Additive manufacturing learns about superalloys

May 18, 2019 // By Christoph Hammerschmidt
Additive manufacturing learns about superalloys
Scientists at the Fraunhofer Institute for Material and Beam Technology IWS in Dresden have developed methods that make it possible to use more materials in additive manufacturing than ever before. Their achievements could enable additive manufacturing systems to produce, for example, better aircraft engines in the future that consume less fuel.

To achieve their goal of faster, more versatile additive manufacturing with new superalloys, engineers must first improve the current industrial 3D printers so that these machines can also process very strong and extremely heat-resistant alloys. The researchers are drawing on their experience with laser powder deposition welding and using artificial intelligence (AI). They contribute their materials expertise to the Fraunhofer "futureAM" joint project. The aim of the partners is to make additive production systems for metal components 10 times faster and also to cope with superalloys.

In order to be able to use more materials in additive manufacturing, the engineers at the Fraunhofer IWS have refined laser powder deposition welding over many years. In this process, a system transports various filler powders into a process zone. There, a laser melts the powder and welds it onto a workpiece surface. This produces the desired shape layer by layer. One of the advantages of this process is that the process can be very flexibly adapted to the requirements of high-performance materials. This makes it possible, for example, to print nickel-based alloys that are difficult to weld and process using traditional methods. However, this only works if the temperature, powder types, delivery rate and other settings are correct. As part of the Fraunhofer lead project "futureAM - Next Generation Additive Manufacturing", Fraunhofer IWS engineers are recording numerous sensor data with very high sampling rates for this purpose.

However, this generates very large amounts of data that are difficult for people to understand. In order to nevertheless find hidden connections in these signal floods, the experts use methods of artificial intelligence (AI) and machine learning, which is also being researched at the Fraunhofer IWS. Over time, the machines learn to make decisions independently. For example, they can see for themselves whether a slight rise in temperature in the welding process can be tolerated or whether they have to take immediate countermeasures.

Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.