High-Resolution Additive Manufacturing Error Prediction and Compensation Through 3D CNN Leveraging Semantic Segmentation

Abstract

Additive manufacturing (AM) is a relatively new domain of manufacturing processes that began with its first patent in 1986. Since then, AM processes quickly grew in popularity due to their flexibility, superior efficiency in high mix low volume manufacturing settings, and lower material costs compared to more subtractive processes. Despite its increasing popularity, AM processes remain behind subtractive processes in terms of quality and the speed at which new technologies are integrated. Introducing Industry 4.0 technologies is an excellent opportunity to address the need for quality assurance tools for AM processes. First, the question of how the quality of additively manufactured parts can be increased to match parts created through subtractive processes must be asked. In this dissertation, two machine learning (ML) models are developed and utilized in a federated environment to mimic what one would see in a production setting. The proposed models increase AM part quality by (1) predicting the resulting geometry of an AM process and (2) compensating for geometric errors by altering the initial stereolithography (STL) file before slicing. In addition to performing geometric error prediction and compensation, the models were enhanced to be resilient to changes in geometry by training on segments of a 3D object rather than the whole object. Next, process parameters from fused-filament fabrication (FFF) processes were added to the ML models to add resilience process parameter variance. Lastly, the ML models were deployed in a federated environment created from three FFF 3D printers that collaboratively created a dataset for the ML models. Collectively, these works expand the research area created by AM, federated learning, and error compensation. This proposal addresses research gaps in the current literature by first setting the prediction and compensation resolution of voxel-based ML methods to a static 100 µm, thereby reducing the error associated with each voxel. Secondly, process parameters are introduced to the model, further increasing prediction and compensation accuracy compared to predicting on the geometry alone. Lastly, the models are deployed in a federated AM environment with multiple 3D printers acting as clients to reduce each client's time spent generating data while maintaining model performance.