Neural-network-based model for build-time estimation in selective laser sintering

Cost assessment for rapid manufacturing (RM) is highly dependent on time estimation. Total build time dictates most indirect costs for a given part, such as labour, machine costs, and overheads. A number of parametric and empirical time estimators exist; however, they normally account for error rates between 20 and 35 per cent which are then translated to inaccurate final cost estimations. The estimator presented herein is based on the ability of artificial neural networks (ANNs) to learn and adapt to different cases, so that the developed model is capable of providing accurate estimates regardless of machine type or model. A simulation is performed with MATLAB to compare existing approaches for cost/time estimation for selective laser sintering (SLS). Error rates observed from the model range from 2 to 15 per cent, which shows the validity and robustness of the proposed method.