How can we ensure reliable, repeatable AM processes? With the Alchemite deep learning software, you can get more from your data. Understand critical property/process relationships and get guidance on which changes in your processing setup will give you the best results.
Challenge: Additive Manufacturing (AM) is a new processing technology used in a wide range of industries to produce and repair bespoke and high-value parts including aerospace engine components, turbine blades, and oil drilling tools. But the process to ‘print’ materials is often poorly understood and subject to significant variation based on the exact processing parameters and conditions. In our example, limited data was available on a direct laser deposition method, consisting of only ten sets of processing variables. This dataset was not enough for traditional machine learning techniques to be able to predict the properties of a wider family of processing variables.
Solution: We optimized the direct laser deposition process for AM using historical welding data and the available sparse direct laser deposition dataset. Alchemite was able to leverage abundant weldability data to automatically identify and exploit relevant property-property relationships enabling new insights into the impact of processing variables.
Outcome: We were able to optimize this AM process and broaden its application, potentially saving years of research.
Alchemite for additive manufacturing
With the Alchemite software scientists and engineers can apply powerful deep learning methods to get more from their AM project data – even when that data is sparse and noisy. You could use Alchemite to:
- Validate and clean AM project data
- Quickly generate models that provide insight into key property-process relationships
- Identify which test or experiment it would be most productive to do next
- Optimize process parameters
- Run virtual experiments on candidate materials and processes