Operations Research, Systems Engineering and Industrial Engineering Commons^™

Data Lakehouse And Machine Learning Pipeline For Aircraft Fuel Efficiency Experimentation, Skyler G. Kepley

Theses and Dissertations

Fuel efficiency is crucial for the U.S. Air Force, impacting mission success, aircraft performance, and cost savings. This study presents an information system that integrates flight and maintenance data using a data lakehouse. It automates ingestion, enrichment, and predictive modeling, leveraging AutoML for optimization and SHAP for transparency. A case study on C-130J aircraft shows that optimizing D Check cycles can save 11.52 pounds of fuel per flight hour. These findings highlight the effectiveness of data-driven decision-making in aviation, offering a scalable, automated solution for improving fuel efficiency and reducing costs.

Machine Learning With Flight Data Recorder Data For Flight Fuel Consumption Predictions, Adam C. Levandowski

Theses and Dissertations

This study applies advanced Machine Learning (ML) to Flight Data Recorder (FDR) data for fuel consumption predictions. It explores feature engineering, model selection, and Hyper-Parameter Optimization (HPO) across all flight phases. Baseline models like Ordinary Least Squares (OLS) regression, Multi- Layer Perceptrons (MLPs), and decision trees are compared to Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs) with Gated Recurrent Unit (GRU) layers, and XGBoost. Results analyze segmentation strategies, tailored features, and model performance. A counterfactual analysis compares ML models to operational fuel predictions, demonstrating their deployment potential. Findings establish a foundation for future ML-driven advancements in aviation fuel optimization.

Island Nation Duress: Simulating Passive Peer-To-Peer Bluetooth Communication During Disaster Relief, Jason K. Medeiros

Theses and Dissertations

Pacific Islands under U.S. jurisdiction are highly vulnerable to natural disasters, yet many lack the infrastructure to effectively respond and recover. Clear communication during and after such events is critical for evacuation, hazard awareness, and first responders’ coordination. This research explores a simulation-based approach using Bluetooth communication to relay messages across Guam, assessing its efficiency through statistical analysis. By examining regional differences and geographic impacts on Bluetooth messaging, the study aims to identify key factors that enhance peer-to-peer communication for timely and effective disaster response.

Real-Time Decision-Making During Maritime Chokepoint Disruption Using Digital Twin, Jared M. Orendorff

Theses and Dissertations

This research develops a digital twin of the global maritime shipping system to model disruptions in major shipping lanes like the Suez and Panama Canals. By incorporating live ship-tracking data, the model simulates closures, forecasts queue lengths, and determines the best rerouting options. Findings show that canal closures cause large traffic backlogs and increased congestion at alternative chokepoints, while rerouted ships may face higher piracy risks in regions like the Gulf of Guinea and the Strait of Malacca. This tool helps decision-makers respond effectively to maritime disruptions.

Utility Of Self-Sensing Damage Technology Through A2/Ad Drone Combat Simulation, Sidhanth Venkatasubramaniam

Theses and Dissertations

Since the introduction of the first unmanned aerial vehicle (UAV), UAVs have consistently improved in capability and versatility. The ability to perform military operations without the risk of losing human life is crucial for the United States military. The trade-off for this versatility is cost, and several ongoing research efforts are being made to improve UAV mission success and the lifespan of UAVs. An area of research that falls under the categories mentioned is self-damage detection. The Air Force Research Laboratories (AFRL) are developing a capability to enable a UAV to assess airframe damage, enabling real-time determination of damage potentially …

Improving Zero Shot Learning By Linking Multi-Label Cnns With Llms, Michael A. Wegner

Theses and Dissertations

Classifying previously unseen objects poses a significant challenge for traditional computer vision algorithms, which rely on extensive labeled training data. Zero-shot reasoning offers a way to overcome this limitation. This research explores a novel method for image recognition using the Animals with Attributes 2 (AWA2) dataset as a proof of concept. A multi-label ResNet50 model predicts core attributes like color, ear shape, or number of limbs. Those attributes then feed into ChatGPT which leverages its extensive knowledge base to classify the animal based on the provided attributes. This novel approach skips the need to train on every possible class. Instead, …

Analysis Of An Army Recruiter Allocation Model (Ram), Erik J. Wittendorf

Theses and Dissertations

The United States Army Recruiting Command’s mission to recruit America’s best and brightest volunteers that can deploy, fight, and win requires an effective distribution of its recruiting force to serve as local community ambassadors. This research analyzes an Army recruiter allocation model (RAM) and assesses its underlying assumptions, objective function, and constraints. A detailed study of relative market potential and production rates for up to 1,319 Army recruiting stations and 18,789 ZIP codes enables RAM modification recommendations leveraging evolving recruiting concepts and identifies areas of future work to continue improving the Army’s understanding of the recruiting environment.

An Analysis Of Development Phase Nre/Rec Costs In Dod Acquisition Efforts, Jason Aristizabal

Theses and Dissertations

Estimating Nonrecurring Engineering (NRE) and Recurring Engineering (REC) costs in defense acquisition programs remains challenging, especially in development. While production costs are studied, NRE/REC ratios in development receive little attention. This study analyzes NRE/REC ratios across WBS elements, commodity types, and time periods using defense program data. Results show significant variability, challenging the assumed 1:1 ratio. System Level, PME, and ST&E elements follow distinct trends, highlighting shifting cost structures. These findings stress the need for adaptive methodologies, enabling cost analysts to refine estimates based on historical trends and program-specific factors for improved resource planning.

Accuracy Of Time Phasing Missile And Munition Using The Continuous Distribution Function, Joseph Zobler

Theses and Dissertations

Accurate cost and schedule estimates are crucial for maintaining the U.S. military’s technological and operational superiority, ensuring efficient resource allocation and timely development of advanced defense systems. This research examines S-curve models for time-phasing non-recurring Research, Development, Test, and Evaluation (RDT&E) expenditures in missile and munition acquisition programs. This research evaluates the commonly used 60/40 rule, which assumes 60% of expenditures occur by 50% of the schedule, for its accuracy using Cost Assessment Data Enterprise (CADE) and Earned Value Management Central Repository (EVM-CR) data from 21 missile and munition development programs.

Cognitive Warfare In The South China Sea: Analyzing Media Influence And Public Opinion In Taiwan, Wyatt F. Blatti

Theses and Dissertations

In a time where conflict extends beyond traditional battlefields, cognitive warfare emerges as a powerful tool to influence perceptions and gain strategic advantages. This study investigates China’s cognitive warfare strategies against Taiwan through trend analysis, topic modeling, and sentiment analysis of news media articles from March 2013 to August 2024 to uncover evolving techniques and mitigation efforts. The findings highlight the potential for tracking cognitive campaigns overtime but will require more than news media alone and suggests future research to better understand indicators of cognitive warfare.

Reinforcement Learning For Aeromedical Evacuation In Nonstationary Combat Environments, Micah J. Kartchner

Theses and Dissertations

This research formulates the medical evacuation (MEDEVAC) dispatching problem as a sequential decision process and investigates the application of reinforcement learning under nonstationary conditions. We model the dynamic arrival rate of MEDEVAC requests using a nonstationary Hawkes process and design a Double Deep Q-Network algorithm that incorporates belief states to anticipate future requests. Through computational experimentation, we analyze the impact of belief formulation on decision quality and system performance. Results indicate that policies incorporating belief states significantly outperform myopic dispatching policies, reducing urgent casualty wait times by up to 49.68% and increasing on-time evacuations by up to 21.91%.

An Agent-Based Modeling Framework For Evaluating The Linkage Between Disaster Facility Damage And Mental Health, Emily S. Reeves

Theses and Dissertations

This research establishes a novel agent-based modeling framework to establish the linkage between disaster-induced facility damage and mental health outcomes and the evaluation of treatment methods within the civilian and USAF mental health spheres. The study models the degradation and recovery of agent mental health using simulated data and evaluates the efficacy of three distinct treatment approaches through statistical methods. The methodology integrate agent-based modeling with resilient engineering concepts to simulate mental health resilience curves based on vulnerability, exposure, and facility damage. Agents’ mental health indices were tracked through phases of degradation, stagnation, and recovery based on the three treatments …

Understanding The Acceptance Of Digital Tools Within An Air Force Environment Using The Utaut2 Model, Britton J. Edwards

Theses and Dissertations

This research paper explores factors influencing digital tool adoption in a military context, using a modified UTAUT2 model with the inclusion of Military Status as a moderating factor. The study examines the moderating effects of Military Status on Social Influence towards Behavioral Intention and Behavioral Intention on Use Behavior. Data was collected through a Likert-scale survey from respondents across multiple Department of the Air Force (DAF) organizations. Findings revealed Social Influence had the potential to positively influence Behavioral Intention to use digital tools, but military experience did not significantly moderate this relationship. However, past experience with the legacy tool and …

Performing Requirements Specification And Analysis Through Open Generative Pre-Trained Transformers, Harvey J. Hurst

Theses and Dissertations

Every acquisition program begins with a requirement, and for those programs to succeed, robust requirements engineering (RE) must be implemented. RE encompasses eliciting, analyzing, specifying, and validating requirements—a critical process throughout a program's lifecycle. Despite its importance, RE faces challenges such as scope creep, ambiguity, redundancy, and inadequate automation support, often exacerbated by reliance on historical data. To address these issues, this thesis leverages advancements in Generative Technology, particularly large language models (LLMs) such as Generative Pre-Trained Transformers (GPTs). This research developed two GPT-based tools: the Single Requirement Analysis Tool and the Set of Requirements Analysis Tool. These tools were …

Model-Based Approach To Support Safety Driven Design And Satisfy Mil-Std-882e Requirements With Stpa Coordination: A Case History In Suas Defense Acquisition, Daniel A. Shea

Theses and Dissertations

Increasingly complex defense systems that are routinely overbudget and behind schedule are driving digital engineering initiatives in the defense acquisition industry. MBSE offers a solution to counter this issue but the lack of guidance on how to implement it has led to significant experimentation. One MBSE area of interest is system safety. This research demonstrates how to conduct model-based Systems Theoretic Process Analysis (STPA) to meet the unique system safety process requirements from MIL-STD882E. Based in systems theory, STPA extended for coordination enables a safety-driven design process of complex systems. This research investigated conducting STPA in the SysML-RAAML modeling language …

A Reinforcement Learning Approach For Maneuvering And Firing Decisions In Sead Operations, Nathaniel Garcia

Theses and Dissertations

The integration of automated processes in defense continues to expand, enhancing the lethality of military forces. Artificial intelligence accelerates decision-making cycles, removes the constraints of human-operated hardware, and improves coordination by enabling seamless integration across multiple systems. Suppression of Enemy Air Defenses (SEAD) missions are critical to the United States (U.S.) military, as they neutralize hostile air defense systems, ensuring air superiority and enabling safe and effective operations for aircraft in contested environments. Therefore, it is necessary to pair emerging autonomous capabilities with an important mission set in defense. This research investigates the Autonomous Unmanned Air-to-Ground Strike (AUAGS) problem, modeling …

Symbology Detection And Numerical Recognition For T-38 Heads-Up Display Recordings, Ben T. Hepner

Theses and Dissertations

The extraction of symbology and numerical data from the T-38 Heads-Up Display (HUD) enhances post-flight analysis and supports real-time decision-making. This research develops a deep learning pipeline using YOLO-based object detection and Optical Character Recognition (OCR) to analyze HUD video data. Model evaluations showed mAP0.5:0.95 ranging from 0.422 (YOLOv11m, hard test set) to 0.696 (YOLOv8m, medium test set), demonstrating robust symbology detection. Numeric detection performed well (mAP_0.5:0.95 = 0.764), but OCR struggled with glare and resolution limitations, achieving a recognition accuracy of 17.35%. These results validate deep learning for HUD data extraction but highlight the need for improved robustness …

Evaluating The Performance Of Conformal Prediction Generated Uncertainty Sets In Robust Optimization, Zion C. Johnson

Theses and Dissertations

Uncertainty is a major challenge in optimization, especially in problems where unpredictable costs impact decision-making. Robust optimization addresses this by modeling uncertainty via uncertainty sets. These sets are then used such that solutions hold under worst-case scenarios, with success depending on the accuracy of the uncertainty sets. This research examines the use of conformal prediction to construct uncertainty sets for RO, an approach that has not been widely explored. We test split and full conformal prediction in a robust optimization minimum cost flow problem, and comparing them to interval-based and normal-based ellipsoidal uncertainty sets. Experiments run across different network structures …

Proximal Policy Optimization Applied To The Beyond Visual Range Air Combat Maneuvering Problem, Daniel B. Joseph

Theses and Dissertations

Artificial intelligence (AI) grows ever-more important in warfighting. Emerging technologies allow for the use of AI to control aircraft and weapons systems. This research investigates the application of reinforcement learning (RL) through the Proximal Policy Optimization (PPO) algorithm to a two-versus-two (2v2) beyond-visual-range (BVR) air combat maneuvering problem (ACMP). Implemented in the Advanced Framework for Simulation, Integration, and Modeling (AFSIM), the methodology frames the engagement as a Markov decision process, wherein an autonomous RL agent learns continuous control decisions—throttle, pitch, roll, and yaw—under a cooperative communication scheme. A multi-phase curriculum-learning approach facilitates the progressive acquisition of flight stability, weapon deployment, …

Learning To Dogfight: Proximal Policy Optimization Vs. Double Deep Q Network For 2v2 Air Combat With Directed Energy Weapons In Afsim, Caden W. Wilson

Theses and Dissertations

This research utilizes reinforcement learning (RL) to train two blue agents each imbued with a directed energy weapon (DEW) in a 2v2 within visual range air combat maneuvering problem. A phased solution approach is employed to repeatedly tune and train several RL algorithm implementations: Proximal Policy Optimization (PPO) and Double Deep Q Network (DDQN). Phase I of training includes reward shaping for basic flight elements such as altitude, airspeed, and target proximity. Phase II of training builds off policies developed in Phase I, but rewards emphasize winning the aerial engagement by any means necessary. DDQN significantly outperforms PPO in Phase …

An Analysis Of Hardware Modification Cost: A Test Of A 1:1 Ratio Heuristic, Oluwasegun Faleye

Theses and Dissertations

Accurate cost estimation for Department of Defense (DoD) hardware modification programs remains a critical challenge due to the complexity of Group A and Group B modifications and their associated installation costs. This study evaluates the validity of a 1:1 ratio heuristic, which suggests that Group A modification kits combined with installation costs should equate to the costs of Group B modification kits. This study analyzes cost relationships across system types and modification categories using a dataset of 255 modification programs from the Air Force Life Cycle Management Center (AFLCMC). Statistical methods, including means tables and regression modeling, evaluate the validity …

Cloud One Migration Duration And Its Drivers, Grayson T. Hall

Theses and Dissertations

As modern warfare evolves with rapid technological advancements, cloud computing plays a critical role in managing the vast amounts of data required for real-time decision making, as well as enabling seamless organizational access to mission-critical programs and information from around the globe. Recognizing its importance, the Department of Defense (DoD) identified cloud computing as essential for maintaining the military’s technological edge. However, despite cloud computing’s strategic significance, the DoD faces challenges in successfully implementing department-wide cloud computing. In contrast, the Air Force’s cloud computing environment, Cloud One, is fully operational and has already integrated over 145 systems into its platform. …

Using Mbse To Facilitate Integration And Stakeholder Support For Autonomous Aerial Refueling Flight Test, Kevin G. Keth

Theses and Dissertations

he Department of Defense has pushed to implement Digital Material Management, to include Engineering (DE) and Model-Based Systems Engineering (MBSE) into acquisition processes, publishing various supporting documents such as the Systems Engineering Guidebook, DoDI 5000.97 Digital Engineering, and DoD Reference Architecture Description. DE and MBSE aims to establish a digital authoritative source of truth accessible to all stakeholders responsible for system architecture. However, within multidisciplinary teams, individuals often come from diverse professional backgrounds unrelated to DE and systems engineering, making it challenging to fully leverage the benefits of the digital model. This paper describes an MBSE model that adopts a …

Safety-Driven Concept Development Using System Theoretic Process Analysis Extended For Coordination In A Model Based Environment: A Case Study On Autonomous Satellite Teaming, Taylor L. Matarazzo

Theses and Dissertations

Rigorous system safety analysis methods, allow programs to identify potential problems helping to minimize their impact to program schedules and budgets. In the contested, congested, and competitive space environment, coordination within and between systems is critical to mission success. System Theoretic Process Analysis extended for Coordination (STPA-coord) can prescriptively analyze these coordination interactions. STPA-coord shifts the conversation of system safety from elements ofreliability to elements of control, providing insights that holistically analyze the system. As studies suggest, decisions made early in a systems design determine 80-86% of a programs final cost, therefore integrating system safety as early into design can …

Weighed And Measured: Toward An Evaluation Method For Digital Models In Source Selection, Liam N. O'Neill

Theses and Dissertations

Inspired by a recent model-based source selection conducted by the Advanced Range Threat System (ARTS) Program Office at Hill AFB, this research effort explored the development of new tools the DoD could use when evaluating models submitted with proposals. Specifically, the effort aimed to incorporate the Multi-Objective Decisions Analysis (MODA) framework into SysML diagrams as a solution for technical evaluations on models submitted with offeror proposals, eventually producing the Model-Based Decision Tool (MBDT). The MBDT is built from a Value Hierarchy based on key system requirements, each weighted by priority and measured by their own Single-Dimensional Value Functions (SDVFs). By …

Smart Manufacturing Readiness Assessment - Analysis Of A Modern Tool From A Sociotechnical Perspective, Todd Lemon

All-Inclusive List of Electronic Theses and Dissertations

Smart Manufacturing has emerged out of the pervasive buzzwords in publications as a competitive strategy, characterized by the intensive use of digital information and technology throughout the production processes; shop-floor, people, and systems are married by the Internet creating services critical to manufacturing. The work completed and presented here extends the research in the area of Smart Manufacturing (SM) readiness to include a more comprehensive approach to production floor implementation. The overarching goal is to explore SM implementation in attempt to identify underlying latent factors that relate to preparedness from a joint social and technical perspective, striving for a model …

Designing Pull-Based Energy System Rules For Public Buildings: An Application Of Modularity, Lei Wang

Dissertations and Theses Collection (Open Access)

Building energy systems, particularly Heating, Ventilation, and Air Conditioning (HVAC) systems, play a pivotal role in global sustainability efforts. Yet, traditional centralized HVAC systems continue to face major challenges: high energy consumption, significant operational costs, and limited adaptability to dynamic energy demands. These inefficiencies are compounded by the difficulty of integrating renewable energy sources into outdated system designs. As a result, substantial energy waste persists, posing obstacles to cost-effective, environmentally sustainable building operations.

This dissertation proposes a modular, pull-based energy framework to address these critical challenges. By combining the principles of modularity theory with demand-driven energy distribution, the framework enables …

Advances Towards A Robotic Management Vehicle Suited To Nurse Row Crops To More Efficient Outcomes, Adam Mk Gronewold

Dartmouth College Ph.D Dissertations

Enhancing agricultural production while reducing input costs remains a central challenge in modern row-crop management. Recent advances in computation, imagery, and sensors are enabling more efficient practices across various agricultural domains, and automation technologies are increasingly available to manage tasks central to perennial crop development. Automation in row-crop agriculture, by contrast, lags behind. This thesis explores utilizing small, unmanned ground vehicles to transform row cropping through the implementation of unconventional, in-season management strategies. The first focus of this work considers improvements to nitrogen fertilization using small, autonomous vehicles. An agronomy experiment in corn assessed the effects of gradually applying nitrogen …

Forecasting Army Recruiting Mission Distribution, Maxwell A. Deihl

Theses and Dissertations

The Army’s recruiting landscape has changed markedly in recent years, raising questions about whether forecasting methods of Army contracts remain robust. This thesis recreates the presented models in Joshua McDonald’s 2015 thesis. It replicates and evaluates the models with updated data (2018–2023) to assess their current validity and compare them to novel alternative approaches, such as simpler regression models or neural networks. While the 2015 model remains a valuable baseline, results suggest that either refining its variables or adopting alternative methods can improve predictive accuracy and interpretability. Ultimately, the United States Army Recruiting Command has many options regarding how it …

Methodology Of Automated Control Of Situations In Structurally Complex Systems With Recycled Flows, Khusan Zokirovich Igamberdiev Academician, Madina Mirxalilovma Fozilova

Chemical Technology, Control and Management

This article discusses the methodology of automated management of situations in structurally complex systems with recycled flows. The need to develop a correct model for effectively controlling such systems based on scientific principles of analysis and decision-making is substantiated. Particular attention is paid to modeling, optimizing, and using digital technologies, including artificial intelligence, to improve the accuracy and efficiency of management decisions. The principles of decomposition, multi-criteria optimization, and linguistic models of fuzzy correspondence are described, which can be used in conditions of uncertainty and complexity of industrial facilities.