Improving Ceramic Additive Manufacturing via Machine Learning-Enabled Closed-Loop Control Public
Downloadable Contentopen in viewer
Advanced ceramics are widely used in aerospace, automotive, electronic, laboratory equipment, and other industries. To achieve the geometric complexity and desirable properties that are difficult to obtain by conventional manufacturing methods, ceramic additive manufacturing (AM) methods have been studied intensively in recent years. However, in-process control with feedback is not currently implemented in any commercially available ceramic three-dimensional (3D) printer. Robocasting is one of the most widely utilized AM processes for various ceramic materials at a low cost. This study employed robocasting as an example of implementing an in-process control with a feedback loop in a ceramic AM process. In this research, the material parameters, process parameters, machine parameters, and their influences on quality parameters were investigated. The key parameters of the ceramic robocasting process were identified. The relationships among the functional requirements, design parameters, and process variables in the robocasting process were analyzed using Axiomatic Design (AD) theory. A database of the relationships among pressure, extrusion, and the quality of the printed green part was established. An artificial neural network (ANN) model was created based on the established database. Machine learning-enabled closed-loop control was integrated into the current robocasting process to improve the quality of the printed green parts. Finally, the improvement was validated by comparing the quality of the prints in both controlled operations and uncontrolled operations.
- Defense date
- Date created
- Resource type
- Rights statement
Permanent link to this page: https://digital.wpi.edu/show/6395w984d