Keywords and Phrases
Acoustic Emission; Artificial Neural Network; Deposition Defects Detection; Depth of Cut Detection; Laser Metal Deposition; Machine Learning
"The approach of hybrid manufacturing addressed in this research uses two manufacturing processes, one process builds a metal part using laser metal deposition, and the other process finishes the part using a milling machining. The ability to produce complete functioning parts in a short time with minimal cost and energy consumption has made hybrid manufacturing popular in many industries for parts repair and rapid prototyping. Monitoring of hybrid manufacturing processes has become popular because it increases the quality and accuracy of the parts produced and reduces both costs and production time. The goal of this work is to monitor the entire hybrid manufacturing process. During the laser metal deposition, the acoustic emission sensor will monitor the defect formation. The acoustic emission sensor will monitor the depth of cut during milling machining. There are three tasks in this study. The first task addresses depth-of-cut detection and tool-workpiece engagement using an acoustic emission monitoring system during milling machining for a deposited material. The second task, defects monitoring system was proposed to detect and classify defects in real time using an acoustic emission (AE) sensor and an unsupervised pattern recognition analysis (K-means clustering) in conjunction with a principal component analysis (PCA). In the third task, a study was conducted to investigate the ability of AE to detect and identify defects during laser metal deposition using a Logistic Regression Model (LR) and an Artificial Neural Network (ANN)"--Abstract, page iv.
Liou, Frank W.
Kinzel, Edward C.
Cudney, Elizabeth A.
Mechanical and Aerospace Engineering
Ph. D. in Mechanical Engineering
U.S. National Science Foundation
Product Innovation and Engineering, LLC
Missouri University of Science and Technology Intelligent Systems Center
Missouri University of Science and Technology Manufacturing Engineering Program
Missouri University of Science and Technology
Journal article titles appearing in thesis/dissertation
- Automatic detection of depth of cut during end milling operation using acoustic emission sensor
- Defects monitoring of laser metal deposition using acoustic emission sensor
- Defects classification of laser metal deposition using logistic regression and artificial neural networks for pattern recognition
xiii, 102 pages
© 2018 Haythem Gaja, All rights reserved.
Dissertation - Open Access
Electronic OCLC #
Gaja, Haythem, "Monitoring of hybrid manufacturing using acoustic emission sensor" (2018). Doctoral Dissertations. 2701.