Digital Commons Network^™

Deep Learning Models For Anomaly Detection In Industrial Inspection, Jiawei Guo

Theses and Dissertations

Anomaly detection plays a pivotal role in ensuring the longevity and safety of engineered systems, particularly in domains where defects can have significant operational or economic consequences. From internal damage in structural parts to subtle visual defects in manufactured components, identifying abnormal patterns requires models that are both computationally efficient and suitable for real-world deployment. This dissertation explores deep learning-based solutions designed to address these challenges, with a focus on Structural Health Monitoring (SHM) and industrial defect inspection under real-world scenarios.

This dissertation first addresses the problem of efficient and reliable component- level perception with limited supervision and strict hardware …

Laser-Based Wideband Guided Ultrasonic Wave Inspection Of Isotropic And Anisotropic Materials, Andrew Philip Campbell

Theses and Dissertations

Non-destructive evaluation (NDE) and structural health monitoring (SHM) have experienced significant growth in both capability and utility as material evaluation and damage detection methods for structural components throughout various industries over the past two decades. Evaluating a structure throughout its life cycle or on demand as needed can identify critical weaknesses that impact safe operation and may prevent failures. Various NDE/SHM methods have been shown to be effective; among them, guided ultrasonic waves (GUW), particularly Lamb wave-based methods, have been intensively studied due to their capability to interrogate internal defects and their relatively larger coverage. With the advancements in new …

Optimizing Auv Perception For Competitive Underwater Robotics: Analyzing Performance And Simplicity Of Machine Vision Hardware, Joseph King

Honors Theses

Underwater robotics is a growing field with many practical applications, such as pipeline and offshore structure monitoring, deep sea mining, mine reconnaissance/removal, and marine environmental monitoring. USM’s Robotics Club will participate in the international RoboSub competition, where student-led teams build autonomous underwater vehicles (AUVs) that perform a variety of tasks within a pool requiring camera-based object detection. This project analyzes affordable hardware and software options for providing machine vision to USM’s future RoboSub AUV. The performance of an ESP32-CAM microcontroller, Raspberry Pi 5, and Jetson Orin Nano single-board computers running FOMO and YOLO object detection models was compared. These models …

Modeling And Autonomous Control Systems For A Delivery Drone Application, Dana Helal Alnuaimi

Theses

This thesis focuses on the development of a multi-drone navigation and control system, aiming to enhance payload capacities beyond the limits of single-drone systems. By integrating multiple drones to work collaboratively as a unit, this study addresses the challenges associated with lifting and transporting heavier payloads.

The primary objective is to design and evaluate a multi-drone system capable of working in tandem to transport larger payloads efficiently. The research aims to develop robust control algorithms, supported by system identification for dynamic modeling, and navigation strategies to enable effective coordination between drones.

The study employs a combination of simulation and real-world …

Development Of A Novel Cfd Approach For Predicting Multiphase Flow Enhanced By Machine Learning, Abdulrahman Elazazi Salem

Theses

Accurate estimation of interface orientation is crucial for ensuring both the accuracy and robustness of Volume of Fluid (VOF) schemes in multiphase flow simulations, especially when using non-uniform Cartesian meshes. Conventional gradient reconstruction approaches, such as least-squares (LSQ) methods, often suffer from significant errors and strong oscillations on highly stretched grids. This work proposes a grid-transferable, learning-based methodology that predicts interface unit normal vectors directly from the local volume-fraction field on nonuniform structured Cartesian grids using a feedforward neural network. The methodology extends earlier work originally developed for uniform grids, which is first reproduced to assess how performance deteriorates in …

Study Of The Effect Of Biodiesel Derived From Jojoba Oil With Alcohols Blends On Diesel Engine Performance, Exhaust Emissions, Vibration, And Noise, Yassir Abdelrahman Elbashier

Theses

This study presents a mutual investigation on the properties of the fuels and the performance of an engine using biofuels from mixtures of jojoba oil biodiesel with alcohols. The work consists of mainly two phases, examining the properties of the jojoba biodiesel-alcohols mixtures and the performance and emission behavior in a single piston diesel engine. A base mixture of 50% jojoba biodiesel and 50% diesel produced, and this was fractionally mixed with 5, 10, and 20% methanol and with 5, 10, and 20% diethyl ether (DEE). The rheological properties namely viscosity and shear stresses of all biodiesel blend mixtures were …

Ellie - Exteroceptive Light Locomotion In Eukaryote-Fungi, Brandon Etwarroo

Doctoral Dissertations and Master's Theses

Over the past decade, fungal research and its technological applications have expanded across multiple disciplines, including the emerging field of biohybrid systems. This thesis develops and evaluates a wireless, untethered mobile robot controlled by the action potential-like activity generated by Pleurotus ostreatus sporocarps under red, green, and blue optical stimulation. Light is applied to the sporocarps, the resulting electrical responses are recorded, and these signals are transmitted wirelessly to actuate the mobile robot. Both the action potential-like activity patterns and the robot’s movement trajectories were analyzed. The results demonstrate that wireless robotic control mediated by fungal electrophysiology is feasible. Overall, …

Effect Of Nozzle Pressure Ratio On Thrust And Flow Behavior In A Supersonic De Laval Nozzle, Esha Jain

Doctoral Dissertations and Master's Theses

Supersonic nozzles operate across a range of flow regimes. While an ideally expanded condition yields optimal thrust, practical propulsion systems rarely operate at this design point due to variations in altitude and engine operating conditions. As a result, nozzles frequently operate in off-design conditions. In overexpanded regime, where the exit pressure is lower than the ambient pressure, shock-induced separation may occur within the divergent section of the nozzle, potentially degrading nozzle performance. Understanding the aerodynamic behavior of nozzles operating under off-design conditions is therefore important for improving propulsion system performance and stability. In particular, direct thrust measurements provide a key …

Cavitation-Aware Design Of Hydrofoil Sections For Marine Propeller Blade Development, Samuel G. Bacon

Mechanical & Aerospace Engineering Theses & Dissertations

Cavitation is a major design constraint for marine propeller blade sections because it can reduce hydrodynamic performance, increase vibration and noise, and contribute to surface damage. This thesis develops and applies an exploratory computational framework for cavitation-aware hydrofoil-section design relevant to marine propeller blade development. The framework combines section-level CFD validation, CST-based geometry parameterization, pressure-based pre-screening, matched-load comparison, and focused predicted inception envelope or cavitation-bucket analysis.

The CFD methodology was validated against published YS-920 hydrofoil water-tunnel data using selected fully wetted, near-inception, and cavitating reference cases. The validation results showed that the adopted framework reproduced the key experimental trends needed …

Ultra-High Vacuum Outgassing Characterization Of Thermally Processed Low-Carbon Steel For Advanced Particle Accelerator And Gravitational Wave Detector Applications, Aiman H. Al-Allaq

Mechanical & Aerospace Engineering Theses & Dissertations

This dissertation investigated AISI 1020 low-carbon steel as an alternative vacuum chamber material to conventional stainless steel for ultra-high vacuum (UHV) and extreme-high vacuum (XHV) applications. After a 400 °C/48 h bake, AISI 1020 tube chambers achieved a hydrogen outgassing rate of 2.4 × 10⁻¹⁶ Torr·L·s⁻¹·cm⁻², approximately 2,300 times lower than the prebaked 316L stainless-steel comparator, among the lowest hydrogen outgassing rates ever reported for an uncoated metallic vacuum chamber. Bare and magnetite-coated AISI 1020 chambers were then compared using throughput and rate-of-rise methods. The magnetite coating yielded 5× lower water outgassing at room temperature, but this advantage disappeared after …

Sweep Angle Effects Of Flow Over A Seal Whisker-Inspired Undulated Cylinder, Trevor Dunt, Christin T. Murphy, Ondrej Fercak, Raúl Bayoán Cal, Jennifer A. Franck

Mechanical and Materials Engineering Faculty Publications and Presentations

Flow over a seal whisker-inspired undulated cylinder at swept back angles is computationally investigated, comparing the vortex shedding, forces, and wake characteristics to those of an equivalent smooth geometry. Numerous prior studies have demonstrated that undulated cylinders can reduce mean drag and unsteady lift oscillations; however, none have isolated the effects of the sweep angle resulting from whisker positioning in flow. Inspired by the active control seals exert over their whiskers while navigating and sensing in unsteady aquatic environments, this study investigates how such orientation influences the hydrodynamic performance of the geometry. Simulations are performed of flow across a rigid, …

Wearable Sensor System Used To Measure Linear And Angular Acceleration Of The Head Of American Football Players, David A. Emerson

LSU Master's Theses

American football players are repeatedly subject to high-velocity impacts; collisions can exceed 100 g in the NFL [1]. Rotational accelerations of the head caused by high-velocity collisions have been proven to be extremely damaging to the highly organized brain fibers at the brain-skull interface [2]. The sensor system (SS) measures the nonplanar acceleration at four locations on a chin strap using ADXL314 accelerometers and utilizes rigid-body kinematics to estimate the head rotational state from the measured acceleration of the SS [3]. The SS was validated through progressive testing, including steady-state, linear impact, and rotational impact testing. The ADLX314 sensor exhibited …

Deep Learning Based Control System For Multi-Zone Hvac Residential Buildings, Mohammad H. Z. Alghalayeeni

Mechanical Engineering Theses

Heating, ventilation, and air conditioning (HVAC) systems are major contributors to residential energy consumption. However, most homes continue to rely on single zone thermostat control, which regulates temperature based on a single sensor and cannot account for thermal variations across multiple rooms. This often leads to uneven thermal conditions and inefficient energy use in multi-zone residential buildings. This thesis presents a deep reinforcement learning based approach for improving HVAC zoning control through dynamic airflow distribution. A physics based multi zone thermal model of a residential house was developed to simulate heat transfer processes including conduction, convection, solar and internal heat …

Mould Risk Prevention In Healthcare Facilities In Hot And Humid Climates Through Acmv Air Supply Parameter Optimisation: Development And Validation Of A Multi-Objective Optimisation Framework, Jiang Kaiyun

Student Works (2020-2029)

Air conditioning mechanical ventilation (ACMV) supply parameters—such as airflow rate, temperature, and humidity—significantly influence indoor thermal and hygrometric conditions, influencing airflow patterns and mould proliferation. In healthcare facilities, mould poses significant health risks, particularly for immunocompromised patients, contributing to respiratory issues, allergic reactions, and infections. While ACMV systems are central to infection control and indoor air quality, conventional designs often fall short in hot and humid climates. Existing practices typically prioritise high air change rates (ACH) without sufficient dehumidification, underestimate humidity control, and assume spatial homogeneity, overlooking microclimates conducive to localised mould growth. To address these limitations, this research develops …

Marine Vehicle Dynamics Using Koopman Operator Theory With Hybrid Observables, Mikhalib A L Green

LSU Master's Theses

Accurate modeling of marine vehicle dynamics remains challenging due to strong nonlinear hydrodynamic effects, environmental disturbances, and sensitivity to configuration changes, particularly for small-scale platforms. Classical physics-based models require extensive parameter identification and often exhibit degraded performance outside narrow operating regimes, while purely data-driven approaches may lack structure or impose high computational cost. This thesis presents a data-driven Koopman operator framework with hybrid observables for modeling the dynamics of unmanned marine vehicles. The proposed approach combines structured monomial observables with a learned neural network embedding to construct a lifted state representation in which the nonlinear vehicle dynamics are approximated by …

Mechanical, Thermal And Fire Behaviour Of Hemp-Based Composites With Different Binders For Sustainable Building Applications, Anilcan Aygun, Fahri Birinci, Selim Aytac, Ali Kemal Ayan, Hasan Alp Sahin, Ibrahim Isildak

Journal of Sustainable Construction Materials and Technologies

This study investigates the physical, mechanical and thermal properties of hemp-based composites produced with traditional binders such as lime, cement, gypsum, clay, and water-based glue. Hemp fractions of different sizes (splinter, shiv, fiber and powder) were combined with these binders to manufacture cube and plate specimens, which were tested for physical, mechanical, thermal, and temperature resistance properties. The study aims to compare the mechanical, physical, thermal, and fire behaviour of these composites to assess their suitability for sustainable construction applications. The hemp-based composites were tested for unit weight, water absorption, compressive strength and thermal conductivity. Most specimens are lightweight (<1000 kg/m3), and exhibit good thermal insulation performance and high compressive deformability, making them suitable for seismic-prone regions. The glue-based composite had the lowest unit weight, measured as 330 kg/m3. Thermal conductivity ranged from 0.051 to 0.243 W/m· K, with several mixtures performing better than natural pumice. While cement-based composites showed the highest compressive strength, ranging from 5.5 to 24.8 kg/cm2, natural hydraulic lime is the lowest. Water absorption was high, and moisture release occurred slowly across all hemp fractions. Combustion tests indicated that hemp-based materials have moderate temperature resistance, with charring temperatures ranging from 238–265°C for raw hemp and 300–385°C when mixed with binders. Overall, hemp-based composites are lightweight, eco-friendly, and suitable for non-load-bearing construction and insulation applications. However, improvements in moisture resistance and long-term durability are necessary to enhance their practical applicability.

Sustainable Cement-Blast Furnace Slag Mortar, Richa Jain, Harshit Jain, Ashish Nim

Journal of Sustainable Construction Materials and Technologies

New building materials that required and produced less energy are need of today's infrastructure development. The ability of such building materials to promote sustainable development always puts its demand in active mode. With huge consumption of naturally occurring materials in building construction, the problem related to environment degradation is now common for world. Along with this, world is also facing the problem of reuse, recover and scientifically approved disposal of non-biodegradable wastes. Blast furnace slag (BFS) is one of those steel industry wastes that are abundantly available and their disposal arises as prime challenge for industries. This research work makes …

Identification Of Thruster Faults In Underwater Vehicles By Using Custom Encodings In Spiking Neural Networks, Donovan Gegg

LSU Master's Theses

Autonomous Underwater Vehicles (AUVs) are untethered robotic platforms used for tasks such as seafloor mapping, infrastructure inspection, and environmental monitoring. Recent technological advances have produced smaller, more affordable platforms, broadening access to research teams and small companies alike. This miniaturization comes at the cost of them handling drawbacks associated with a more compact machine such as reduced battery capacity as well as limited processing and sensing capabilities. These constraints make small-sized marine vehicle’s reliability critical as they can cause malfunctions, making the loss of a vehicle more likely. Actuator faults are particularly consequential as unintended and unstable control in an …

Task-Based Analysis Of Augmented Reality In Collaborative Robotic Programming For Manufacturing Assembly, Medhavi Kamran, Snehesh Shrestha, Vinh Nguyen

Michigan Tech Publications

Augmented Reality (AR) is often promoted as a solution to the cognitive and physical demands of traditional Teach Pendant (TP) programming for collaborative robots. Although prior work has suggested advantages of the AR interface, many evaluations have been limited in scope and may not fully represent the complexities of real-world manufacturing tasks. This study compares the performance of an AR interface to that of a standard TP interface for manufacturing assembly tasks of varying difficulty. In a between-groups study, one group of operators completed standardized assembly tasks using the TP interface, while a separate group used the AR interface instead. …

Layer-Wise Printing Parameter Optimization For Laser Powder Bed Fusion, Chaoran Dou, Rongxuan Wang, Raghav Gnanasambandam, Jianzhi Li, Zhenyu James Kong

Manufacturing & Industrial Engineering Faculty Publications

Additive manufacturing (AM) is a transformative technology that enables the fabrication of complex geometries layer by layer. However, metal parts produced via AM processes such as laser powder bed fusion (LPBF) are prone to various defects, including porosity and deformation. These defects often result from suboptimal printing parameter settings. Traditional approaches typically aim to reduce defects by optimizing a fixed set of parameters for the entire part. However, such methods do not account for layer-wise variations in printing conditions caused by changes in geometry, heat transfer, and re-heating effects. While optimizing parameters for each layer could improve part quality, it …

Impact Of Glass Powder As A Sustainable Material On The Workability, Strength, And Durability Properties In High-Performance Basalt Fiber Reinforced Concrete: A Statistical Analysis, Ahmed Fathi Mohamed Salih

Journal of Sustainable Construction Materials and Technologies

The global construction sector is increasingly challenged to balance environmental sustainability with the growing demand for durable, high-performance materials. As cement production continues to be a major source of anthropogenic CO2 emissions, the incorporation of alternative, low-impact binders has become a key strategy for reducing the environmental footprint of concrete. In this context, glass powder (GP)—a finely ground industrial by-product rich in amorphous silica—has emerged as a promising partial replacement for Portland cement. Its pozzolanic reactivity contributes to improved hydration and matrix densification, while its use also supports circular economy principles by diverting waste glass from landfills. At the same …

Roadmap: Integrating Artificial Intelligence In Structural Health Monitoring Systems, Simon Laflamme, Erik Blasch, Flippo Ubertini, Zheng Liu, John Wertz, Christine Knott, Matthew Cherry, Eric Lindgren, Fu-Kuo Chang, Amrita Kumar, Jack Poole, Keith Worden, Austin Downey, Jie Wei, Patrick F. Musgrave, Adrian S. Wong, Guiseppe Quaranta, Marco Martino Rosso, Giuseppe Carlo Marano, Yu Chen, Et. Al.

Faculty Publications

Advances in computing and machine learning (ML) methods have led to a rapid rise in artificial intelligence (AI) research and applications in many fields. AI research benefitted from advances in computation hardware, collection and distribution of large data sets, and proliferation of software techniques. AI techniques include ML for provable results, deep learning for data exploration, reinforcement learning for control, and active learning for adaptive systems. Likewise, AI algorithms can handle large amounts of data, construct unknown representations, and provide a direct link between data and classification for decision making. These unmatched capabilities have been seen as a path to …

An Ambient Acoustic Ice-Fracturing Dataset Taken In Shallow Freshwater, John Case, Andrew Barnard, Daniel Brown

Michigan Tech Publications

This paper describes an acoustic dataset collected on a frozen shallow freshwater lake between February and March of 2024. This collection took place over one full week on Portage Lake in the Upper Peninsula of Michigan, USA. The first sub-dataset consists of ambient ice and environmental noises collected by an array of hydrophones, microphones and geophones placed below, above and on the ice respectively. The second sub-dataset consists of instrumented force hammer impacts at a series of locations on the the ice with the corresponding response at each acoustic sensor. All acoustic data were recorded at a sample rate f …

Lightweight And Resilient Cryptographic Protocols For Next-Generation Networking Systems, Saif Eddine Nouma

USF Tampa Graduate Theses and Dissertations

The security of our increasingly interconnected world is strongly dependent on the strength and practicality of the cryptographic tools we deploy. As billions of embedded devices join the Internet of Things (IoT) and interact with remote cloud infrastructures for data processing, analysis, and actuation, they evolve into so-called digital twins. This rapid expansion introduces numerous attack vectors, particularly targeting constrained IoT devices, which greatly increase the attack surface and often become the root cause of large-scale infrastructure compromises. At the same time, the rise of quantum computing threatens the hardness of today’s intractability assumptions that underpin cryptographic primitives currently deployed. …

Decentralized Q-Learning Supervisory Control For Coordinated Multi-Loop Tuning In Pump Stations, David Brattley, Wayne Weaver

Michigan Tech Publications

This paper introduces a reinforced learning-based supervisory control architecture that oversees multiple Recursive Least Squares (RLS) based self-tuning pump controllers and determines when each loop is permitted to adapt its gains. The supervisor learns adaptation policies that minimize interaction between loops while preserving responsiveness to changing hydraulic conditions. A two-loop pump station simulation is used to evaluate performance under product changes and transient flow disturbances. The results show that the supervisory layer reduces the number of simultaneous adaptation events by over 70%, leading to a 32% lower pressure-tracking error and 45% fewer gain-induced oscillations compared to conventional independent adaptive control. …

Supporting Data For Novel Approach For Quantifying The Impact Of Coherent Structures On The Turbulent Kinetic Energy Decay Rate, Tim Berk, Ankit Gautam

Browse all Datasets

This project investigates the influence of coherent structures on the decay of turbulent kinetic energy (TKE). The work was conducted as part of the PhD research in Mechanical Engineering by Ankit Gautam at Utah State University.

Multimodal Thermal And Mechanical Characterization Of Cryopreservation Effects In Biological Cells, Subhrajyoti Sourav Kumar Kundu

LSU Master's Theses

Cryopreservation is critical for long-term storage of cells, tissues, organs, and reproductive cells in medicine, biotechnology, and conservation. However, its success is limited by ice formation and cryoinjury, prompting extensive research into analytical tools for understanding and improving cryopreservation outcomes. We outline the principles of each technique and how they are used to detect key thermal and physical events such as ice nucleation, vitrification, devitrification, and cryoinjury. DSC enables quantitative thermal characterization including critical cooling/warming rates (ranging from 1-200°C/min for various systems) and glass transition temperatures. Cryomicroscopy provides direct real time visualization of ice crystal dynamics, distinguishing intracellular versus extracellular …

Thermal Management And Lubrication Characteristics Of Tungsten Disulfide (Ws2) Vegetable-Based Nanolubricants, Jaime Taha-Tijerina, Dyana De Leon-Elizondo, Jade Mendieta, Leonardo Taha-Soto

Informatics and Engineering Systems Faculty Publications

Recent innovations with the aid of nanotechnology are more frequently seen in the industrial sectors. Lubricants are a high-end commodity resource used in many manufacturing processes; unfortunately, most of these lubricants are petroleum-based, which come with certain drawbacks, such as environmental aspects, handling issues and high costs. With the incorporation of nanostructures within fluids and lubricants, novel material alternatives are replacing conventional lubrication systems, maintaining the required thermophysical and tribological characteristics. This research provides an analysis of vegetable lubricant, castor oil (CO), and the effects of the incorporation of WS2 nanofiller at diverse filler fractions. A TEMPOS thermal analyzer device …

Acoustic Levitation At Sub-Atmospheric Pressures And Reduced Temperatures: An Approach To Study Ice Crystal And Hypersonic Shockwave Interaction, Imteaz Osmani, David J. Delene, Hallie Boyer Chelmo

Graduate Research Achievement Day Posters

Micrometer-sized atmospheric ice crystals are commonly observed in high-altitude clouds. Inside clouds, they attach in different orientations, producing varied geometries, yet their formation mechanisms remain poorly understood. Their behavior under shock wave conditions remains underexplored due to lack of laboratory techniques capable of producing atmospherically realistic ice in controlled conditions. No experimental data and laboratory techniques exist to date on the interaction between atmospheric ice crystal aggregates and hypersonic shockwaves. To explore realistic atmospheric ice crystals’ thermodynamic and mechanical changes in hypersonic environments, we investigate the formation and behavior of ice crystal aggregates using acoustic levitation that avoids physical contact …

Influence Of Pulse Width On Energy Deposition And Temperature In Nanosecond-Pulsed Discharges, Christopher B. Reuter, Joshua B. Sinrud, Tanvir I. Farouk, Nicholas S. Dewey, Dmitri Kaganovich

Faculty Publications

Nanosecond-pulsed discharges are a promising method to enhance combustion but can generate significant levels of electromagnetic interference (EMI). Modifying the discharge pulse width is an unexplored option to reduce EMI, but few studies have examined how changing the pulse width affects discharge parameters such as energy and temperature. This study addresses this issue by systematically investigating how the pulse width affects the energy per pulse, breakdown time, rotational temperature, and vibrational temperature in air across different frequencies, flow velocities, and gap distances in a plasma-assisted flow tube. It is observed that the pulse width has a substantial impact on the …