The foundry processes. From Art to Science

The manufacture of cast components is a complex process that involves a large number of variables. Additionally, to obtain a component that meets the specified requirements, it is necessary to avoid the formation of defects that may render its commissioning unusable. Defects may invalidate the functionality of the component.

Generally, in the foundry world, the rejection of castings is measured in percentage. This carries the risk that an unsuitable component may be sent to the final customer. Unfortunately, due to the fact that, currently, the scrap is measured in percentage, it is needed to see the problem in a different way and, with the aim to produce perfect components generated tools such as Smart Manufacturing, Digital twins, permanent auditors’ techniques, among others.

This work shows how it is possible to reduce the internal and external scrap rate dramatically by applying Artificial Intelligence techniques, also combining the expert knowledge, data collection, prediction tools, and being managed by a digital twin. All this ecosystem will identify on the production line molds that do not fulfill the requirements, avoiding deviations and, finally, reducing drastically customer complaints.