Hamjah, M. K., Thielen, N., Hagelloch, J. E., Franke, J.
2021 IEEE Region 10 Symposium (TENSYMP), Jeju, Korea, Republic of, 2021, pp. 1-5
In this work, a Machine Learning approach to predict the quality of the aerosol jet printed polymer optical waveguides material is presented. For the acquisition of necessary data, a video camera system was integrated into the aerosol jet printing. An image processing tool was developed to extract printed line width and to map to the process data of the printing. For modeling, an Automated Machine Learning framework was utilized to reduce development time for a proof of concept. The final ML model reached R 2 score of 74 % in predicting line width and surpassed the statistical approaches.
Hamjah, M. K., Thielen, N., Hagelloch, J. E., Franke, J.
2021 IEEE Region 10 Symposium (TENSYMP), Jeju, Korea, Republic of, 2021, pp. 1-5
In this work, a Machine Learning approach to predict the quality of the aerosol jet printed polymer optical waveguides material is presented. For the acquisition of necessary data, a video camera system was integrated into the aerosol jet printing. An image processing tool was developed to extract printed line width and to map to the process data of the printing. For modeling, an Automated Machine Learning framework was utilized to reduce development time for a proof of concept. The final ML model reached R 2 score of 74 % in predicting line width and surpassed the statistical approaches.