Electric-field-assisted direct ink writing (eDIW) process modeling

Abstract

Direct ink writing (DIW) is an extrusion-based additive manufacturing technology. Recently, researchers found that by introducing an electric field into the system, the ink extrusion can be manipulated with a larger flexibility, and hence enhancing the printing success rate, resolution, and enabling higher printing speeds for targeted trace widths, offering advantages over the conventional DIW method including higher printing speed, higher resolution, and a wider range of ink choices. Yet due to the introduction of the additional electric field, the eDIW process becomes more complicated and therefore more challenging to control. This paper introduces a modeling system designed to enhance the eDIW process control over its printing quality and accuracy. In this modeling system, automated image processing techniques are employed to gather training data and machine learning algorithms are explored to predict the printing width. After training, the system takes process parameter settings as direct input and provides result prediction maps as the output. The prediction effectiveness is compared and discussed. Test cases are conducted to evaluate the performance of the proposed methods. This machine-learning-based modeling system shows significant promise and potential in eDIW process planning.