About this Abstract |
Meeting |
MS&T22: Materials Science & Technology
|
Symposium
|
Additive Manufacturing: Equipment, Instrumentation and In-Situ Process Monitoring
|
Presentation Title |
In-situ Sensor Feature Engineering for Process Development of Energy Conversion Materials |
Author(s) |
Joy Gockel, John Middendorf, Joe Walker, Vijayabarathi Ponnambalam, Saniya LeBlanc, Tanvi Banerjee |
On-Site Speaker (Planned) |
Joy Gockel |
Abstract Scope |
In-situ sensing provides the ability to monitor the additive manufacturing (AM) processes as the material is being fabricated. Process parameter development can be accelerated through the combined use of in-situ sensors, material characterization and machine learning. However, a critical challenge in the application of machine learning is the featurization of in-situ sensor signals that are related to the properties of interest. This work focuses on an analysis of in-situ sensor data during the fabrication of bismuth telluride samples using laser powder bed fusion. Samples are selected that represent the extremes of the characterized material properties of interest including porosity, Seebeck coefficient and electrical resistivity. In-situ sensor data from thermal tomography, a high-speed spatter camera and long wavelength infrared imaging are analyzed. The definition of sensor features that are physically and correlatively related to the properties of interest will enable future AM process optimization of energy conversion materials. |