Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


40520.pdf (10.61 MB)

ETD Abstract Container

Abstract Header

Intelligent Design and Processing for Additive Manufacturing Using Machine Learning

Hertlein, Nathan
http://rave.ohiolink.edu/etdc/view?acc_num=ucin1637156915513814

Abstract Details

2021, PhD, University of Cincinnati, Engineering and Applied Science: Mechanical Engineering.
Additive manufacturing has significantly expanded the achievable geometric design space for components to be built from a wide set of materials. At the same time, it has come with complex process parameters that must be chosen carefully to ensure optimal build quality, often on a part-by-part basis. This has created the need for methods to take full advantage of the new design freedom in a manner that is compatible with the capabilities of additive processes and a need for intelligently selecting the interrelated build parameters of the process. Meanwhile, mechanical engineers routinely face a range of design scenarios, each with its own level of complexity. Optimal engineering efforts in these scenarios would each suffer from considerable compromises if addressed by some single computational approach. Therefore, a series of design optimization approaches are required, with differences where necessary and similarities where possible. There is a corresponding need to computationally optimize the AM processes themselves. Collectively, these efforts are motivated by the goal of fully utilizing AM’s design freedom to achieve complex parts with the exact desired behavior, which ranges from lightweight strength to tunable secondary stable configurations. An ensemble of approaches to this end has been emerging in the literature. However, the following challenges persist, which the present work is intended to address, through the careful integration of machine learning with traditional design and manufacturing principles. Computational expense associated with design optimization can be high even when static loading is assumed on linear materials, so we employ a generative adversarial network (GAN) to reduce expensive, iterative finite element analysis (FEA) requirements. There is a scarcity of considerations for strain rate effects, for which we use Bayesian optimization. Current approaches in the literature are also often limited to monostable structures, so we propose objective and optimization formulations to advance the area of bistable structural design. Finally, by relying on a Bayesian network, our process-driven framework for part quality prediction addresses limitations in the literature related to uncertainty quantification.
Sam Anand, Ph.D. (Committee Chair)
Kumar Vemaganti (Committee Member)
Manish Kumar, Ph.D. (Committee Member)
Philip Buskohl, Ph.D. (Committee Member)
180 p.
Mechanical Engineering
Additive Manufacturing; Machine Learning; Artificial Neural Networks; Topology Optimization; Impact Loading; Multistable Structures

Recommended Citations

Citations

  • Hertlein, N. (2021). Intelligent Design and Processing for Additive Manufacturing Using Machine Learning [Doctoral dissertation, University of Cincinnati]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1637156915513814

    APA Style (7th edition)

  • Hertlein, Nathan. Intelligent Design and Processing for Additive Manufacturing Using Machine Learning. 2021. University of Cincinnati, Doctoral dissertation. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=ucin1637156915513814.

    MLA Style (8th edition)

  • Hertlein, Nathan. "Intelligent Design and Processing for Additive Manufacturing Using Machine Learning." Doctoral dissertation, University of Cincinnati, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1637156915513814

    Chicago Manual of Style (17th edition)

ucin1637156915513814
38
© 2021, all rights reserved.
This open access ETD is published by University of Cincinnati and OhioLINK.