A novel ensemble method based on SBLMD-ANN-MOPSO approach for predicting the milling stability regimes

In recent decades, lots of work has been done to mitigate self excited vibration effects in milling operations. Still, a robust methodology is yet to be developed that can suggest stability bounds pertaining to higher metal removal rate (MRR). In the present work, experimentally acquired acoustic signals in milling operation have been computed using a modified Local Mean Decomposition (SBLMD) technique in order to cite tool chatter features. Further, three artificial neural network (ANN) training algorithms viz. Resilient Propagation (RP), Conjugate Gradient-Based (CGP) and Levenberg-Marquardt Algorithm (LM) and two activation functions viz. Hyperbolic Tangent Sigmoid (TANSIG) and Log Sigmoid (LOGSIG) has been used to train the acquired chatter vibration and metal removal rate data set. Over-fitting or under-fitting issues may arise from the random selection of a number of hidden neurons. The solution to these problems is also proposed in this paper. Among these training algorithms and activation functions, a suitable one has been selected and further invoked to develop prediction models of chatter severity and metal removal rate. Finally, Multi-Objective Particle Swarm Optimization (MOPSO) has been invoked to optimize developed prediction models for obtaining the most favourable range of input parameters pertaining to stable milling with higher productivity.

An Experimental Investigation on Micro Drilling of Cold Work Steel X153CrMoV12 By EDM

In this study, it was aimed to analyze the effects of machining parameters on the process quality by drilling holes in heat treated cold work tool steel with a hardness of 60-62 HRC using the electrical discharge machining (EDM) method and Ø2 mm diameter brass electrodes. In this context, drilling was performed using three different current values ​​(5, 6, 7 A), three different voltage values ​​(1, 2, 3 V), three different discharge pulse frequency Ton (23, 26, 29 µs) as well as Toff (3, 5 µs) respectively, and the effects of these machining parameters on the machining time, material removal rate (MRR), electrode wear rate (EWR), surface roughness (SR) and hardness of around the white layer were analyzed using micro, macro and analytical measurements, especially with Scanning Electron Microscopy (SEM) and Energy Dispersive X-Ray Analysis (EDX). As a result of the analysis, ıt was observed that current, voltage, Ton and Toff had an effect on machining time, MRR, EWR, SR and hardness, but current was the most effective parameter, and also worn electrode as well as workpiece residues affected the process quality. Increasing the machining current increased sparking between the workpiece and the electrode, resulting in increased point melting and evaporation, resulting in increased average surface roughness, metal removal rate, and electrode wear rate. As a result of the high metal removal rate, the machining time was greatly reduced and the thermal effect time was reduced, which led to a decrease in the hardness variation on the machined surfaces.

Investigation the Effect of Negative Polarity of Surface Roughness and Metal Removal Rate During EDM Process

The Electro discharge machine that named (EDM) is used to remove the metal from the workpiece by spark erosion. The work of this machining depends on the multiple variables. One of the most influential variants of this machine is the polarity, the material of the electrode, the current and the time pulses. Essentially the polarity of the tool (electrode) positive and the work piece is negative, this polarity can be reversed in this paper was reversed the polarity that was made the tool (electrode) negative and the work piece was positive. The aim of this paper was focused on the influence of reversed the polarity (negative) with changing the electrode metal (copper and graphite) on the surface roughness and metal removal rate by using different parameters (current and pulses of time). Experiments show that: the copper electrode gives (best surface roughness 0.46 µm when the current 5 Am and Ton 5.5 µs) and (worst surface roughness 1.66 µm when the current is 8 A and Ton 25 µs). And give (best values of the MRR 0.00291 g/min when the current is 8 and Ton 25 µs) and (The lowest values of MRR (0.00054 g/min when current is 5 and Ton 5.5 µs). The graphite electrode gives (best surface roughness 2.07 µm when the current 5 Am and Ton 5.5 µs) and (worst surface roughness 4.17 µm when the current is 8 A and Ton 25 µs). And give (best values of the MRR 0.05823 g/min when the current is...

Ensembled local mean decomposition and genetic algorithm approach to investigate tool chatter features at higher metal removal rate

Improper selection of cutting parameters leads to regenerative chatter and loss in productivity. In the present work, a methodology has been proposed to select a proper combination of input cutting parameters for stable turning with improved metal removal rate. Chatter signals generated during the turning of Al6061-T6 have been acquired using a microphone. Stability lobes diagram has been plotted to access the stability regime. Further, to study the effect of feed rate on stability, the recorded signals have been processed using local mean decomposition signal processing technique, followed by the selection of dominating product functions using Fourier transform. The decomposed signals have been used to evaluate the new output parameter, that is, chatter index. Prediction models of chatter index and metal removal rate have been developed. Moreover, these prediction models have been optimized using multi-objective genetic algorithm for ascertaining the optimal range of cutting parameters for stable turning with higher metal removal rate. Finally, obtained stable range has been validated by performing more experiments.

Investigation the Electrode Wear Rate and Metal Removal Rate in EDM Process using Taguchi and ANOVA Method

The experimental work of this paper leads to electrical discharge machining (EDM). A system for machining in this process has been developed. Many parameters are studied such as current, pulse on-time, pulse off time of the machine. The main aim of this work is to calculate the metal removal rate (MRR) and electrode wear rate (EWR) using copper, electrodes when machining tool steel H13 specimens of a thickness (4mm). Different current rates are used ranging from (30, 42, and 54) Amp, pulse on-time ranging from (75, 100, and 125) and pulse off time ranging from (25, 50, and 75) found that high current gives large electrode wear and metal removal rate and. The experiment design was by Taguchi Method. From an analysis of variance (ANOVA) the more active influence of input factors on the outputs is currently for metal removal rate (MRR) (58%) and electrode wear rate (EWR) (57).

Experimental Investigation of Drilling Small Hole on Duplex Stainless Steel (SS2205) Using EDM

This work investigates drilling of small holes of Ø 3 mm on duplex Stainless Steel. Its machinability index is very low (0.66) as compared to other steels, hence Electrical Discharge Machine is used. The input parameters are Current, Spark Gap & Di electric Pressure. Each input parameter is considered for 3 levels. Therefore total number of experiments is 3×3×3 – 27. To reduce the number of runs, Taguchi L9 orthogonal array is used, which is having advantage of maximum and minimum trial runs in its design. The output response is metal removal rate. To find the best operating parameter, the regression model of ANOVA is given to input of MAT Lab-Genetic Algorithm. The experimental results indicated that models are significant. The test result indicated that the contributions of current is 42.42%, Di electric pressure is 35.36% and Spark gap is 1.93% on metal removal rate. From Genetic Algorithm it is observed among three levels of factors, lower value of current and Di electric pressure produced maximum metal removal rate. The SS 2205 has wide variety of applications such as high pressure components, control valves etc., which are having large number of components to it. Hence performing micro holes on such high hardness alloy is useful.

Influence of Polarity of Electro Discharge Machine (EDM) on Surface Roughness (SR) and Metal Removal Rate (MRR) of Low Carbon Steel

Electro discharge machining (EDM) is one of a thermal process that is used for remove of metal from the workpiece by spark erosion. The work of this machine depends on multiple variables. One of the more influential variants on this machine is the change of polarity and the use of this variable is not wide and the research depends on the polarity of the machinist. Essentially, the polarity of the tool (electrode) is positive and the workpiece is negative, this polarity can be reversed. This paper focuses on the influence of changing the polarity (positive and negative) on the surface roughness and metal removal rate by using different parameters (current, voltages, polarity and Ton). Experiments show that the positive electrode gives (best surface roughness = 1.56 µm when the current = 5 Am and Ton = 5.5 µs) and (best metal removal rate = 0.0180 g/min when the current = 8 Am and Ton = 25 µs). Negative electrode gives (best surface roughness = 0.46 µm when the current = 5 Am and Ton = 5.5 µs) and (best metal removal rate = 0.00291 g/min when the current = 8 Am and Ton = 25 µs).

Memetic Cuckoo-Search-Based Optimization in Machining Galvanized Iron

In this article, an improved variant of the cuckoo search (CS) algorithm named Coevolutionary Host-Parasite (CHP) is used for maximizing the metal removal rate in a turning process. The spindle speed, feed rate and depth of cut are considered as the independent parameters that describe the metal removal rate during the turning operation. A data-driven second-order polynomial regression approach is used for this purpose. The training dataset is designed using an L16 orthogonal array. The CHP algorithm is effective in quickly locating the global optima. Furthermore, CHP is seen to be sufficiently robust in the sense that it is able to identify the optima on independent reruns. The CHP predicted optimal solution presents ±10% deviations in the optimal process parameters, which shows the robustness of the optimal solution.