Artificial neural network modelling of erosion-abrasion-based hybrid machining of aluminium-silicon carbide-boron carbide composite. (2017)

• Record Type: Journal Article
• Authors: Yadav, Ravindra Nath; Yadava, Vinod
• Is Part Of: International journal of engineering systems modelling and simulation. Volume 9:Number 2(2017)
• Page Start: 63
• Page End: 77
• Publication Date: 2017
• Subjects: artificial neural networks -- ANNs -- electro-discharge diamond grinding -- EDDG -- erosion-abrasion hybrid machining -- EAHM -- metal matrix composites -- MMCs -- modelling -- electro-discharge machining -- EDM -- aluminium -- silicon carbide -- boron carbide -- electrical discharge machining -- pulse current -- pulse on-time -- pulse off-time -- grinding wheel RPM -- abrasive grit number -- the material removal rate -- MRR -- surface quality -- surface roughness; Engineering systems -- Computer simulation -- Periodicals; Engineering systems -- Mathematical models -- Periodicals; 620.0042
• Languages: English
• ISSNs: 1755-9758

Abstract

The erosion-abrasion-based hybrid machining (EAHM) is newly developed machining process, which comprises the erosion-based machining such as electro-discharge grinding (EDG) and abrasion-based machining such as diamond grinding (DG) for machining of difficult to machine hard and brittle materials. The aim of this study is to develop an artificial neural network (ANN) model for EAHM process during machining of aluminium-silicon carbide-boron carbide (Al%SiC%B4C) composite workpiece. The ANN model has been trained and tested with experimental observations, which are collected after experimentations. The experiments were conducted on EDM machine considering the effect of pulse current, pulse on-time, pulse off-time, wheel RPM and abrasive grit number on the material removal rate and average surface roughness. It has been found that the developed ANN model was significantly predicted the responses within the acceptable limit. Such developed model is further used to study the effect of process parameters on the performance measures.