A neural network-based build time estimator for layer manufactured objects

A correct prediction of build time is essential to calculate the accurate cost of a layer manufactured object. The methods presented in literature are of two types: detailed-analysis- and parametric-based approaches. The former require that a lot of data, related to the kinematic and dynamic performance of the machine, should be known. Parametric models, on the other hand, are of general use and relatively simple to implement; however, the parametric methods presented in literature only provide a few of the components of the total build time. Therefore, their performances are not properly suited in any case. In order to overcome these limitations, this paper proposes a parametric approach which uses a more complete set of build-time driving factors. Furthermore, considering the complexity of the parametric build time function, an artificial neural network is used so as to improve the method flexibility. The analysis of the test cases shows that the proposed approach provides a quite accurate estimation of build time even in critical cases and when supports are required.