Semester
Summer
Date of Graduation
2021
Document Type
Thesis
Degree Type
MS
College
Statler College of Engineering and Mineral Resources
Department
Industrial and Managements Systems Engineering
Committee Chair
Zhichao Liu
Committee Member
Thorsten Wuest
Committee Member
Kenneth R Currie
Abstract
Directed energy deposition (DED) is a rising field in the arena of metal additive manufacturing and has extensive applications in aerospace, medical and rapid prototyping. The process parameters, such as laser power, scanning speed and specimen height, play a great deal in controlling and affecting the properties of DED fabricated parts. Nevertheless, both experimental and simulation methods have shown constraints and limited ability to generate accurate and efficient computational predictions on the correlations between the process parameters and the final part quality. In this work, a data driven machine learning model XGBoost has been built and applied to predict the tensile behaviors of the stainless steel 316 parts by DED with variation in process parameters i.e. laser power, scanning speed, layer height and energy density. For the validation purpose, molten pool temperature data has been provided to the model and it was able to predict the molten pool temperature successfully with a very high accuracy. After the tensile testing, the model was able to predict the tensile properties i.e. yield strength, elongation (%) and ultimate tensile strength of the fabricated parts with a limited size of training data and to compute the significance of the factors affecting the part quality. Performance of the model was then compared with ridge regression and XGBoost outperformed ridge regression.
Recommended Citation
Era, Israt Zarin, "Prediction of Tensile Behaviors of L-DED 316 Stainless Steel parts using Machine Learning" (2021). Graduate Theses, Dissertations, and Problem Reports. 8274.
https://researchrepository.wvu.edu/etd/8274