2023-07-17 18:58:07
In a US defense program, Senvol has shown that Machine Learning algorithms can be used very well for the rapid development of material properties for AM. The study involved 17-4 PH stainless steel (304 L) for a powdered bed fusion AM system. Senvol warns that further research is needed.
Developing parameters for the right material properties is time consuming and costly in the AM industry. The high costs stem in large part from the fact that this requires the generation of a huge amount of empirical data with a fixed process. That raises a barrier.
Both time-saving and cost-reducing
Lots of empirically collected data
This means that all empirical data has to be generated once more every time there is a major change in the process. This results in an AM process that is not only costly and time-consuming to implement the first time, but also to maintain over the long term when changes in the AM process inevitably occur. Senvol wants to accelerate this and make it cheaper by a completely different approach, namely by using Machine Learning algorithms.
Develop faster
The Senvol ML software supports the qualification of AM processes and was used in the program to develop statistically sound material properties. This software can be applied to any AM process. Importantly, this project has not developed any real allowable values. Due to budgetary and programmatic constraints, the project team had to make a number of simplifying decisions. But according to those involved, the effectiveness of this approach has been proven. The potential of this approach is great.
Positive effect on costs and planning
Met Senvol ML you immediately receive a number of suggestions and can therefore suffice with much less empirically determined data and work towards the final goal more quickly. Senvol has previously achieved a similar result in the development of properties for a polymer. Now for stainless steel. According to William E. Frazier, retired Chief Scientist for Air Vehicle Engineer at NAVAIR / The Navy Senior Scientist for Material Engineering, and currently President of Pilgrim Consulting LLC, further development of the Senvol ML software can positively impact cost, schedule and performance of additive manufacturing for both commercial and defense purposes.
Senvol’s partners in the program were EWI and Pilgrim Consulting. Battelle and Lockheed Martin Fellow Hector Sandoval also served as technical advisors to the program. The contract was administered by the National Center for Manufacturing Sciences (NCMS) through the AMMP Other Transaction Agreement (OTA) program.
Photo: the test pieces printed in the AMMP program in which Senvol participated.
1689652384
#Senvol #shows #added #material #development #Machine #Learning
