Analysis and predictive modeling of performance parameters in electrochemical drilling process

In this paper, the effect of feed rate, voltage, and flow rate of electrolyte on some performance parameters such as surface roughness, material removal rate, and over-cut of SAE-XEV-F valve-steel during electrochemical drilling in NaCl and NaNo₃ electrolytic solutions have been studied using the main effect plot, the interaction plot and the ANOVA analysis. In continuation, in this case which the training dataset was small, an investigation has been done on the capability of the optimum presented regression analysis (RA), artificial neural network (ANN), and co-active neuro-fuzzy inference system (CANFIS) to predict the surface roughness, material removal rate and over-cut. The predicted parameters by the employed models have been compared with the experimental data. The comparison of results indicated that in electrochemical drilling using different electrolytic solutions, CANFIS gives the best results to predict the surface roughness and over-cut as well, while ANN is the best for predicting the material removal rate.     

Empirical modeling and optimization of wire electrical discharge machining

Wire electrical discharge machining is a widely used process in manufacturing industries to machine complex profiles. The performance of any machining process is based on choosing the right combination of input parameters. Metal removal rate and surface roughness are the most important output parameters, which decide the performance of a machining process. The selection of optimal parameters in wire electrical discharge machining is difficult as it is a complex process and involves a large number of variables. The present work models the metal removal rate and the surface roughness in terms of the input variables using the response surface methodology and, consequently, the developed mathematical models are utilized for optimization. Since the influences of machining parameters on the metal removal rate and the surface roughness are opposite, the problem is formulated as a multiobjective optimization problem. Non-dominated sorting genetic algorithm is then applied to obtain the Pareto-optimal set of solutions.     

Investigation into erosion rate of AISI 4340 steel during wire electrical discharge turning process

Wire electrical discharge turning (WEDT) process was developed to generate cylindrical form on any electrically conductive material applied in aerospace and automotive industry. The mechanism of metal removal in WEDT process is by means of successive spark discharge. Each spark results in the formation of crater. In the present work, a new model is proposed to predict the erosion rate of each spark for a given discharge energy. A new method is proposed to measure the crater depth from 2D roughness profile of the machined component. The proposed model is validated by conducting experiments on AISI 4340 steel and the results obtained are presented in the paper. It is observed that the results are in close proximity with the experimental values at low discharge energy. The stochastic erosion mechanism of WEDT process is analyzed using scanning electron microscope images of spark eroded wire. Using the proposed model the erosion rate can be controlled and better surface characteristic of machined surface can be achieved.     

Optimum surface roughness in end milling Inconel 718 by coupling neural network model and genetic algorithm

In this study, optimum cutting parameters of Inconel 718 are determined to enable minimum surface roughness under the constraints of roughness and material removal rate. In doing this, advantages of statistical experimental design technique, experimental measurements, artificial neural network and genetic optimization method are exploited in an integrated manner. Cutting experiments are designed based on statistical three-level full factorial experimental design technique. A predictive model for surface roughness is created using a feed forward artificial neural network exploiting experimental data. Neural network model and analytical definition of material removal rate are employed in the construction of optimization problem. The optimization problem was solved by an effective genetic algorithm for variety of constraint limits. Additional experiments have been conducted to compare optimum values and their corresponding roughness and material removal rate values predicted from the genetic algorithm. Generally a good correlation is observed between the predicted optimum and the experimental measurements. The neural network model coupled with genetic algorithm can be effectively utilized to find the best or optimum cutting parameter values for a specific cutting condition in end milling Inconel 718.     

Prediction of depth removal in leather surface grit blasting using neural networks and Box-Behnken design of experiments

In this work, leather material is for the first time prepared by grit blasting process in order to improve peel strength when bonding. Peel tests show that it is the surface depth of removal rather than surface roughness that dominates the bonding performance. Therefore, measurement of surface removal is critical for surface preparation of using a grit blasting process. Indirect measurement of preparation performance is essential due to the hazardous conditions for conventional sensing equipment in the blasting chamber. A neural network modelling approach is proposed for the prediction of surface removal of leather materials, and the neural network model also characterizes the process, which is very useful for machine design and optimum control. The data used for the training of the artificial neural network is collected through screening experiments, which was efficiently planned using the Box-Behnken design method.     

Experimental investigations and modeling of drill bit-guided abrasive flow finishing (DBG-AFF) process

Abrasive flow finishing (AFF) is one of the widely used advanced finishing processes in which a small quantity of work material is removed by flowing semisolid abrasive-laden putty over the workpiece surface to be finished. AFF is popular for finishing and deburring of difficult-to-access areas. This process is also used for radiusing, producing compressive residual stresses, and removal of recast layer. In order to enhance productivity of the process, several modifications in AFF process are being tried. In this paper, a concept of rotating the medium along its axis has been introduced to achieve higher rate of finishing and material removal. This process is termed as drill bit-guided abrasive flow finishing (DBG-AFF) process. In order to provide random motion to the abrasives in the medium and to cause frequent reshuffling of the medium, the medium is pushed through a helical fluted drill, which is placed in the finishing zone. The experiments are carried out to compare AFF and DBG-AFF processes with AISI 1040 and AISI 4340 as workpiece materials. The performance of DBG-AFF as compared to AFF is encouraging, specifically with reference to percentage change in average surface roughness (% ΔR _a) and amount of material removed. Modeling using non-linear multi-variable regression analysis and artificial neural networks are carried out to conduct parametric analysis and to understand, in depth, the DBG-AFF process. The simulation data of neural network show a good agreement with experimental results.     

基于灰色理论的钛合金电火花加工工艺参数优化试验

为对材料去除速度、电极损耗和表面质量等工艺目标进行综合评价,以钛合金材料为试验对象,基于成熟的电火花加工设备,对峰值电流、脉冲宽度、占空比和抬刀周期等可调工艺参数进行正交试验研究,运用灰色理论进行试验数据分析,将多工艺目标转化为单一考量指标（灰关联度）,简化了试验过程,得到了工艺参数组合优化方案。验证试验结果表明,该参数组合能够在保证表面质量要求的同时,有效提高加工效率和降低电极损耗。     

Investigations into high-speed rough and finish end-milling of hardened EN24 steel for implementation of control strategies

High-speed end-milling is used for production of variety of parts, dies, and molds made of hardened EN24 steel which are widely used in power and transport industries. Since desired productivity and quality are important in these industries, different strategies are needed for rough and finish end-milling operations. In this paper, a framework is presented for integrating different requirements of high-speed end-milling. In flat end-milling experiments, slots are machined in hardened EN24 steel using single insert cutter under different sets of cutting parameters for roughing and finishing operations. For rough end-milling, the responses such as material removal volume, tool wear and cutting forces are measured with respect to cutting time. A response surface is developed to predict material removal volume and a set of cutting parameters is selected for a given range of material removal volume using differential evolution (DE) algorithm till the tool wear reaches certain value. The experimental data is also used to develop Bayesian-based artificial neural network (ANN) model. Using this ANN model, reference values for cutting force and cutting time are generated for rough end-milling. Similarly, DE is used to predict a set of cutting parameters for a given range of surface roughness using response surface model. The reference cutting force is obtained for finish end-milling using ANN model. These reference values are useful in the monitoring and implementation of control strategy for the high-speed end-milling operations.     

Optimization of the EDM parameters on machining Ti–6Al–4V with multiple quality characteristics

In this paper, parameter optimization of the electrical discharge machining process to Ti–6Al–4V alloy considering multiple performance characteristics using the Taguchi method and grey relational analysis is reported. Performance characteristics including the electrode wear ratio, material removal rate and surface roughness are chosen to evaluate the machining effects. The process parameters selected in this study are discharge current, open voltage, pulse duration and duty factor. Experiments based on the appropriate orthogonal array are conducted first. The normalised experimental results of the performance characteristics are then introduced to calculate the coefficient and grades according to grey relational analysis. The optimised process parameters simultaneously leading to a lower electrode wear ratio, higher material removal rate and better surface roughness are then verified through a confirmation experiment. The validation experiments show an improved electrode wear ratio of 15%, material removal rate of 12% and surface roughness of 19% when the Taguchi method and grey relational analysis are used.     

Multi-objective optimization for turning processes using neural network modeling and dynamic-neighborhood particle swarm optimization

In this paper, we introduce a procedure to formulate and solve optimization problems for multiple and conflicting objectives that may exist in turning processes. Advanced turning processes, such as hard turning, demand the use of advanced tools with specially prepared cutting edges. It is also evident from a large number of experimental works that the tool geometry and selected machining parameters have complex relations with the tool life and the roughness and integrity of the finished surfaces. The non-linear relations between the machining parameters including tool geometry and the performance measure of interest can be obtained by neural networks using experimental data. The neural network models can be used in defining objective functions. In this study, dynamic-neighborhood particle swarm optimization (DN-PSO) methodology is used to handle multi-objective optimization problems existing in turning process planning. The objective is to obtain a group of optimal process parameters for each of three different case studies presented in this paper. The case studies considered in this study are: minimizing surface roughness values and maximizing the productivity, maximizing tool life and material removal rate, and minimizing machining induced stresses on the surface and minimizing surface roughness. The optimum cutting conditions for each case study can be selected from calculated Pareto-optimal fronts by the user according to production planning requirements. The results indicate that the proposed methodology which makes use of dynamic-neighborhood particle swarm approach for solving the multi-objective optimization problems with conflicting objectives is both effective and efficient, and can be utilized in solving complex turning optimization problems and adds intelligence in production planning process.     

An integrated study of surface roughness for modelling and optimization of cutting parameters during end milling operation

The aim of this study is to develop an integrated study of surface roughness to model and optimize the cutting parameters when end milling of AISI 1040 steel material with TiAlN solid carbide tools under wet condition. A multiple regression analysis using analysis of variance is conducted to determine the performance of experimental measurements and to show the effect of four cutting parameters on the surface roughness. Artificial neural network (ANN) based on Back-propagation (BP) learning algorithm is used to construct the surface roughness model exploiting a full factorial design of experiments. Genetic algorithm (GA) supported with the tested ANN is utilized to determine the best combinations of cutting parameters providing roughness to the lower surface through optimization process. GA improves the surface roughness value from 0.67 to 0.59 μm with approximately 12% gain. Then, machining time has also decreased from 1.282 to 1.0316 min by about 20% reduction based on the cutting parameters before and after optimization process using the analytical formulas. The final measurement experiment has been performed to verify surface roughness value resulted from GA with that of the material surface by 3.278% error. From these results, it can be easily realized that the developed study is reliable and suitable for solving the other problems encountered in metal cutting operations as the same as surface roughness.     

A study of surface roughness in drilling using mathematical analysis and neural networks

Drilling is one of the most common and fundamental machining processes. It is most frequently performed in material removal and is used as a preliminary step for many operations, such as reaming, tapping and boring. Because of their importance in nearly all production operations, twist drills have been the subject of numerous investigations. The aim of this study is to identify suitable parameters for the prediction of surface roughness. Back propagation neural networks are used for the detection of surface roughness. Drill diameter, cutting speed, feed and machining time are given as inputs to the neural network structure and surface roughness was estimated. Drilling experiments with 12 mm drills are performed at three cutting speeds and feeds. The number of neurons are selected from 1,2,3, ..., 20. The learning rate was selected as 0.01, and no smoothing factor was used. The best structure of neural network was selected based on a criteria including the minimum of sum of squares with the actual value of surface roughness. For mathematical analysis, an inverse coefficient matrix method was used for calculating the estimated values of surface roughness. Comparative analysis was performed between actual values and estimated values obtained by mathematical analysis and neural network structures.     

Surface Improvement Using a Combination of Electrical Discharge Machining with Ball Burnish Machining Based on the Taguchi Method

This study investigates the feasibility of improving surface integrity via a novel combined process of electrical discharge machining (EDM) with ball burnish machining (BBM) using the Taguchi method. To provide burnishing immediately after the EDM process, ZrO₂ balls were attached to the tool electrode in the experiments. To verify the optimal process, three observed values, i.e. material removal rate, surface roughness, and improvement ratio of surface roughness were chosen. In addition, six independent parameters were adopted for evalu-ation by the Taguchi method. From the ANOVA and S/N ratio response graph, the significant parameters and the optimal combination level of machining parameters were obtained. Experimental results indicate that the combined process effectively improves the surface roughness and eliminates the micro pores and cracks caused by EDM. Therefore, the combination of EDM and BBM is a feasible process by which to obtain a fine-finishing surface and achieve surface modification.     

Thermal modeling of the material removal rate and surface roughness for die-sinking EDM

The die-sinking electrical discharge machining (EDM) process is characterized by slow processing speeds. Research effort has been focused on optimizing the process parameters so as for the productivity of the process to be increased. In this paper a simple, thermal based model has been developed for the determination of the material removal rate and the average surface roughness achieved as a function of the process parameters. The model predicts that the increase of the discharge current, the arc voltage or the spark duration results in higher material removal rates and coarser workpiece surfaces. On the other hand the decrease of the idling time increases the material removal rate with the additional advantage of achieving slightly better surface roughness values. The model’s predictions are compared with experimental results for verifying the approach and present good agreement with them.     

Application of adaptive neuro-fuzzy inference system and cuckoo optimization algorithm for analyzing electro chemical machining process

Electrochemical machining process (ECM) is increasing its importance due to some of the specific advantages which can be exploited during machining operation. The process offers several special privileges such as higher machining rate, better accuracy and control, and wider range of materials that can be machined. Contribution of too many predominate parameters in the process, makes its prediction and selection of optimal values really complex, especially while the process is programmized for machining of hard materials. In the present work in order to investigate effects of electrolyte concentration, electrolyte flow rate, applied voltage and feed rate on material removal rate (MRR) and surface roughness (SR) the adaptive neuro-fuzzy inference systems (ANFIS) have been used for creation predictive models based on experimental observations. Then the ANFIS 3D surfaces have been plotted for analyzing effects of process parameters on MRR and SR. Finally, the cuckoo optimization algorithm (COA) was used for selection solutions in which the process reaches maximum material removal rate and minimum surface roughness simultaneously. Results indicated that the ANFIS technique has superiority in modeling of MRR and SR with high prediction accuracy. Also, results obtained while applying of COA have been compared with those derived from confirmatory experiments which validate the applicability and suitability of the proposed techniques in enhancing the performance of ECM process.     

Modeling and Optimization of Machining Process in Discontinuously Reinforced Aluminium Matrix Composites

This article presents development of an Artificial Neural Networks (ANN) based model for the prediction of surface roughness during machining of composite material using Back Propagation algorithm. Statistically designed experiments based on Taguchi method were carried out on machining of Al/SiCp composite material. The experimentation helped generate a knowledge base for the ANN system and understand the relative importance of process, tool and work material dependent parameters on the roughness of surface generated during machining. The ANN model trained using the experimental data was found to predict the surface roughness with fair accuracy. An optimization approach was also proposed to obtain optimal cutting conditions that yield the desired surface roughness while maximizing the metal removal rate.     

Soft computing models based prediction of cutting speed and surface roughness in wire electro-discharge machining of tungsten carbide cobalt composite

This paper reports on an experimental investigation of small deep hole drilling of Inconel 718 using the EDM process. The parameters such as peak current, pulse on-time, duty factor and electrode speed were chosen to study the machining characteristics. An electrolytic copper tube of 3 mm diameter was selected as a tool electrode. The experiments were planned using central composite design (CCD) procedure. The output responses measured were material removal rate (MRR) and depth averaged surface roughness (DASR). Mathematical models were derived for the above responses using response surface methodology (RSM). The results revealed that MRR is more influenced by peak current, duty factor and electrode rotation, whereas DASR is strongly influenced by peak current and pulse on-time. Finally, the parameters were optimized for maximum MRR with the desired surface roughness value using desirability function approach.     

Optimization of milling parameters using artificial neural network and artificial immune system

The present paper is an attempt to predict the effective milling parameters on the final surface roughness of the work-piece made of Ti-6Al-4V using a multi-perceptron artificial neural network. The required data were collected during the experiments conducted on the mentioned material. These parameters include cutting speed, feed per tooth and depth of cut. A relatively newly discovered optimization algorithm entitled, artificial immune system is used to find the best cutting conditions resulting in minimum surface roughness. Finally, the process of validation of the optimum condition is presented.     

Neural-network-based modeling and optimization of the electro-discharge machining process

In this research, a new integrated neural-network-based approach is presented for the prediction and optimal selection of process parameters in die sinking electro-discharge machining (EDM) with a flat electrode (planing mode). A 3–6–4–2-size back-propagation neural network is developed to establish the process model. The current (I), period of pulses (T), and source voltage (V) are selected as network inputs. The material removal rate (MRR) and surface roughness (Ra) are the output parameters of the model. Experimental data were used for training and testing the network. The results indicate that the neural model can predict process performance with reasonable accuracy, under varying machining conditions. The effects of variations of the input machining parameters on process performance are then investigated and analyzed through the network model. Having established the process model, a second network, which parallelizes the augmented Lagrange multiplier (ALM) algorithm, determines the corresponding optimum machining conditions by maximizing the MRR subject to appropriate operating and prescribed Ra constraints. The optimization procedure is carried out in each level of the machining regimes, such as finishing (Ra≤2 μm), semi-finishing (Ra≤4.5 μm), and roughing (Ra≤7 μm), from which, the optimal machining parameter settings are obtained. The optimization results have also been discussed, verified experimentally, and the amounts of relative errors calculated. The errors are all in acceptable ranges, which, again, confirm the feasibility and effectiveness of the adopted approach.     

Multi-objective optimization of process parameters in Electro-Discharge Diamond Face Grinding based on ANN-NSGA-II hybrid technique

The effective study of hybrid machining processes (HMPs), in terms of modeling and optimization has always been a challenge to the researchers. The combined approach of Artificial Neural Network (ANN) and Non-Dominated Sorting Genetic Algorithm-II (NSGA-II) has attracted attention of researchers for modeling and optimization of the complex machining processes. In this paper, a hybrid machining process of Electrical Discharge Face Grinding (EDFG) and Diamond Face Grinding (DFG) named as Electrical Discharge Diamond face Grinding (EDDFG) have been studied using a hybrid methodology of ANN-NSGA-II. In this study, ANN has been used for modeling while NSGA-II is used to optimize the control parameters of the EDDFG process. For observations of input-output relations, the experiments were conducted on a self developed face grinding setup, which is attached with the ram of EDM machine. During experimentation, the wheel speed, pulse current, pulse on-time and duty factor are taken as input parameters while output parameters are material removal rate (MRR) and average surface roughness (R_a). The results have shown that the developed ANN model is capable to predict the output responses within the acceptable limit for a given set of input parameters. It has also been found that hybrid approach of ANN-NSGA-II gives a set of optimal solutions for getting appropriate value of outputs with multiple objectives.