Machining
Amith H Gadagi; Chandrashekar Adake
Abstract
In a turning process, it is essential to predict and choose appropriate process parameters to get a component’s proper surface roughness (Ra). In this paper, the prediction of Ra through the artificial neural network (ANN), multiple regression analysis (MRA), and random forest method (machine learning) ...
Read More
In a turning process, it is essential to predict and choose appropriate process parameters to get a component’s proper surface roughness (Ra). In this paper, the prediction of Ra through the artificial neural network (ANN), multiple regression analysis (MRA), and random forest method (machine learning) are made and compared. Using the process variables such as feed rate, spindle speed, and depth of cut, the turning process of glass fiber-reinforced plastic (GFRP) composite specimens is conducted on a conventional lathe with the help of a single-point HSS turning tool brazed with a carbide tip. The surface roughness of turned GFRP components is measured experimentally using the Talysurf method. By utilizing Taguchi's L27 array, the experiments are carried out and the experimental results are utilized in the development of MRA, ANN, and random forest method models for predicting the Ra. It is observed that the mean absolute error (MAE) of MRA, ANN and random forest for the training cases are found to be 39.33%, 0.56%, and 24.88%, respectively whereas for the test cases MAE is 54.34%, 2.59%, and 24.88% for MRA, ANN, and random forest, respectively.
Machining
Jayasimha SLN; Ganapathy Bawge; Raju H.P.
Abstract
Traditional methods of finishing like grinding, lapping, and honing are limited to finishing of vital shapes such as flat and circular. These conventional methods are lagging for processing components that are fabricated by hard materials, involving complicated profiles in particular. Hence, it is essential ...
Read More
Traditional methods of finishing like grinding, lapping, and honing are limited to finishing of vital shapes such as flat and circular. These conventional methods are lagging for processing components that are fabricated by hard materials, involving complicated profiles in particular. Hence, it is essential to explore a finishing process, which addresses wide applications, better accuracy, higher efficiency, consistent quality and economy in finishing complex shaped parts. So, a new precision finishing process like extrusion honing has been implemented for polishing from several microns to the nano level. This work aims to assess the influence of a number of abrasive media passes on the surface integrity of aluminum, copper, and titanium grade-2 materials. The study has been performed by adopting an abrasive 36 mesh size with a concentration of 40% followed by 10 abrasive media passes. The influence of these process parameters has been studied in analyzing the roughness characteristics Ra, Rmax, Rz, and Rmax/Ra and the nature of surface induced by SEM characterization for the metals of consideration using the extrusion honing process.
Machining
Pawan Kumar; Meenu Gupta; Vineet Kunar
Abstract
The present research attempts to analyze the surface topography of WEDMed Inconel 825 concerning surface crack density (SCDi) and recast layer thickness (RCLt). Formation of cracks, recast layer, and heat-affected zone are the major issues in determining the final performance of the WEDM machined sample. ...
Read More
The present research attempts to analyze the surface topography of WEDMed Inconel 825 concerning surface crack density (SCDi) and recast layer thickness (RCLt). Formation of cracks, recast layer, and heat-affected zone are the major issues in determining the final performance of the WEDM machined sample. In this study, WEDM characteristics viz. pulse on time (Ton), pulse off time (Toff), gap voltage (SV), peak current (IP), wire tension (WT), and wire feed (WF) are optimized for the response SCDi and RCLt by response surface methodology. The outcome manifests that the topography of the machined surface becomes more rougher at the increased value of Ton, IP, and SV. RSM emerges as a great tool in the development of a predicted model based on the desirability approach and finding optimal parametric combinationm which results in reduced SCDi and RCLt. At the optimum combination of process parameters, i.e., 109 machine unit Ton, 36 machine unit Toff, 54 V SV, 120A IP, 9 machine unit WT and 7 m/min WF, the values obtained for SCDi and RCLt are 0.00160 μm/μm2 and 20.991μm, respectively with an error of less than 5%.
