A 3D printing software company based in the US suggests that a data-driven approach to additive manufacturing (AM) is the way forward to revolutionize this new technology.

US company Senvol, based in New York City, has forged a place in the growing additive manufacturing (AM) industry by supplying a range of 3D printing software and machine data to the industry.

This includes the Senvol Database, a comprehensive database of AM machines and materials, which details more than 1000 AM machines and 2000 compatible materials. The database allows users to search 3D printing technology by over 30 fields, such as machine build size, material type, and material tensile strength, and can be found via the company’s website.

Related products are the Senvol API, which makes it possible to incorporate the data and structure of the Senvol Database into a company’s software, while the Senvol SOP is a standard operating procedure (SOP) that details how to generate pedigreed (ie, with a background genealogy) AM data.

Data analysis

The company has also developed machining learning (ML) software, Senvol ML, that helps companies characterize or qualify AM materials and processes and develop better substantiated material properties – thus reducing the need for conventional material characterization and testing. It is based on a modularized integrated computational materials engineering (ICME) probabilistic framework for AM data, in which the data is categorized into four modules: process parameters, process signatures, material properties, and mechanical performance. The software being developed is powered by an algorithm that quantifies the relationships between the four modules.

Senvol says that the software also allows users to select the appropriate process parameters on a particular AM machine, given a target mechanical performance. It can predict a factor, such as fatigue life, from a given set of process parameters, and when given a target mechanical performance, such as a target tensile strength, the algorithm determines what process parameters to use to achieve it. The algorithm ‘learns’ from previous data sets and applies those ‘learnings’ to new data sets, thereby reducing the amount of data needed in the future and improving prediction accuracy. The algorithm next recommends to the user what additional data points are needed to improve prediction accuracy.

Senvol ML also reportedly includes computer vision algorithms that analyze in real-time in-situ monitoring data, such as high-resolution photos, photo-diode data and videos of the melt pool. This enables a user to detect irregularities in real-time and begin to quantify the relationships between irregularities in the build and the resulting mechanical performance.

Log in to your free materialstoday.com profile to access the article.

Already a Materials Today member?

Log in to your Materials Today account to access this feature.