Semester of Graduation
Spring 2024
Degree
Master of Science in Computer Science (MSCS)
Department
Computer Science
Document Type
Thesis
Abstract
Following the current trends for minimizing human intervention in training intelligent architectures, this thesis proposes a self-supervised method for quality control of Additive Manufacturing (AM) parts. An Inconel 939 sample is fabricated with the Laser Powder Bed Fusion (L-PBF) method and scanned using X-ray Computed Tomography (XCT) to reveal the internal cracks. The presented workflow employs three modules that generate crack-like features for training a CycleGAN network within a self-supervised framework. By incorporating a combination of uniform and normal random variables, the method generates random cracks, exhibiting superior performance in fine-grain crack detection and capturing narrow tips compared to other approaches. Furthermore, a preliminary investigation into the training process reveals the algorithm's capability to predict crack propagation direction. The project introduces the IN939Crack dataset, a pioneering public dataset comprising typical internal features in Inconel 939 parts fabricated through L-PBF.
Date
1-25-2024
Recommended Citation
Nemati, Mohammadsaber, "Self-supervised Crack Detection in X-ray Computed Tomography Data of Additive Manufacturing Parts" (2024). LSU Master's Theses. 5892.
https://repository.lsu.edu/gradschool_theses/5892
Committee Chair
Hao Wang