Mechanical Engineering Commons^™

Deep Reinforcement Learning For The Design Of Structural Topologies, Nathan Brown

All Dissertations

Advances in machine learning algorithms and increased computational efficiencies have given engineers new capabilities and tools for engineering design. The presented work investigates using deep reinforcement learning (DRL), a subset of deep machine learning that teaches an agent to complete a task through accumulating experiences in an interactive environment, to design 2D structural topologies. Three unique structural topology design problems are investigated to validate DRL as a practical design automation tool to produce high-performing designs in structural topology domains.

The first design problem attempts to find a gradient-free alternative to solving the compliance minimization topology optimization problem. In the proposed …

Multiple Objective Function Optimization And Trade Space Analysis, Yifan Xu

All Theses

Optimization can assist in obtaining the best possible solution to a design problem by varying related variables under given constraints. It can be applied in many practical applications, including engineering, during the design process. The design time can be further reduced by the application of automated optimization methods. Since the required resource and desired benefit can be translated to a function of variables, optimization can be viewed as the process of finding the variable values to reach the function maxima or minima. A Multiple Objective Optimization (MOO) problem is when there is more than one desired function that needs to …

An Application Of Optimized Bistable Laminates As A Low Velocity, Low Impact Mechanical Deterrent, Graham Lancaster

All Theses

This research considers the problem of using bistable laminates as a mechanical deterrent to the impending impact of a particle. The structure will be controlled through an algorithm that will utilize piezoelectric devices to activate them in unison with the bistable laminate to successfully deter. A novel experimental setup will be constructed to ensure that the bistable laminate stays fixed when acting as a mechanical deterrent. Piezoelectricity is the main driving force of the bistable laminate to morph and this study will use a Macro Fiber Composite (MFC) actuator that contains piezoelectric ceramic rods in a patch to transfer electrical …

Development Of A Reverse Engineered, Parameterized, And Structurally Validated Computational Model To Identify Design Parameters That Influence American Football Faceguard Performance, William Ferriell

All Dissertations

Traumatic brain injury (TBI) continues to have the greatest incidence among athletes participating in American football. The headgear design research community has focused on developing accurate computational and experimental analysis techniques to better assess the ability of headgear technology to attenuate impacts and protect athletes from TBI. Despite efforts to innovate the headgear system, minimal progress has been made to innovate the faceguard. Although the faceguard is not the primary component of the headgear system that contributes to impact attenuation, faceguard performance metrics, such as weight, structural stiffness, and visual field occlusions, have been linked to athlete safety. To improve …

Identifying Target Properties For The Design Of Meta-Material Tank Track Pads, Venkata Sampath Dangeti

All Theses

On track vehicle systems, track pads are designed to provide traction and support the weight of the vehicle, they have limited service life due to common failure by blowout. According to the literature, blowout is a failure mode caused by overheating due to hysteresis in elastomeric materials during high speed operations. Elastomers are used primarily for their high compliance, which is essential to protect the suspension components and maintain structural integrity of the track pad. The objective of the work is to explore the use of linear elastic meta-materials with optimized topology to replace elastomers and reduce or eliminate the …

Design Of Meta-Materials Outside The Homogenization Limit Using Multiscale Analysis And Topology Optimization, Christopher Czech

All Dissertations

The field of meta-materials engineering has largely expanded mechanical design possibilities over the last two decades; some notable design advances include the systematic engineering of negative Poisson's ratio materials and functionally graded materials, materials designed for optimal electronic and thermo-mechanical performances, and the design of materials under uncertainty. With these innovations, the systematic engineering of materials for design-specific uses is becoming more common in industrial and military uses. The motivation for this body of research is the design of the shear beam for a non-pneumatic wheel. Previously, a design optimization of a finite element model of the non-pneumatic wheel was …

Modeling, Finite Element Analysis, And Optimization Of Non-Pneumatic Tire (Npt) For The Minimization Of Rolling Resistance, Mallikarjun Veeramurthy

All Theses

Recently, the development of non-pneumatic tires (NPT) such as the Michelin Tweel is receiving increased attention due to potential advantages over pneumatic tires such as low mass, no run flat, good contact pressure distribution, and low rolling resistance (RR). This study focuses on the design of a NPT based on properties of vertical stiffness, contact pressure, and rolling energy loss. Using a finite element (FE) model, a parametric study is conducted to study the effect on vertical stiffness, contact pressure, and rolling resistance (RR) response considering three design variables: (1) thickness of the spokes, (2) the shear band thickness, and …

Requirements Determination Of A Novel Non-Pneumatic Wheel Shear Beam For Low Rolling Resistance, Niranjan Thyagaraja

All Theses

The hysteretic loss associated with cyclic shear in the elastomeric shear layer is one of the prevailing concerns for the development of a low rolling loss non-pneumatic wheel. We propose to eliminate the hysteretic losses associated with the elastomeric shear layer and thus, reduce the corresponding rolling resistance by using linear elastic materials which are inherently non-hysteretic. Since the shear modulus of a viscoelastic shear layer is less than that of an elastic material by several orders of magnitude, the challenge to achieve a low effective shear modulus shear layer with linear elastic materials directs towards the development of a …

Agent-Based Under Hood Packing, Karthik Ravindranath

All Theses

Improving vehicle performance and passenger comfort has been a prime engineering concern and focus of research for many years in automotive design. Turning to high-performance components in an effort to improve vehicle performance alone is often not enough and their placement and interactions with other components should also be an integral part of the improvement process. With the advancement in hybrid electric vehicle technology, the packing of components under the hood is ever more essential and challenging. Under hood packing is a multi-objective optimization problem with many, and mostly conflicting objectives. A non-deterministic multi-objective evolutionary algorithm needs to be integrated …