Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 3 of 3
Full-Text Articles in Engineering
Parametric Structural Optimization Of A Wheel Using The Flex Representation Method, Gregory John Vernon
Parametric Structural Optimization Of A Wheel Using The Flex Representation Method, Gregory John Vernon
Theses and Dissertations
The use of the finite element method within an optimization workflow is fraught with challenges that limit the automation of such workflows. These challenges are inherent to the traditional finite element formulations which are heavily dependent on a manual meshing process that introduces variability that is challenging to account for within an automated workflow. The recently developed flex representation method (FRM) provides a salient solution to the manual meshing process without sacrificing solution accuracy. In response to the development of FRM a global automotive company requested a study to explore the applicability of FRM to one of their sizing-optimization problems: …
Hybrid Machine Learning And Physics-Based Modeling Approaches For Process Control And Optimization, Junho Park
Hybrid Machine Learning And Physics-Based Modeling Approaches For Process Control And Optimization, Junho Park
Theses and Dissertations
Transformer neural networks have made a significant impact on natural language processing. The Transformer network self-attention mechanism effectively addresses the vanishing gradient problem that limits a network learning capability, especially when the time series gets longer or the size of the network gets deeper. This dissertation examines the usage of the Transformer model for time-series forecasting and customizes it for a simultaneous multistep-ahead prediction model in a surrogate model predictive control (MPC) application. The proposed method demonstrates enhanced control performance and computation efficiency compared to the Long-short term memory (LSTM)-based MPC and one-step-ahead prediction model structures for both LSTM and …
Selecting And Optimizing Origami-Based Patterns For Deployable Space Systems, Diana Stefania Bolanos
Selecting And Optimizing Origami-Based Patterns For Deployable Space Systems, Diana Stefania Bolanos
Theses and Dissertations
This thesis addresses the design difficulties encountered when designing deployable origami-based arrays. Specific considerations regarding thickness accommodation, deployment, and parameter modifications are discussed. Patterns such as the Miura-ori, flasher, and hexagon are investigated, with emphasis placed on pattern modification from zero-thickness to finite-thickness. Applying origami principles to form engineering solutions is a complicated task. Competing requirements may create confusion around which pattern is most favorable for the space array application. Implementing origami into a finite-thickness, engineered system poses challenges that are not manifest in a zero-thickness model. As such, it is important to understand and address the limitations of the …