ProgramMaster Logo
Conference Tools for MS&T21: Materials Science & Technology
Login
Register as a New User
Help
Submit An Abstract
Propose A Symposium
Presenter/Author Tools
Organizer/Editor Tools
About this Abstract
Meeting MS&T21: Materials Science & Technology
Symposium Additive Manufacturing of Metals: Equipment, Instrumentation and In-Situ Process Monitoring
Presentation Title Physics Guided Machine Learning DED Melt Pool Width Prediction
Author(s) Brett Diehl, Clara Mock, Lester Hitch, Brandon McWilliams, Berend Rinderspracher
On-Site Speaker (Planned) Brett Diehl
Abstract Scope Directed energy deposition (DED) is of interest to the aerospace and defense industries for the production of novel and complex geometries, as well as repair applications. However, variability during the build process can result in deviations in final component geometry, structure, and mechanical properties which adds to the complexity of process planning and slows down adoption of this technology. Neural nets were trained to predict melt pool width, given input drivers such as build height, laser power, laser speed, and thin wall length. Physical constraints on the relationships between the 1st and 2nd derivatives of input drivers and melt pool width were enforced using custom loss functions, yielding physics-guided neural networks (PGNNs). PGNNs predicted the melt pool width with a higher performance (R-square = 0.991) than traditional neural networks (R-square = 0.884). Physics-based loss functions performed superior to traditional methods of regularization and were a superior method of training on unbalanced datasets versus sample/class weighting. This work demonstrates the benefits of enforcing physical constraints on machine learning predictions of additive manufacturing processes using finite estimates of mathematical expressions of physical laws.
Proceedings Inclusion? Undecided

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

Advancing Measurement Science of Laser Powder Bed Fusion (LPBF) Process Monitoring Applying Thermal Imaging
Combined In-situ Monitoring of Meltpool, Powder Layer, and Part Topography for Laser Powder Bed Fusion (LPBF) Based Metal Additive Manufacturing
Defect Recognition and Improvement in Ti-6Al-4V Fabrication by In-situ Monitoring and Feedback System of Directed Energy Deposition LAMDA 200
Functionally Graded Material Development by Leveraging Ultrasonic Grain Refinement in Additive Manufactured Nickel 718
High-speed Observations and Quantification of Spatter in Laser Powder Bed Fusion
In-situ Sensing in Processing Parameter Development for Bismuth Telluride Bulk Part Fabrication Using Laser Powder Bed Fusion
Innovative and Practical Approaches to Laser Powder Bed Fusion Sensing and Process Enhancement
Laser Powder Bed Fusion of Tall Thin Walled Structures: Dimensional Inaccuracy Due to Local Buckling, and In Situ Infrared Imaging for Early Failure Detection
Materials Characterization of Anomalies Identified Through In-situ Process Monitoring Data Analytics
Melt Pool Level Flaw Detection in Laser Hot Wire Additive Manufacturing Using a Trained Convolutional Long Short Term Memory Autoencoder
Physics Guided Machine Learning DED Melt Pool Width Prediction
Plenoptic Imaging for In-situ PIV and Melt Pool Monitoring in Laser Directed Energy Deposition
Studying the Effect of Inert Gases on Thermal Behavior in Laser Powder Bed Fusion Using In Situ Monitoring and Similarity Analysis
Ultrasonics for Monitoring Melt Pool Dynamics and Solidification

Questions about ProgramMaster? Contact programming@programmaster.org