance Method (MDM), from the perspective of mating of machined surface with sealing rings (Simmering rings). Set of Pareto-optimal solutions comprised of six solutions only. The reason for such situation can be seen as similarity of the optimization criteria, which in a different way described the same surface.
According to Tian-Syung Lan [2], Surface roughness was a major objective in modern Computer Numerical Control (CNC) turning industry. Most optimization researches for CNC finish turning were either accomplished within certain manufacturing circumstances, or achieved through number of experimental runs. Therefore, a general optimization scheme was deemed necessary for the industry.
Approach: In this study, four parameters (cutting depth, feed rate, speed and tool nose run off) with three levels (low, medium and high) were considered to optimize the surface roughness for Computer Numerical Control finish turning. Additionally, twenty-seven fuzzy control rules using trapezoid membership function with respect to seventeen linguistic grades for the surface roughness were constructed. Considering thirty and eighty input and output intervals respectively, the de-fuzzification using centre of gravity was moreover completed. The optimum general deduction parameters were then received through the Taguchi experiment.
Results: The confirming experiment for optimum deduction parameters was furthermore implemented on an ECOCA-3807 CNC lathe. It was shown that the surface roughness from the fuzzy deduction optimization parameters was significantly advanced compared to those from benchmark. The author concluded that, this study not only proposed a parametric deduction optimization scheme using orthogonal array, but also contributed to the satisfactory fuzzy approach to the surface roughness for CNC turning with profound insight.
Farhad Kolahan et. al [3] applied multi objective optimization of machining processes to simultaneously achieve several goals such as increased product quality, reduced time and improved efficiency of production. This article presented an approach that combines grey relational analysis and regression modelling to convert the values of multi responses obtained from Taguchi design of experiments into a multi objective model. The approach was implemented on turning process of St 50.2 Steel. After the development of the model, Analysis of Variance was applied to determine the adequacy of the model. The developed multi objective model was then optimized by simulated annealing algorithm in order to determine the best set of parameter values. This study illustrated that regression analysis can be effectively used for high precision modelling and estimation of process variables.
Meenu Gupta and Surinder Kumar [4] presented a report on experimental analysis and optimization of performance characteristics in unidirectional glass fiber reinforced plastic composites using Taguchi method and Grey relational technique. Performance parameters such as surface roughness and metal removal rate were optimized during rough cutting operation. Tool nose radius, tool rake angle, feed rate, cutting speed, cutting environment and depth of cut were taken as process parameters and investigated using mixed L18 orthogonal array. Grey relation analysis was used to optimize the parameters and Principal Component Analysis was used to find the relative significance of performance characteristics. Depth of cut was the factor, which had great influence on surface roughness and metal removal rate, followed by feed rate. The percentage contribution of depth of cut was 54.399% and feed rate was found to be 5.355%.
G. Sridhar and G. Venkateswarlu [5] suggested Taguchi and Grey Relational Analysis to optimize the machining parameters for turning of EN8steel on lathe machine to yield minimum cutting forces and surface roughness. The process parameters such as rotational speed, feed, depth of cut and cutting fluid were selected. In this study, the experiments were carried out as per Taguchi experimental design and L9 orthogonal array was used. Analysis of variance was also used to find out the most influencing processing parameters on the responses. The regression equations were also established between the process parameters and responses. The results indicated that the depth of cut is the most significant factor affecting the cutting force and surface roughness followed by a feed, speed and cutting fluid.
Abdelouahhab Jabri and Abdellah El Barkany [6], presented a multi-optimization technique based on genetic algorithms to search optimal cuttings parameters such as cutting depth, feed rate and cutting speed of multi-pass turning processes. Two objective functions were simultaneously optimized under a set of machining constraints, cutting cost and tool life time. The model dealt with multi-pass turning processes, where the cutting operations were divided into multi-pass rough machining and finish machining. Results obtained from Genetic Algorithms method were presented in Pareto frontier graphic. This technique allowed selection of optimal cutting parameters of a normal stat; other cutting parameters could be selected for different situation.
Hari Singh and Pradeep Kumar [7] worked on the objective of obtaining an optimal setting of turning process parameters (cutting speed, feed rate and depth of cut) resulting in an optimal value of the feed force when machining EN24 steel with TiC-coated tungsten carbide inserts. The effects of the selected turning process parameters on feed force and the subsequent optimal settings of the parameters were accomplished using Taguchi’s parameter design approach. The results indicated that the selected process parameters significantly affected the selected machining characteristics. The results were confirmed by further experiments.
A significant pool of CBN tool wear studies had been surveyed by Yong Huang et. al [8], in an attempt to achieve better processing and tooling applications, and discussed the tool wear pattern and mechanism perspectives. Although various tool wear mechanisms, or combination of several, coexisted and dominated in CBN turning of hardened steels, suggested that abrasion, adhesion (possibly complicated by tribo-chemical interactions), and diffusion primarily governed the CBN tool wear in hard turning.
Somashekara and Lakshmana Swamy [9] studied on optimal setting of turning parameters (Cutting speed, Feed and Depth of Cut) which resulted in an optimal value of Surface Roughness while machining Al 6351-T6 alloy with Uncoated Carbide Inserts. Several statistical modelling techniques were used to generate models including Genetic Algorithm and Response Surface Methodology. An attempt was made to generate a model to predict Surface Roughness using Regression Technique and optimize the process parameters using Taguchi Technique. S/N ratio and ANOVA analysis were also applied to obtain significant factors influencing Surface Roughness.
Aman Aggarwal and Hari Singh [10] made an attempt to review the literature on optimizing machining parameters in turning processes. Various conventional techniques employed for machining optimization included geometric programming, geometric plus linear programming, goal programming, sequential unconstrained minimization technique, dynamic programming, etc. The latest techniques for optimization included fuzzy logic, scatter search technique, genetic algorithm, Taguchi technique and response surface methodology.
Uroš Župerl and Franci Cuš [11] presented a new multi-objective optimization technique, based on ant colony optimization algorithm (ACO), to optimize the machining parameters in turning processes. Three conflicting objectives, production cost, operation time and cutting quality were simultaneously optimized. An objective function based on maximum profit in operation was used. The approach used adaptive neuro-fuzzy inference system (ANFIS) to represent the manufacturer objective function and an ant colony optimization algorithm (ACO) to obtain the optimal objective value. New evolutionary ACO was explained in detail. Also a comprehensive user friendly software package was developed to obtain the optimal cutting parameters using the proposed algorithm. An example was presented to give a clear picture from the application of the system and its efficiency. The results were compared and analysed using methods of other researchers and handbook recommendations. The results indicated that the ant colony paradigm was effective compared to other techniques carried out by other researchers.
Yigit Kazancoglu et.al [12] investigated the multi-response optimization of the turning process for an optimal parametric combination to yield the minimum cutting force and surface roughness with the maximum material-removal rate (MRR) using a combination of a Grey relational analysis (GRA) and the Taguchi method. Nine experimental runs based on an orthogonal array of the Taguchi method were performed to derive objective functions to be optimized within the experimental domain. The objective functions were selected in relation to the parameters of the cutting process: cutting force, surface roughness and MRR. The Taguchi approach was followed by the Grey relational analysis to solve the multi-response optimization problem. The significance of the factors on the overall quality characteristics of the cutting process was also evaluated quantitatively using the analysis-of-variance method. Optimal results were verified through additional experiments. It was concluded that a proper selection of the cutting parameters produced a high material removal rate with a better surface roughness and a lower cutting force.
Thamizhmanii and Hasan [13] worked on analysis of surface roughness, cutting tool forces and tool wear in machining cast gray iron. The methodology adopted was turning process. The tests were conducted by designing various cutting speeds, feeds and a constant depth of cut. In turning cast gray iron, flank wear, crater wear and built up edge are the common phenomenon. Findings from the tests were the formation of flank wear, crater wear while machining the cast gray iron. The surface roughness from various tests showed a decrease in value at higher cutting speed and feed rate. The cutting tool produced micro chipping and not affected the surface finish. Micro cracks were obtained from the edge of micro chipping. The notch wear might have been caused due to hard particles and other impurities present in the material. There was no formation of built- up- edge that is usually occurring during machining cast iron at lower cutting speed.
Mithilesh Kumaret.al [14] studied the influence of cutting parameters (cutting speed, feed per tooth, axial depth of cut and radial depth of cut) during ball-end milling of Al2014-T6 under dry condition. The experimental plan was based on face centred, rotary central composite design (RCCD). Three cutting force components i.e. tangential, radial and axial forces were measured and then analysis of variance (ANOVA) was performed. It was found that the quadratic model best fitted for prediction of the force components. The analysis of result showed that the cutting forces increases as increase in feed per tooth and axial depth of cut but decreases with increase in cutting speed. Radial depth of cut had significant effect on the cutting force components.
S.R. Das et al. [15] made an attempt has been made to evaluate the performance of multilayer coated carbide inserts during dry turning of hardened AISI 4340 steel (47 HRC). The effect of machining parameters (depth of cut, feed and cutting speed) on surface roughness (Ra) was investigated by applying ANOVA. The experiments were planned based on Taguchi’s L27 Orthogonal array design. Results showed that surface roughness (Ra) mainly influenced by feed and cutting speed, whereas depth of cut exhibited negligible influence on surface roughness. The experimental data were further analyzed to predict the optimal range of surface roughness (Ra). Finally a second order regression model was developed to find out the relationship between the machining parameters and surface roughness.
Ashok Kumar Sahoo [16] studied on the performance of multilayer coated carbide insert in the machining of hardened AISI D2 steel (53 HRC) using Taguchi design of experiment. The experiment was designed based on Taguchi L27 orthogonal array to predict surface roughness. The S/N ratio and optimum parametric condition were analysed. The analysis of variance had also been carried out to predict the significant factors affecting surface roughness. Based on Taguchi S/N ratio and ANOVA, feed was the most influencing parameter for surface roughness followed by cutting speed whereas depth of cut was least significant from the experiments. In regression model, the value of R2 being 0.98 indicated that 98 % of the total variations were explained by the model. Developed model could be effectively used to predict the surface roughness on the machining of D2 steel with 95% confidence intervals.
Mangesh R. Phate and V. H. Tatwawadi [17] developed an artificial neural network (ANN) based model of material removal rate (MRR) in the turning of ferrous and nonferrous material in a Indian small-scale industry. MRR of the formulated model was proved with the testing data and artificial neural network (ANN) model was developed for the analysis and prediction of the relationship between inputs and output parameters during the turning of ferrous and nonferrous materials. The input parameters of this model were operator, work piece, cutting process, cutting tool, Machine and the environment. A three layered feed forward back propagation neural network model was used and trained with pairs of independent/dependent datasets generated when machining ferrous and nonferrous material. A very good performance of the neural network, in terms of contract with experimental data, was achieved.
Abdelouahhab Jabri et al. [18] worked on multi objective optimization technique based on genetic algorithms to search optimal cuttings parameters (cutting depth, feed rate and cutting speed) of multi-pass turning processes. Two objective functions were simultaneously subjected to optimize under a set of practical of machining constraints, the first objective function was cutting cost and the second one was the used tool life time. Results obtained from Genetic Algorithms method were presented in Pareto frontier graphic.
Vaibhav B. Pansare and Mukund V. Kavade [19] made an attempt to obtain optimum turning parameters for minimum surface roughness value by using Ant Colony Optimization (ACO) algorithm in multi-pass turning operation. The cutting process has roughing and finishing stage. Also the relationship between the parameters and the performance measures were determined using multiple linear regression, this mathematical model is used to determine optimal parameters. The experimental results showed that the proposed technique was both effective and efficient.
Kalyanmoy Deb and Rituparna Datta [20] proposed Evolutionary multi-objective optimization (EMO) for determining optimal machining parameters for ensuring an efficient working of a machining process. The efficiency of the methodology was demonstrated through two case studies – one having two objectives and the other having three objectives. EMO solutions were modified using a local search procedure to achieve a better convergence property. A heuristic-based local search procedure was suggested for a computationally faster approach in which the problem-specific heuristics were derived from an innovative study performed on the EMO solutions.
Ozel et al. [21] carried out finish turning of AISI D2 steels (60 HRC) using ceramic wiper (multi-radii) design inserts for surface finish and tool flank wear investigation. For prediction of surface roughness and tool flank wear multiple linear regression models and neural network models were developed. Neural network based predictions of surface roughness and tool flank wear were carried out, compared with a non-training experimental data and the results thereof showed that the proposed neural network models were efficient to predict tool wear and surface roughness patterns for a range of cutting conditions. The study concluded that best tool life was obtained in lowest feed rate and lowest cutting speed combination.
Wang and Lan [22] used Orthogonal Array of Taguchi method coupled with grey relational analysis considering four parameters viz. speed, cutting depth, feed rate, tool nose run off etc. for optimizing three responses: surface roughness, tool wear and material removal rate in precision turning on an ECOCA-3807 CNC Lathe. The MINITAB software was explored to analyze the mean effect of Signal-to-Noise (S/N) ratio to achieve the multi-objective features. This study not only proposed an optimization approaches using Orthogonal Array and grey relational analysis but also contributed a satisfactory technique for improving the multiple machining performances in precision CNC turning with profound insight.
Srikanth and Kamala [23] evaluated optimal values of cutting parameters by using a Real Coded Genetic Algorithm (RCGA) and explained various issues of RCGA and its advantages over the existing approach of Binary Coded Genetic Algorithm (BCGA). They concluded that RCGA was reliable and accurate for solving the cutting parameter optimization and construct optimization problem with multiple decision variables. These decision variables were cutting speed, feed, depth of cut and nose radius. The authors highlighted that the faster solution can be obtain with RCGA with relatively high rate of success, with selected machining conditions thereby providing overall improvement of the product quality by reduction in production cost, reduction in production time, flexibility in machining parameter selection.
Reddy et al. [24] adopted multiple regression model and artificial neural network to deal with surface roughness prediction model for machining of aluminium alloys by CNC turning. For judging the efficiency and ability of the model in surface roughness prediction the authors used the percentage deviation and average percentage deviation. The study of experimental results showed that the artificial neural network was efficient as compared to multiple regression models for the prediction of surface roughness.
Thamma [25] constructed the regression model to find out the optimal combination of process parameters in turning operation for Aluminium 6061 work pieces. The study highlighted that cutting speed, feed rate, and nose radius had a major impact on surface roughness. Smoother surfaces could be produced when machined with a higher cutting speed, smaller feed rate, and smaller nose radius.
Shetty et al. [26]discussed the use of Taguchi and response surface methodologies for minimizing the surface roughness in turning of discontinuously reinforced aluminium composites (DRACs) having aluminium alloy 6061 as the matrix and containing 15 vol. % of silicon carbide particles of mean diameter 25μm under pressured steam jet approach. The measured results were then collected and analyzed with the help of the commercial software package MINITAB15. The experiments were conducted using Taguchi’s experimental design technique. The matrix of test conditions included cutting speeds of 45, 73 and 101 m/min, feed rates of 0.11, 0.18 and 0.25 mm/rev and steam pressure 4, 7, 10 bar while the depth of cut was kept constant at 0.5 mm. A second order model was established between the cutting parameters and surface roughness using response surface methodology. The experimental results revealed that the most significant machining parameter for surface roughness was steam pressure followed by feed. The predicted values and measured values were fairly close, which indicated that the developed model could be effectively used to predict the surface roughness in the machining of DRACs.
Shreemoy Kumar Nayak et al. [27] studied on the influence of different machining parameters such as cutting speed (V), feed (f) and depth of cut (t) on different performance measures during dry turning of AISI 304 austenitic stainless steel. ISO P30 grade uncoated cemented carbide inserts was used as cutting tool. L27 orthogonal array design of experiments was adopted with the following machining parameters: V= 25, 35, 45 m/min., f= 0.1, 0.15, 0.2 m/rev. and t= 1, 1.25, 1.5 mm. Three important characteristics of machinability such as material removal rate (MRR), cutting force (Fc) and surface roughness(R) were measured. Attempt was further made to simultaneously optimize the machining parameters using grey relational analysis. The recommended parametric combination based on the studied performance criteria (i.e. MRR, Fc and Ra) was found to be V =45m/min, f=0.1mm/rev, t=1.25mm. A confirmatory test was also carried out to support the analysis and an improvement of 88.78% in grey relational grade (GRG) was observed.
K. Kadirgama et al. [28] opted response ant colony optimization (RACO) for optimum surface roughness on milled mould aluminium alloys (AA6061-T6). The approach was based on Response Surface Method (RSM) and Ant Colony Optimization (ACO). The main objectives are to find the optimized parameters and the most dominant variables (cutting speed, feed rate, axial depth and radial depth). The authors had shown the use of RACO to formulate an optimised minimum surface roughness prediction model for end machining of AA6061-T6. This prediction model was tested on the validation experimental and the error analysis of the prediction result with the measured results was estimated at 4.65% for minimum surface roughness which was small and showed the efficacy of the prediction model. Finally, the simulation results have shown that ACO combined with RSM can be very successively used for reduction of the effort and time required.
Abburi N.R. and Dixit [29] proposed a methodology for the multi objective optimization of multipass turning process. A real parameter genetic algorithm was used for minimizing the production time, which provided a near optimum solution.
Adeel H. Suhail et al. [30] stated that the quality of surface finish is an important requirement for many turned work pieces to optimize measures, work piece surface temperature and surface roughness. A Taguchi technique was used to measure the optimal cutting parameters. They suggested it is possible to increase machine utilization and decrease production cost in an automated manufacturing environment.
2016-4-27-1461735646