國立虎尾科技大學 |

Comprehensive Modeling of Process-Molten Pool Condition-Property Correlations for Wire-Feed Laser Additive Manufacturing.

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Comprehensive Modeling of Process-Molten Pool Condition-Property Correlations for Wire-Feed Laser Additive Manufacturing./
Author:	Jamnikar, Noopur.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
Description:	134 p.
Notes:	Source: Dissertations Abstracts International, Volume: 83-04, Section: B.
Contained By:	Dissertations Abstracts International83-04B.
Subject:	Mechanical engineering. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28650952
ISBN:	9798460421947

Comprehensive Modeling of Process-Molten Pool Condition-Property Correlations for Wire-Feed Laser Additive Manufacturing.
Jamnikar, Noopur.

Comprehensive Modeling of Process-Molten Pool Condition-Property Correlations for Wire-Feed Laser Additive Manufacturing. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 134 p.

Source: Dissertations Abstracts International, Volume: 83-04, Section: B.

Thesis (Ph.D.)--Colorado School of Mines, 2021.

This item must not be sold to any third party vendors.

Wire-feed laser additive manufacturing (WLAM) is gaining wide interest due to its high level of automation, high deposition rates, and good quality of printed parts. The complexity of modeling the directed energy deposition (DED) process, high characterization and printing cost, and the destructive testing of the final build part for quality testing motivates the need for developing in situ quality assurance and control techniques. In-process monitoring and feedback controls that would reduce the uncertainty in the quality of the fabricated parts are in the early stages of development. Machine learning (ML) promises the ability to accelerate the adoption of in-process monitoring and control in additive manufacturing (AM) by modeling and predicting process-sensing-property connections between process setting inputs and material quality outcomes. However, the lack of sufficient sensing and characterization data for training ML models is a significant challenge in the field of AM industry due to associated high costs. This thesis explores the in situ quality assurance and control methods by studying the process-molten pool condition-property relation for the robotic laser wire-feed DED process. Analysis and characterization are performed on the experimentally collected in situ sensing data for the molten pool under a set of controlled process parameters for a WLAM system. The real-time molten pool dimensional information and temperature data are the indicators for achieving good quality of the build, which can be directly controlled by processing parameters. Thus, the process-molten pool condition-property relations are of preliminary importance for developing a quality control and assurance framework. The results highlight collaborative and quantitative multi-modality models for controlling and estimating the process and quality parameters using real-time sensing data.

ISBN: 9798460421947Subjects--Topical Terms:

557493
Mechanical engineering.
Subjects--Index Terms:

Convolutional neural network (CNN)

Comprehensive Modeling of Process-Molten Pool Condition-Property Correlations for Wire-Feed Laser Additive Manufacturing.
LDR:03176nam a2200385 4500 001 1067226
005 20220823142321.5
008 221020s2021 ||||||||||||||||| ||eng d
020 $a 9798460421947
035 $a (MiAaPQ)AAI28650952
035 $a AAI28650952
040 $a MiAaPQ $c MiAaPQ
100 1 $a Jamnikar, Noopur. $3 1372687
245 1 0 $a Comprehensive Modeling of Process-Molten Pool Condition-Property Correlations for Wire-Feed Laser Additive Manufacturing.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 134 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-04, Section: B.
500 $a Advisor: Zhang, Xiaoli.
502 $a Thesis (Ph.D.)--Colorado School of Mines, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Wire-feed laser additive manufacturing (WLAM) is gaining wide interest due to its high level of automation, high deposition rates, and good quality of printed parts. The complexity of modeling the directed energy deposition (DED) process, high characterization and printing cost, and the destructive testing of the final build part for quality testing motivates the need for developing in situ quality assurance and control techniques. In-process monitoring and feedback controls that would reduce the uncertainty in the quality of the fabricated parts are in the early stages of development. Machine learning (ML) promises the ability to accelerate the adoption of in-process monitoring and control in additive manufacturing (AM) by modeling and predicting process-sensing-property connections between process setting inputs and material quality outcomes. However, the lack of sufficient sensing and characterization data for training ML models is a significant challenge in the field of AM industry due to associated high costs. This thesis explores the in situ quality assurance and control methods by studying the process-molten pool condition-property relation for the robotic laser wire-feed DED process. Analysis and characterization are performed on the experimentally collected in situ sensing data for the molten pool under a set of controlled process parameters for a WLAM system. The real-time molten pool dimensional information and temperature data are the indicators for achieving good quality of the build, which can be directly controlled by processing parameters. Thus, the process-molten pool condition-property relations are of preliminary importance for developing a quality control and assurance framework. The results highlight collaborative and quantitative multi-modality models for controlling and estimating the process and quality parameters using real-time sensing data.
590 $a School code: 0052.
650 4 $a Mechanical engineering. $3 557493
650 4 $a Operations research. $3 573517
650 4 $a Computer science. $3 573171
653 $a Convolutional neural network (CNN)
653 $a Molten pool
653 $a Process parameter
653 $a Property
653 $a Quality control
653 $a Wire-feed laser additive manufacturing (WLAM)
690 $a 0548
690 $a 0796
690 $a 0984
710 2 $a Colorado School of Mines. $b Mechanical Engineering. $3 1241272
773 0 $t Dissertations Abstracts International $g 83-04B.
790 $a 0052
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28650952