Optimization of Electrochemical Machining Process Based on Artificial Neural Network Technique

Many advanced machining processes have higher initial investment, maintenance and tooling costs. In these circumstances micro electrochemical machining [µECM] processes meet the requirements with better efficiency and economy. The micro electrochemical machining process parameter such as electrolyte concentration, machine voltage, and pulse on time and duty factor are optimized with considerations of the multiple performance characteristics such as material removal rate (MRR) and overcut. Increase in electrolyte concentration considerably improves MRR but yields a poorer over cut. Increased machine voltage serves to increase both MRR and over cut significantly. Increased pulse on time and duty factor did not have notable impact on MRR and overcut. Less concentration of sodium chloride [NaCl] is sufficient for machining compared with sodium nitrate [NaNO3]. Higher MRR and better over cut are achieved with sodium chloride and moreover it is more economical than sodium nitrate.

The behavior of wire electrochemical discharge machining of Al2O3 particle-reinforced aluminum alloy 6061 was studied. The effects of machining voltage, current, pulse duration, and electrolyte concentration, on material removal rate (MRR) were evaluated in the light of the contribution of the electrical discharge machining (EDM) and electrochemical machining (ECM) actions. The relative strength of the EDM and ECM activities in the machining process under different conditions was studied with the aid of the voltage waveforms. It was found that the conditions of high current or high concentrations of electrolyte would promote the ECM activity and result in a high MRR. The relative importance of the various cutting parameters on MRR was established using orthogonal analysis. The results suggest that to achieve the highest MRR, the applied current is the most influential factor among current, pulse duration and electrolyte concentration. This outcome is supported by experimental results and is explained in terms of the surface area of the matrix phase and the spark gap size.

Electrochemical discharge machining (ECDM) is recognized as a successful method for processing non-conductive materials through thermal erosion and chemical dissolution. This article aims at the development of a finite element modeling (FEM) based three-dimensional (3D) thermal model for estimating the temperature distribution for scrutinizing the material removal rate (MRR) in electrochemical discharge drilling of silica glass material. The predicted FEM results are verified against existing literature and experimental results during micro-drilling operation. Simulations for evaluating the parametric studies such as the effect of applied voltage, electrolyte concentration, electrolyte type, energy partition on MRR is performed. Results revealed that the experimental values of MRR exhibit fare agreement with the predicted FEA results. Experiments are performed using adaptive tool feed based closed-loop ECDM machining that retracts the tool in an upward direction once its contact is detected with the work material. Tool contacts often result in a high tool wear rate (TWR). Moreover, the response surface methodology (RSM) based mathematical models are established to correlate the input variable’s relationship with the response parameters. Tool feed rate, applied voltage, and electrolyte concentration are chosen as numerical input variables while electrolyte type and tool material are chosen as categorical variables. MRR, TWR, and a number of tool contacts (NTC) are chosen as response parameters. A number of tool contacts are selected since it influences both MRR and TWR. The model’s adequacy is checked using the analysis of variance (ANOVA) and found significant for all the responses. The multi-response optimization of distinctive input variables is acquired by utilizing the desirability function (obtained 0.8646) for maximizing the MRR and minimizing the both TWR and NTC.

Surface finish and increased productivity (increased material removal rate (MRR)) are two premier performance parameters in machining and determination of optimal cutting parameters influencing the machining performance is paramount for different cutting conditions, cutting tools and workpiece materials. This study focuses on optimising a set of cutting parameters (cutting speed, feed rate and depth of cut) during dry turning operation of AISI H13 tool steel using a brazed uncoated tungsten carbide tip as the cutting tool material. Taguchi's L9 orthogonal array was employed for minimising surface roughness and maximising MRR based on signal-to-noise ratio results. Analysis of variance (ANOVA) conducted showed that the feed rate affected the performance responses (surface roughness and MRR) the most. Additionally, artificial neural network (ANN) and regression models were developed for both surface roughness and MRR, which showed promising prediction capability for calculating the surface roughness and MRR at any combination of cutting speed, feed and depth of cut.

Material wear of the tool electrode and metal workpiece in electrochemical discharge machining

Die sinking–electrochemical spark machining (DS–ECSM) is one of the hybrid machining processes, combining the features of electrochemical machining (ECM) and electro-discharge machining (EDM), used for machining of nonconducting materials. This article reports an intelligent approach for the modelling of DS–ECSM process using finite element method (FEM) and artificial neural network (ANN) in integrated manner. It primarily comprises development of two models. The first one is the development of a thermal finite element model to estimate the temperature distribution within the heat-affected zone (HAZ) of single spark on the workpiece during DS–ECSM. The estimated temperature field is further post-processed for determination of material removal rate (MRR) and average surface roughness (ASR). The second one is a back propagation neural network (BPNN)-based process model used in a simulation study to find optimal machining parameters. The BPNN model has been trained and tested using the data generated from the FEM simulations. The trained neural network system has been used in predicting MRR and ASR for different input conditions. The ANN model is found to accurately predict DS–ECSM process responses for chosen process conditions. This article also presents an effective approach for multiobjective optimization of DS–ECSM process using grey relational analysis.

Optimization of process parameters in Electro-chemical machining (ECM) of D3 die steels using Taguchi technique

The aim of this study is to develop an artificial neural network (ANN) model for spark assisted diamond face grinding (SADFG) of cobalt bonded tungsten carbide (WC-Co) composite to predict the material removal rate (MRR) and average surface roughness (Ra). The experiments were conducted on a self-developed face grinding setup, which is attached with EDM machine. A bronze metal bonded diamond wheel is used for experimentations. All the experiments were performed according to the central rotatable design. The current, pulse on-time, duty factor and wheel speed were taken as input process parameters and responses are measured in terms of MRR and Ra. Central rotatable design is used for experimentation. The obtained experimental data set was used to train the ANN model. The ANN architecture with back propagation algorithm has been used for modelling of process parameters of SADFG process. It has been found that the developed ANN model is capable to predict the MRR and Ra with absolute average percentage error of 10.40% and 6.81%, respectively. It has been also found that wheel speed at 1,300 RPM is suitable for achieving of the better surface finish while duty factor at 0.70 has been found more appropriate for higher MRR.

Manufacturing engineers are facing new challenges during machining of electrically nonconducting or partially conducting materials such as glass, quartz, ceramics, and composites. Traveling wire electrochemical spark machining (TW-ECSM), a largely unknown technology, has been applied successfully for cutting these types of materials. However, hardly any theoretical work has been reported related to machining performance of TW-ECSM process. The present work is an attempt in this direction. In the present work, a 3-D finite element transient thermal model has been developed to estimate the temperature field and material removal rate (MRR) due to Gaussian distributed input heat flux of a spark during TW-ECSM. First, the developed code calculates the temperature field in the workpiece and then MRR is calculated using this temperature field. The calculated MRR has been compared with the experimental MRR for verifying the approach. Computational experiments have been performed for the determination of energy partition and spark radius of a single spark. The effects of various process parameters such as energy partition, duty factor, spark radius, and ejection efficiency on MRR have been reported. It has been found that MRR increases with increase in energy partition, duty factor, and ejection efficiency but decreases with increase in spark radius.

Wear Properties of Cryogenic Treated Electrodes on Machining Of En-31

Hard materials cannot be machined effectively by the individual machining process. In order to machine workpiece made from hard and stiff materials effectively a concept of Hybrid machining process (HMP) is originated. The HMP is an integration of two or more machining process to get the advantage of each individual process. HMP is used to machine This study focuses on evolving a novel process using both oil and gas as dielectrics to analyse the effect on tool wear rate (TWR) and material removal rate (MRR). The flow of compressed gas through eccentric-hole rotating tool improved the debris removal from inter-electrode gap, hence it improve the flushing competence of the machining process. In this experimental investigation, the workpiece material is Al-20% SiC metal matrix composite (MMC) and the electrode material is copper. The experiments were conducted following the Taguchi method of design experiments. The effect of various machining parameters on MRR and TWR has been studied. The optimization of process parameter has also been done. The results of TWR and MRR are analysed using S/N ratio, ANOVA and main effect plots. The experimental results, revels that discharge current, gap voltage and pulse on time significantly affected MRR, and TWR. The experimental inference reveal that provision of compressed air through eccentric hole rotary tool has a positive effect on machinability of electrical discharge machining (EDM) process.

Machining of low machinable non conducting engineering materials like borosilicate glass has imposed challenges in the manufacturing of micro devices like microfluidics, MEMS etc. Electrochemical discharge machining (ECDM), a hybrid processes of electric discharge machining (EDM) and electro chemical machining (ECM), emerging as a potential method to address the low machinability problems. In the present work the influence of helical tungsten carbide tools of varying diameter assisted with high speed tool rotation was adopted to improve machining performance in terms of on the material removal rate (MRR), heat affected zone (HAZ), radial over cut (ROC), tool wear rate (TWR) and depth of machining (DOM). It was found that the hydrodynamic region was more predominant with tool diameters 600 μm, 700 μm and at 2,500 rpm and resulted to a low machining depth. Smaller diameter tools assisted with rotational was found significant influence on the machining responses.

Influence of workpiece materials on aerosol emission from die sinking electrical discharge machining process

The objective of this paper is to optimise the Material Removal Rate (MRR) of ultrasonic drilling on alumina based ceramics using silicon carbide abrasive. The parameters considered are workpiece material, tool material, grit size of the abrasive, power rating and slurry concentration. The optimal settings of the parameters are determined through experiments planned, conducted and analysed using the Taguchi method. The results obtained are validated by conducting the confirmation experiments.

Electro Discharge Drilling of Hybrid MMC