Enhancement of Surface Quality of DMLS Aluminium Alloy using RSM Optimization and ANN Modelling

Abstract

Direct Metal Laser Sintering (DMLS) is an additive manufacturing technology gaining popularity due to its ability to produce near net-shaped functional components. As there is a great need to improve the surface quality of DMLS components to upgrade their dynamic properties, an attempt was made to study the influence of process parameters like laser power, scan speed, and overlap rate on the surface quality of DMLS Aluminum alloy (AlSi10Mg) in as-built condition. The optimized process window to generate the best surface quality was achieved using Response Surface Method (RSM). Artificial Neural Network (ANN) modeling is also developed to map the influence of process parameters on surface quality. Conclusively, Scan speed is found to be most influential over surface quality as per the F and P test results. The optimized process parameters for best surface quality (3.52 μm) were 300 W laser power, 600 mm/sec scan speed, and 25% overlap rate. Both RSM and ANN models were accurate in prediction. However, ANN is recorded as superior with the highest coefficient of correlation (R)