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 …

Modeling And Solution Methodologies For Mixed-Model Sequencing In Automobile Industry, Ibrahim Ozan Yilmazlar

All Dissertations

The global competitive environment leads companies to consider how to produce high-quality products at a lower cost. Mixed-model assembly lines are often designed such that average station work satisfies the time allocated to each station, but some models with work-intensive options require more than the allocated time. Sequencing varying models in a mixed-model assembly line, mixed-model sequencing (MMS), is a short-term decision problem that has the objective of preventing line stoppage resulting from a station work overload. Accordingly, a good allocation of models is necessary to avoid work overload. The car sequencing problem (CSP) is a specific version of the …

Essays On Perioperative Services Problems In Healthcare, Amogh S. Bhosekar

All Dissertations

One of the critical challenges in healthcare operations management is to efficiently utilize the expensive resources needed while maintaining the quality of care provided. Simulation and optimization methods can be effectively used to provide better healthcare services. This can be achieved by developing models to minimize patient waiting times, minimize healthcare supply chain and logistics costs, and maximize access. In this proposal, we study some of the important problems in healthcare operations management. More specifically, we focus on perioperative services and study scheduling of operating rooms (ORs) and management of necessary resources such as staff, equipment, and surgical instruments. We …

Optimal Global Supply Chain And Warehouse Planning Under Uncertainty, Avnish Kishor Malde

All Dissertations

A manufacturing company's inbound supply chain consists of various processes such as procurement, consolidation, and warehousing. Each of these processes is the focus of a different chapter in this dissertation.

The manufacturer depends on its suppliers to provide the raw materials and parts required to manufacture a finished product. These suppliers can be located locally or overseas with respect to the manufacturer's geographic location. The ordering and transportation lead times are shorter if the supplier is located locally. Just In Time (JIT) or Just In Sequence (JIS) inventory management methods could be practiced by the manufacturer to procure the raw …

Hierarchical And Distributed Architecture For Large-Scale Residential Demand Response Management, Pramod Herath Mudiyanselage

All Dissertations

The implementation of smart grid brings several challenges to the power system. The ‘prosumer’ concept, proposed by the smart grid, allows small-scale ‘nano-grids’ to buy or sell electric power at their own discretion. One major problem in integrating prosumers is that they tend to follow the same pattern of generation and consumption, which is un-optimal for grid operations. One tool to optimize grid operations is demand response (DR). DR attempts to optimize by altering the power consumption patterns. DR is an integrated tool of the smart grid. FERC Order No. 2222 caters for distributed energy resources, including demand response resources, …

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 …

Strategies To Improve The Efficiency Of Emergency Medical Service (Ems) Systems Under More Realistic Conditions, Kanchala Sudtachat

All Dissertations

Emergency medical service (EMS) systems provide medical care to pre-hospital patients who need rapid response and transportation. This dissertation proposes a new realistic approach for EMS systems in two major focuses: multiple unit dispatching and relocation strategies. This work makes recommendations for multiple-unit dispatch to multiple call priorities based on simulation optimization and heuristics. The objective is to maximize the expected survival rate. Simulation models are proposed to determine the optimization. A heuristic algorithm is developed for large-scale problems. Numerical results show that dispatching while considering call priorities, rather than always dispatching the closest medical units, could improve the effectiveness …

Predictive Maturity Of Inexact And Uncertain Strongly Coupled Numerical Models, Ismail Farajpour

All Dissertations

The Computer simulations are commonly used to predict the response of complex systems in many branches of engineering and science. These computer simulations involve the theoretical foundation, numerical modeling and supporting experimental data, all of which contain their associated errors. Furthermore, real-world problems are generally complex in nature, in which each phenomenon is described by the respective constituent models representing different physics and/or scales. The interactions between such constituents are typically complex in nature, such that the outputs of a particular constituent may be the inputs for one or more constituents. Thus, the natural question then arises concerning the validity …

Optimization Of Porous Pavement Mixtures Based On Aggregate Structure, Andrew Neptune

All Dissertations

Porous pavements are sustainable features that are used to help manage the quantity and quality of stormwater runoff. These pavements may include porous asphalt, permeable interlocking concrete pavers and pervious concrete. Since pavements that are purposefully designed to drain water through their matrix are relatively new, contractors and engineers are faced with various challenges such as improper design and installation, poor workability, and excessive finishing which may lead to clogged pores. Therefore, this study on porous pavements examined pervious concrete mixtures to evaluate an optimization process for the preparation of porous pavement mixtures based on aggregate structure to meet desired …

Stochastic Tools For Network Security: Anonymity Protocol Analysis And Network Intrusion Detection, Lu Yu

All Dissertations

With the rapid development of Internet and the sharp increase of network crime, network security has become very important and received a lot of attention.
In this dissertation, we model security issues as stochastic systems. This allows us to find weaknesses in existing security systems and propose new solutions. Exploring the vulnerabilities of existing security tools can prevent cyber-attacks from taking advantages of the system weaknesses. We consider The Onion Router (Tor), which is one of the most popular anonymity systems in use today, and show how to detect a protocol tunnelled through Tor. A hidden Markov model (HMM) is …

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 …

Development And Integration Of Geometric And Optimization Algorithms For Packing And Layout Design, Santosh Tiwari

All Dissertations

The research work presented in this dissertation focuses on the development and application of optimization and geometric algorithms to packing and layout optimization problems. As part of this research work, a compact packing algorithm, a physically-based shape morphing algorithm, and a general purpose constrained multi-objective optimization algorithm are proposed. The compact packing algorithm is designed to pack three-dimensional free-form objects with full rotational freedom inside an arbitrary enclosure such that the packing efficiency is maximized. The proposed compact packing algorithm can handle objects with holes or cavities and its performance does not degrade significantly with the increase in the complexity …

Biohydrogen Production By The Hyperthermophilic Bacterium Thermotoga Neapolitana, Xiaohui Yu

All Dissertations

ABSTRACT Thermotoga neapolitana can use different sources of carbon and nitrogen for growth and produces biological hydrogen. Sources of carbon (glucose, sucrose, xylose, xylan, cellulose, cellobiose, starch, corn starch, beet bulp pellet, and rice flour) and nitrogen (yeast extract, fish meal, cottonseed meal, canola meal, linseed meal, and soybean meal) were compared. In the carbon studies, glucose, sucrose, rice flour, and xylan produced similar levels of hydrogen. In the nitrogen studies, Trypticase combined with alternative nitrogen sources can efficiently increases the yield of hydrogen produced by Thermotoga neapolitana. Yeast extract with trypticase as the dual nitrogen sources produced significantly increased …