Loading...
Location
Allen E. Paulson College of Engineering and Computing (CEC)
Session Format
Poster Presentation
Co-Presenters and Faculty Mentors or Advisors
Dr. Hossein Taheri, Faculty Advisor
Abstract
Additive manufacturing (AM) becomes increasingly popular nowadays because of its time and cost-saving benefits. AM can create complex geometrical shapes by a single process which saves time. Besides, subtractive manufacturing has to waste some material during machining and preparation for assembly, but additive manufacturing does not have a high amount of waste. Because of the complexity of the manufacturing process, there are some defects that can be formed in AM parts. These flaws need to be identified to make AM parts more efficient in various industries. Various non-destructive (NDT) techniques have been developed and used for quality inspection of the AM parts and for identification of possible porosity and cracks. In situ monitoring through acoustic emission (AE) is one of the most used technologies which also needs to have more development for commercial use. In this study, acquired data through AE from the direct energy deposition (DED) AM process has been analyzed for the identification of different process conditions. The analysis is done through wavelet transformation, and the transformed imaged is being analyzed by a convolutional neural network (CNN). The classification by wavelet transformation and CNN is finally evaluated by nanoindentation, SEM, and EDS experiments for verification of material properties.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Presentation Type and Release Option
Presentation (Open Access)
Recommended Citation
Hossain, Md Shahjahan, "Acoustic Emission (AE) for In Situ Monitoring of Metal Additive Manufacturing Process" (2021). GS4 Georgia Southern Student Scholars Symposium. 102.
https://digitalcommons.georgiasouthern.edu/research_symposium/2021/2021/102
Presentation Updated
Md Shahjahan Hossain_Poster_207.pdf (944 kB)
Poster Updated
Acoustic Emission (AE) for In Situ Monitoring of Metal Additive Manufacturing Process
Allen E. Paulson College of Engineering and Computing (CEC)
Additive manufacturing (AM) becomes increasingly popular nowadays because of its time and cost-saving benefits. AM can create complex geometrical shapes by a single process which saves time. Besides, subtractive manufacturing has to waste some material during machining and preparation for assembly, but additive manufacturing does not have a high amount of waste. Because of the complexity of the manufacturing process, there are some defects that can be formed in AM parts. These flaws need to be identified to make AM parts more efficient in various industries. Various non-destructive (NDT) techniques have been developed and used for quality inspection of the AM parts and for identification of possible porosity and cracks. In situ monitoring through acoustic emission (AE) is one of the most used technologies which also needs to have more development for commercial use. In this study, acquired data through AE from the direct energy deposition (DED) AM process has been analyzed for the identification of different process conditions. The analysis is done through wavelet transformation, and the transformed imaged is being analyzed by a convolutional neural network (CNN). The classification by wavelet transformation and CNN is finally evaluated by nanoindentation, SEM, and EDS experiments for verification of material properties.
