Study on shrinkage behaviour of laser sintered PA 3200GF specimens using RSM and ANN

Purpose - The purpose of this paper is to provide a better understanding of process parameters that have a significant effect on the shrinkage behaviour of laser-sintered PA 3200GF specimens. Design/methodology/approach - A five-factor, three-level and face-centred central composite design was used to collect data, and two methods, namely, response surface methodology (RSM) and artificial neural network (ANN) were used for predicting shrinkage. Sensitivity analysis based on the developed empirical equations has been carried out to determine the most significant parameter, which contributes the most to control shrinkage. In addition, a comparative analysis has also been performed for the results obtained by RSM and ANN. Findings - The results revealed that part bed temperature, scan speed and scan spacing are the three dominant parameters, which have a great influence on shrinkage. Strong interactions between laser power-scan spacing, laser power-scan length and scan speed-scan spacing have been observed. Through sensitive analysis, it is observed that shrinkage is more sensitive to the scan speed variations than other four process parameters. Practical implications - This study can be used as a guide, and the demonstrated results will provide a good technical database to the different additive manufacturing users of various industries such as automobile, aerospace and medical. Originality/value - To the best of the authors' knowledge, this is the first study to report the shrinkage behaviour of laser-sintered PA 3200GF parts fabricated under different sintering conditions.