Term of Award

Spring 2021

Degree Name

Master of Science in Applied Engineering (M.S.A.E.)

Document Type and Release Option

Thesis (open access)

Copyright Statement / License for Reuse

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Department

Department of Manufacturing Engineering

Committee Chair

Hossein Taheri

Committee Member 1

Daniel Cox

Committee Member 2

Drew Snelling

Abstract

Additive Manufacturing (AM) is currently a widely used technology in different industries such as aerospace, medical, and consumer products. Previously it was mainly used for prototyping of the products, but now it is equally valuable for commercial product manufacturing. More profound understanding is still needed to track and identify defects during the AM process to ensure higher quality products with less material waste. Nondestructive testing becomes an essential form of testing for AM parts, where AE is one of the most used methods for in situ process monitoring. The Acoustic Emission (AE) approach has gained a reputation in nondestructive testing (NDT) as one of the most influential and proven techniques in numerous engineering fields. Material testing through Acoustic Emission (AE) has become one of the most popular techniques in AM because of its capability to detect defects and anomalies and monitor the progress of flaws. Various AE technique approaches have been under investigation for in-situ monitoring of AM products. The preliminary results from AE exploration show promising results which need further investigation on data analysis and signal processing. AE monitoring technique allows finding the defects during the fabrication process, so that failure of the AM can be prevented, or the process condition can be finely tuned to avoid significant damages or waste of materials. In this work, recorded AE data over the Direct Energy Deposition (DED) additive manufacturing process was analyzed by the Machine Learning (ML) algorithm to classify different build conditions. The feature extraction method is used to obtain the required data for further processing. Wavelet transformation of signals has been used to acquire the time-frequency spectrum of the AE signals for different process conditions, and image processing by Convolutional Neural Network (CNN) is used to identify the transformed spectrum of different build conditions. The identifiers in AE signals are correlated to the part quality by statistical methods. The results show a promising approach for quality evaluation and process monitoring in AM. In this work, the assessment of deposition properties at different process conditions is also done by optical microscope, Scanning Electron Microscope (SEM), Energy-Dispersive X-ray Spectroscopy (EDS), and nanoindentation technique.

Research Data and Supplementary Material

No

Share

COinS