الفهرس | Only 14 pages are availabe for public view |
Abstract In the present study, stir casting method (SCM) was used to produce metal matrix composites (MMC). Aluminum (Al) 6061 and silicon carbide particles (F500≈15µm) were selected as matrix and reinforcement materials respectively. Matrix (Al6061), Al-5%SiC and Al-10%SiC were subjected to Electric discharge machining (EDM) to analyses the effect of input parameters namely peak current (Ip), pulse-on-time (Ton), duty cycle (DT) and gap (g). Optical microscope was used to determine the SiC particles distribution in the Al matrix of the composites (as-cast). The digital balance was used to determine the material removal rate (MRR) and Tool wear rate (TWR) for the matrix and composites. The maximum values of MRR obtained, were 0.355 g/min, 0.324 g/min and 0.344 g/min in case of matrix (Al 6061), Al-5%SiC and Al-10%SiC respectively. The minimum values of TWR obtained, were 0.414%, 0% and 0.386% in case of matrix (Al 6061), Al-5%SiC and Al-10%SiC respectively. Surface roughness measurement tester (TR200) used to determine the surface roughness (Ra) for the matrix and composites. The minimum values of Ra obtained, were 1.552µm, 1.963µm and 3.354µm in case of matrix (Al6061), Al-5%SiC and Al-10%SiC respectively. An artificial neural network (ANN) model was developed for EDM process during machining of Al6061 and aluminum-silicon carbide (Al%SiC) composite workpiece. The ANN model has been trained and tested with experimental observations, which are collected after experimentations. It was trained to predict the machine input parameters needed to obtain the required metal removal rate, surface roughness and tool wear. It has been found that the developed ANN model had achieved significant results with mean squared error around 8%. |