Available at: https://digitalcommons.calpoly.edu/theses/2817
Date of Award
6-2024
Degree Name
MS in Industrial Engineering
Department/Program
Industrial and Manufacturing Engineering
College
College of Engineering
Advisor
Xuan Wang
Advisor Department
Industrial and Manufacturing Engineering
Advisor College
College of Engineering
Abstract
Inkjet additive manufacturing is the next step toward ubiquitous manufacturing by enabling multi-material printing that can exhibit various mechanical, electronic, and thermal properties. These characteristics are realized in the careful formulation of the inks and their functional materials, but there are many constraints that need to be satisfied to allow optimal jetting performance and build quality when used in an inkjet 3-D printer. Previous research has addressed the desirable rheology characteristics to enable stable drop formation and how the metallic nanoparticles affect the viscosity of inks. The contending goals of increasing nanoparticle-loading to improve material deposition rates while trying to maintain optimal flow dynamics is the closely held trade secret in formulating these inkjet compositions. We use data from previous experiments and the CRC Handbook of Chemistry and Physics to train machine learning regression models to predict the relevant factors of inkjet printability at a standardized temperature of 25ºC: viscosity, surface tension, and density. These models were used to predict the rheological factors of the main components of a UV-curable inkjet ink formulation: UV-curable monomers and oligomers, photoinitiators, dispersants, and humectants. This paper compares the relative performance of five machine learning algorithms to assess the effectiveness of each approach for chemoinformatics regression tasks.
Award received:
Third Place in Masters Thesis Competition at 2024 North American IEOM Conference
Included in
Computational Chemistry Commons, Industrial Technology Commons, Nanoscience and Nanotechnology Commons, Polymer and Organic Materials Commons