Machine Learning for Predicting Additive Manufacturing Part Quality - Tutorial on Support Vector Regression

Learn how to use machine learning, specifically support vector regression (SVR), to predict the quality of additive manufacturing parts in this comprehensive 55-minute tutorial. Explore the challenges of 3D printing accuracy and discover how to train an SVR model using real factory data to predict part dimensions based on design geometry and manufacturing parameters. Master techniques like grid search hyperparameter tuning and nested cross-validation to improve model performance. Compare SVR with other algorithms such as k-nearest neighbors (KNN) and evaluate their computational cost and predictive accuracy. Gain hands-on experience using Jupyter Notebooks on nanoHUB to apply these concepts in practice.

Machine Learning Predicts Additive Manufacturing Part Quality
Additive Manufacturing
Qualification for AM
Research Objectives
Tutorial Overview
Introduction to Machine Learning
Support Vector Regression
Machine Learning Framework
Exploratory Data Analysis
Data Split
Jupyter Notebook on nanoHUB
Demo
Data Standardization
Hyperparameter Tuning
Cross Validation
Nested Cross Validation
Demo
Summary