Digital Commons Network^™

Uncertainty-Aware Deep Learning For Prediction Of Remaining Useful Life Of Mechanical Systems, Samuel J. Cornelius

Theses and Dissertations

Remaining useful life (RUL) prediction is a problem that researchers in the prognostics and health management (PHM) community have been studying for decades. Both physics-based and data-driven methods have been investigated, and in recent years, deep learning has gained significant attention. When sufficiently large and diverse datasets are available, deep neural networks can achieve state-of-the-art performance in RUL prediction for a variety of systems. However, for end users to trust the results of these models, especially as they are integrated into safety-critical systems, RUL prediction uncertainty must be captured. This work explores an approach for estimating both epistemic and heteroscedastic …

Study Of Alloy And Process Modifications To Design Hydrogen Resilient High Hardness Steels, William R. Williams

Theses and Dissertations

High hardness steels (HHS) are vulnerable to hydrogen embrittlement, which can lead to rapid degradation of mechanical properties. Improved resistance to hydrogen embrittlement would be beneficial to many industries including construction, automotive, and military. A comparison study was performed to assess the hydrogen susceptibility of select commercially available and in-house designed HHS alloys. Slow strain rate tensile tests, performed with specimens charged with various levels of hydrogen, provided a macroscopic view of the onset of hydrogen embrittlement. Hydrogen permeation and thermal desorption spectroscopy tests determined the uptake and diffusivity of hydrogen through the material. The evaluation of hydrogen susceptibility for …

Testing Of Methods For Reducing Motivational Bias In Multi - Criteria Decision Analysis Problems, Chadwick Samuel Kerr

Theses and Dissertations

The idea of multi-criteria decision making has been around for quite a while. All judgement tasks are potential points of bias introduction. Each judgement task was assessed to identify common biases introduced through an extensive literature review for each task and bias. In several other studies, the distinction is made between cognitive and motivational biases. Cognitive biases are widely studied and well known with mitigations that have been validated. Motivational biases are judgements influenced by the decision maker’s desire for a specific outcome, also referred to as intentional bias, that are hard to correct and received very little testing and …

The Development Of An Immersive Virtual Exploratory Engine (Ivee) For Immersive Analytics, Sofia Karam

Theses and Dissertations

Due to increasing data complexity, researchers are struggling to visually explore data using traditional methods. Research has shown that a variety of analytics-related tasks can be enhanced using new emerging technologies (e.g., virtual reality [VR] and augmented reality [AR]). This paper provides a detailed design approach for developing an immersive virtual engine system for conducting exploratory and descriptive data analytics. This system is called the Immersive Virtual Exploratory Engine (IVEE), is a VR system that allows users to experience full intractability with its graphical elements and examines various datasets within the same immersive environment. Basic plots—such as histograms, line plots, …

Verification Of Acoustic Dissipation In Two-Phase Dilute Dispersed Flow Models In Computational Fluid Dynamics, Brennan Reeder

Theses and Dissertations

With existing numerical models for fluid particle systems in CHEM, the acoustic-particle interactions associated with two-phase dilute dispersed flow can be captured and the particle model can be validated using experimental and analytical data and verified using numerical techniques. The experimental and analytical data come from Zink and Delsasso and provides data for particles of diameters 5 to 15 microns for frequencies between 500Hz to 13600Hz. In the particle number density measurements by Zink and Delsasso there was a 10% estimated error range. Using the fourth order skew symmetric flux in CHEM and the built in Eulerian and Lagrangian particle …

Predictive Computational Materials Modeling With Machine Learning: Creating The Next Generation Of Atomistic Potential Using Neural Networks, Mashroor Shafat Nitol

Theses and Dissertations

Machine learning techniques using artificial neural networks (ANNs) have proven to be effective tools to rapidly mimic first principles calculations. These tools are capable of sub meV/atom accuracy while operating with linear scaling with respect to the system size. Here novel interatomic potentials are constructed based on the rapid artificial neural network (RANN) formalism. This approach generates precise force fields for various metals that have historically been difficult to describe at the atomic scale. These force fields can be utilized in molecular dynamics simulations to provide new physical insights. The RANN formalism, which is incorporated into a LAMMPS molecular dynamics …

A Data-Driven Approach For The Investigation Of Microstructural Effects On The Effective Piezoelectric Responses Of Additively Manufactured Triply Periodic Bi-Continuous Piezocomposite, Wenhua Yang

Theses and Dissertations

A two-scale model consisting of ceramic grain scale and composite scale are developed to systematically evaluate the effects of microstructures (e.g., residual pores, grain size, texture) and geometry on the piezoelectric responses of the polarized triply periodic bi-continuous (TPC) piezocomposites. These TPC piezocomposites were fabricated by a recently developed additive manufacturing (AM) process named suspension-enclosing projection-stereolithography (SEPS) under different process conditions. In the model, the Fourier spectral iterative perturbation method (FSIPM) and the finite element method will be adopted for the calculation at the grain and composite scale, respectively. On the grain scale, a DL approach based on stacked generative …

Modulation Of Effector Gene Expression In The Blood-Feeding Arthropods Cimex Lectularius Linnaeus, (Hemiptera: Cimicidae) And Aedes Albopictus Skuse, (Diptera: Culicidae), Travis C. Van Warmerdam

Theses and Dissertations

Hematophagy, or blood-feeding behavior, has independently evolved multiple times in the class Insecta and results in the transmission of vector-borne parasites, bacteria and viruses causing 17% of all infectious diseases and over 700,000 human deaths annually. One of the major challenges in studying the discrete mechanisms involved in host-response to hematophagy or the host seeking behavior of hematophagous insects, is the vast amount of signaling processes and genes that are inextricably tied to these interactions. These experiments used the clustered regularly interspersed short palindromic repeat (CRISPR)/CRISPR-associated (Cas) and dsRNA knock-down technologies to examine mechanisms of immunological reactivity and host-seeking behavior. …

Evaluation Of The Utility And Performance Of An Autonomous Surface Vehicle For Mobile Monitoring Of Waterborne Biochemical Agents, Jessica Simmerman Wolfe

Theses and Dissertations

Real-time water quality monitoring is crucial due to land utilization increases which can negatively impact aquatic ecosystems from surface water runoff. Conventional monitoring methodologies are laborious, expensive, and spatio-temporally limited. Autonomous surface vehicles (ASVs), equipped with sensors/instrumentation, serve as mobile sampling stations that reduce labor and enhance data resolution. However, ASV autopilot navigational accuracy is affected by environmental forces (wind, current, and waves) that can alter trajectories of planned paths and negatively affect spatio-temporal resolution of water quality data. This study demonstrated a commercially available solar powered ASV equipped with a multi-sensor payload ability to operate autonomously to accurately and …

Evaluation Of Hyperspectral Band Selection Techniques For Real-Time Applications, Samantha Butler

Theses and Dissertations

Processing hyperspectral image data can be computationally expensive and difficult to employ for real-time applications due to its extensive spatial and spectral information. Further, applications in which computational resources may be limited can be hindered by the volume of data that is common with airborne hyperspectral image data. This paper proposes utilizing band selection to down-select the number of spectral bands to consider for a given classification task such that classification can be done at the edge. Specifically, we consider the following state of the art band selection techniques: Fast Volume-Gradient-based Band Selection (VGBS), Improved Sparse Subspace Clustering (ISSC), Maximum-Variance …

Effects Of Bonding Pressure And Lamina Thickness On Mechanical Properties Of Clt Composed Of Southern Yellow Pine, Cody S. Bates

Theses and Dissertations

This study produced cross-laminated timber panels at a range of four lamina thickness (5/8, 1, 1 1/8, and 1 1/4 inch) and three bonding pressures (50, 125, 200 psi), producing a total of 12 panels for mechanical testing. The goal of this study is to observe how the thickness and pressure trends affect the mechanical properties of CLT. Tests include flatwise bending, flatwise shear, internal-bond, and delamination. Results showed that bending MOE decreases as the panel thickness increases while bonding pressure had no significance. Bending MOR was less significant for the thickness and more significant for pressure compared to the …

Automated Design Of 3d Cad Platforms, William Fernando Quintero Restrepo

Theses and Dissertations

The agile creation of 3D CAD platforms (3D CAD models that can be configured to obtain a family of Products) has become an important factor for increasing competitiveness of organizations that create discrete products. Design Automation (DA) is a powerful tool that can be used for speeding up and optimizing the design process of those 3D CAD platforms. Nonetheless, for effectively applying DA on the development of 3D CAD platforms it is desirable to count on tools that address the three fundamental hurdles that are also obstructing the wide adoption of DA in practice. These hurdles are the lack of …

Leveraging Choice Modeling Technique For Enhancing The Cyber Resilience Of The Smart Grid, Kesava Karishma Devi Dadi

Theses and Dissertations

This research focuses on the cyber-attack of the smart grid and its retrieval to a normal state by estimating the smart grid's resilience. This study developed a theoretical model to estimate the resilience of the smart grid using choice modeling. A utility function is formulated based on various factors and sub-factors of resilience to estimate the resilience of the smart grid. Choice modeling is applied to estimate the model parameters in various fields such as marketing, energy, transportation, and health and to predict the outcome.

Catalytic Light Alkanes Selective Conversion Through Ammonia-Assisted Reforming, Siavash Fadaeerayeni

Theses and Dissertations

The fact that hydrogen is a clean and versatile fuel offers an attractive carbon-free source of energy and leverages the U.S. economy toward long-term sustainable economic growth. At an industrial scale, hydrogen production is mostly relying on methane steam reforming producing stoichiometric amounts of carbon oxides (CO and CO2), which imposes economic and environmental concerns. To mitigate the issue, we propose NH3 assisted anaerobic reforming of natural gas liquids (ethane and propane) as an alternative approach to produce COx free hydrogen. Here, in the first chapter, through comprehensive performance evaluation, characterization, and transient kinetic studies, it is shown that the …

Field Durability Test Of Clt Wall Envelope Using Physical Barriers Against Termites And Structural Performance Of Nailed Hold-Down Brackets Connected To Fungus-Exposed Clt Walls, Kamal Neupane

Theses and Dissertations

The effectiveness of using commercial polyethylene flashing and stainless-steel mesh in CLT wall systems as the termite barriers were evaluated in a short-term field test. American Wood Protection Association (AWPA) E21's visual ratings ranged from 10 to 9 in the specimens showing little damage when no physical barriers were used. Termites were able to crawl beyond the physical barriers in few specimens showing the necessity of further research on height and installation method of physical barriers. On the second part, the effect of decay caused due to Postia placenta, a brown-rot fungus, on the structural performance of hold-down brackets connected …

Evaluation Of The Variable Rate Capabilities Of A Sprayer Equipped With Pulse Width Modulation Nozzle Control And Direct Chemical Injection Systems, William Walker

Theses and Dissertations

Variable-rate technologies coupled with broadcast spray systems serve to reduce chemical inputs, misapplication of chemicals, and environmental pollution, thus improving profitability and sustainability. Sprayer variable rate control involves using pulse width modulation (PWM) solenoids and/or direct chemical injection to adjust the application rate. The objectives of this research were to: outfit a conventional broadcast sprayer with PWM and direct inject technologies; evaluate the accuracy of the PWM system to control application rate for strait line and turn segments; and characterize the direct injection system’s transport delay time. For the PWM evaluation, the mean flow rate and coefficient of variation of …

Design Of Plastic Contaminant Eliminator In Seed Cotton, Joshua H. Tandio

Theses and Dissertations

Plastic contamination in cotton is a problem in cotton industry and researchers have worked on this problem with different approaches. This thesis documents the design of mechanical and electronic real-time systems for detecting and removing plastic contaminants. The mechanical system was designed to expose plastic embedded inside the seed cotton to the sensor and to separate plastic contaminated cotton from the process stream. The detection system consisted of an embedded computer interfaced with a USB camera and Neural Network (NN) software running in it. Two NN models were tested, a transfer learning model and a built-from-scratch original model. The original …

Evaluating The Effects Of Pine And Miscanthus Biochar On Water Activity And Escherichia Coli Populations In Commercial Broiler Litter, Christopher Austin Marty

Theses and Dissertations

The decrease in subtherapeutic antibiotic administration in poultry has increased the need to address production challenges caused by pathogens, such as E. coli. One potential way to improve bird health and reduce bacterial infection is through the addition of litter amendments that absorb moisture. Biochar (BC) has previously been shown to increase water holding capacity in poultry litter, but its effects on E. coli mitigation are unknown. The objectives of this research were to 1) evaluate water activity of poultry litter amended with pine and miscanthus BC, and 2) determine the effects of different BC inclusion rates on litter …

Implementing Food Science-Based Instruction In Career Technical Education Courses, Jasmine D. Hendrix

Theses and Dissertations

Students are exposed to food concepts in agriculture-based career technical education (CTE) courses which provide a gateway for students to become more aware of food science career pathways. Professional development for Mississippi (MS) CTE teachers is needed to effectively implement food science-based instruction since there is not a food science curriculum framework adopted in MS. The objective of this study was to assess a food science professional development training for MS CTE teachers that would increase their self-perceived knowledge of food science, self-perceived ability to conduct food science skills, and their self-efficacy to implement food science-based instruction. Thirty-one teachers participated …

A Longitudinal Analysis Of Pathways To Computing Careers: Defining Broadening Participation In Computing (Bpc) Success With A Rearview Lens, Mercy Jaiyeola

Theses and Dissertations

Efforts to increase the participation of groups historically underrepresented in computing studies, and in the computing workforce, are well documented. It is a national effort with funding from a variety of sources being allocated to research in broadening participation in computing (BPC). Many of the BPC efforts are funded by the National Science Foundation (NSF) but as existing literature shows, the growth in representation of traditionally underrepresented minorities and women is not commensurate to the efforts and resources that have been directed toward this aim.

Instead of attempting to tackle the barriers to increasing representation, this dissertation research tackles the …

Deep Multi-Modal U-Net Fusion Methodology Of Infrared And Ultrasonic Images For Porosity Detection In Additive Manufacturing, Christian E. Zamiela

Theses and Dissertations

We developed a deep fusion methodology of non-destructive (NDT) in-situ infrared and ex- situ ultrasonic images for localization of porosity detection without compromising the integrity of printed components that aims to improve the Laser-based additive manufacturing (LBAM) process. A core challenge with LBAM is that lack of fusion between successive layers of printed metal can lead to porosity and abnormalities in the printed component. We developed a sensor fusion U-Net methodology that fills the gap in fusing in-situ thermal images with ex-situ ultrasonic images by employing a U-Net Convolutional Neural Network (CNN) for feature extraction and two-dimensional object localization. We …

Modeling The Ballistic Limit Of Fragment Simulating Projectiles Impacting A36 Mild Steel Spaced Armor Configurations, Daniel H. Rios-Estremera

Theses and Dissertations

Terminal ballistics study multivariate behavior and aftermath of projectile and target interactions. Tests and models are often based on monolithic armors, however, layered and spaced armors are common in real world applications. Such configurations add complexities that require research to understand their effects on terminal ballistics. The ballistic limit velocity (V50) represents the speed where armor perforation probability is 50%. It is used for quantitative comparison of protection capabilities for different armors. This research studied the V50 of spaced and layered A36 steel armors against fragment simulating projectiles (FSPs). Four methods for estimating armor V50 were evaluated and compared to …

Unmanned Ground Vehicle System To Collect Soil Moisture Data, Austin Edward Flynt

Theses and Dissertations

With an increased interest in precision agriculture, it is important to identify efficient ways to monitor soil moisture. Soil moisture can be monitored using handheld sensors, but this method is laborious and time consuming. Remote methods, such as radar systems can be used as well, but these methods require ground truth data to verify their accuracy. It becomes clear that to collect this data regularly and reliably, a mobile robotic device is necessary. This thesis proposes to implement mobile robot take soil moisture measurements with less human effort than existing methods while maintaining the same accuracy. This soil moisture data …

Methods For Inference And Analysis Of Gene Networks From Rna Sequencing Data, Himangi Srivastava

Theses and Dissertations

RNA (Ribonuceic Acid) sequencing technology is a powerful technology used to give re- searchers essential information about the functionality of genes. The transcriptomic study and downstream analysis highlight the functioning of the genes associated with a specific biological process/treatment. In practice, differentially expressed genes associated with a particular treatment or genotype are subjected to downstream analysis to find some critical set of genes. This critical set of genes/ genes pathways infers the effect of the treatment in a cell or tissue. This disserta- tion describes the multiple stages framework of finding these critical sets of genes using different analysis methodologies …

Development Of A Bioinspired Nugalbot For Precision Seeding Of Rice, Harsa Dhani

Theses and Dissertations

Many people around the world live in islands with mountainous lands. These people plant upland rice for their staple food. However, farming in these disadvantageous farms requires high input and gains low yield. One possible solution for improving productivity is by utilizing precision seeding. This study is focused on developing a robot for precision seeding of rice that is suitable for farming in rough terrain. A bioinspired human arm robot for picking seeds and making a hole on the ground was developed in accordance with Aalborg method for bioinspired design. Development of a mobile platform to carry the robot arm …

Dissection Of The Genetic Architecture Of Grain Quality In Rice, Shuai Liu

Theses and Dissertations

Rice is an important human staple food for over half of the world’s population. Amylose content (AC), gelatinization temperature (GT), grain protein content (GPC), percentage grain chalkiness (PGC), and mineral content are important parameters for evaluating rice quality, which attracts customers and breeders. Only limited genes or QTLs (OsAAP6, OsGluA2, OsASN1, Chalk5, OsHMA3, etc.) are reported regulating rice GPC, PGC, and mineral content due to the lack of genetic knowledge and molecular markers. To dissect the genetic architecture of rice grain quality regulation, genome wide association studies (GWAS) were performed using two populations …

Evaluation Of Alternate Wetting And Drying Irrigation Management In Rice, Richard Lee Atwill Ii

Theses and Dissertations

Water level declines in the Mississippi River Valley Alluvial Aquifer (MRVAA) are attributed largely to withdrawals for rice (Oryza sativa L.) irrigation. This study was performed to determine if alternative irrigation strategies for rice could reduce withdrawal from the MRVAA without having an adverse effect on grain yield, grain quality, control of barnyardgrass, and profitability. Research was conducted in Stoneville, MS and 19 on-farm locations across the Delta region of Mississippi from 2014 through 2017 to determine the irrigation threshold for alternate wetting and drying (AWD) rice irrigation, the effect of AWD management on barnyardgrass control, and effects of …

The Development Of Authentic Virtual Reality Scenarios To Measure Individuals’ Level Of Systems Thinking Skills And Learning Abilities, Vidanelage L. Dayarathna

Theses and Dissertations

This dissertation develops virtual reality modules to capture individuals’ learning abilities and systems thinking skills in dynamic environments. In the first chapter, an immersive queuing theory teaching module is developed using virtual reality technology. The objective of the study is to present systems engineering concepts in a more sophisticated environment and measure students learning abilities. Furthermore, the study explores the performance gaps between male and female students in manufacturing systems concepts. To investigate the gender biases toward the performance of developed VR module, three efficacy measures (simulation sickness questionnaire, systems usability scale, and presence questionnaire) and two effectiveness measures (NASA …

School Transportation Protocol And Procedures Related To Students’ Safety And Discipline: Reflective Experiences Of School Bus Drivers And School Administrators, David Luke

Theses and Dissertations

This dissertation deals with the protocol and procedures related to students’ safety and discipline while on a school bus as experienced by school bus drivers’ and school administrators’ experiences as a guide for changes to the existing programs. The following was the overarching research question that guided the study: How do school bus drivers and school administrators describe their reflective experiences related to bus driver training and protocol and procedures associated with student safety and discipline?

A qualitative research design was selected for the study. A case study approach was used to collect and analyze data for the study.

Participants …

Detecting Malware In Memory With Memory Object Relationships, Demarcus M. Thomas Sr.

Theses and Dissertations

Malware is a growing concern that not only affects large businesses but the basic consumer as well. As a result, there is a need to develop tools that can identify the malicious activities of malware authors. A useful technique to achieve this is memory forensics. Memory forensics is the study of volatile data and its structures in Random Access Memory (RAM). It can be utilized to pinpoint what actions have occurred on a computer system.

This dissertation utilizes memory forensics to extract relationships between objects and supervised machine learning as a novel method for identifying malicious processes in a system …