Engineering Commons^™

Multi-Model Safe Neuro-Optimal Output Tracking Control Of Autonomous Surface Vessels With Explainable Ai, Behzad Farzanegan, S. Jagannathan

Electrical and Computer Engineering Faculty Research & Creative Works

This paper presents a safety-aware deep reinforcement learning (DRL)-based trajectory tracking control of autonomous surface vessels (ASVs). A multilayer neural network (MNN) observer estimates the ASV's state and uncertain dynamics. By utilizing the estimate state vector from the observer, a safety-aware DRL-based optimal policy is formulated using control barrier function (CBF) and Karush-Kuhn-Tucker (KKT) conditions. An actor-critic MNN with singular value decomposition (SVD)-based update mitigates vanishing gradients. To enhance adaptability, an online safe lifelong learning (SLL) scheme counters catastrophic forgetting across varying ASV dynamics. The Shapley Additive Explanations (SHAP) method identifies key features influencing the control policy. Simulations on an …

Bibliometric Analysis With R Biblioshiny On Safety Behavior In Aviation, Büşra Yıldırım, İnan Eryılmaz, Ahmet Karacan, Nusret Erceylan

International Journal of Aviation, Aeronautics, and Aerospace

Safety behaviors in aviation are not limited to technical knowledge and skills in ensuring the safety of flight operations, but also include the attitudes, decision-making processes and collaborations of individuals and teams. In this context, in this study, a bibliometric analysis of publication and citation trends, key concepts and interactions of studies in the field was conducted to identify current and potential trends in aviation and safety behavior-based research, and to explore the intersections between safety behavior and aviation studies and the areas waiting to be explored. The bibliometric analysis using the RStudio-based Biblioshiny program was conducted on 1065 articles …

Safety And Optimality Monitors For Learning-Enabled Systems Using Conformal Prediction, Jackson Cox

McKelvey School of Engineering Graduate Student Theses & Dissertations

The use of machine learning to create data-driven plant models and controllers has led to an increased need for safety and optimality monitors for model-based systems. System plant models are subject to uncertainty due to learning constraints such as unseen data and overfitting or physical constraints such as unknown dynamics and noise. This uncertainty is detrimental to safety-critical systems and must be properly regulated. To curb this uncertainty, we create prediction sets using the guarantees provided by Conformal Prediction. With a user-specified high probability, these prediction sets contain the true plant system states for an entire prediction horizon, which we …

Building Safely: How Spanish Specific Safety Can Impact Job Sites, Luis D. Aguilar Montano

Construction Management

This project explores how Spanish Specific Safety Training is being approached in the construction industry, with an attempt to identify some possible issues associated with language barriers and accessibility to these trainings. This research involved data collection through thirty analytical surveys, in addition to conducting three semi-structured interviews with construction workers and supervisors. The focus of the data collection was to gain insights into several key areas, including training accessibility, workplace injuries, language barriers, and worker comfort. The survey results indicated strong support for Spanish-language safety training, with respondents recognizing its potential to improve safety and overall worker comfort. Many …

Design Of A Safe And Sustainable Airplane For Future, Henil Patel, Carlie Vogt, Matthew Talty, Jemimah Davies, Kyle Smothers, Mellisa Pritchet

Sustainability Conference

As a part of Airplane Preliminary Design course, this Design Note estimates the capabilities, performance, and stability behaviors of our conceptual airplane design, Boeing 7S7 – Sanctum prior to proceeding to the preliminary stage. This aircraft seeks to create a solution to achieving Net Zero Emissions by 2050 and increasing the safety measures. The design of this aircraft uses various analytical methods such as the DAPCA IV model, other methods were derived from design books. This design involved the use of software such as CATIA, VSP, SURFACES, Microsoft Excel, and Python. Results demonstrates that this aircraft is able to fly …

Longitudinal Pedestrian Safety Trends By Vehicle Type And Model: A 2015-2022 Study Of Texas, Olivia Tafoya

Civil Engineering ETDs

We observed pickup trucks, SUVs, and passenger cars and their two most popular vehicle models across Texas from 2015 through 2022. For each vehicle type and model, we obtained all reported pedestrian crashes, counts of registered vehicles, and vehicle design characteristics. Results suggest that older vehicles are more likely to seriously injure or kill a pedestrian than newer ones. They also indicate that SUVs were more deadly, after controlling for exposure using the number of registered vehicles, than other vehicle types. Of the models studied, the full-size SUVs proved to be particularly dangerous for pedestrians, being 2.08 times more likely …

Safety And Risk Management Strategies For Achieving Regulatory Compliance In Construction Projects, Danny Rodriguez

Harrisburg University Dissertations and Theses

The architectural and construction business places great importance on safety and regulatory compliance because of its inherent high-risk nature and strict legal obligations. The prevalence of accidents and infractions at construction sites underscores the imperative for enhanced safety management systems and compliance with rules, notwithstanding substantial endeavors. The main objective of this study is to examine the many elements that impact the effectiveness of safety management, adherence to regulations, and the development of a safety culture, with the ultimate purpose of improving safety outcomes on construction sites.

The issue statement pertains to the difficulties associated with safety management and compliance …

Evaluation Of Roadway Reconfigurations In Louisville, Kentucky, William Staats, Adam Kirk

Kentucky Transportation Center Research Report

In 2009, Louisville Metro Public Works undertook its first roadway reconfiguration project, converting a section of Eastern Parkway (US 60A) from a four-lane undivided road to a three-lane section with a two-way left-turn lane and one travel lane in each direction. Since this initial project, Louisville Metro Public Works and the Kentucky Transportation Cabinet (KYTC) have completed 40 roadway reconfigurations to reduce the number of through lanes and reassign existing right-of-way to other roadway users. Additionally, the agencies have 25 more planned or proposed reconfiguration projects. This report documents the safety and operational performance of reconfigured roads. Across all projects, …

Sustainable Waste-To-Bioproducts Engineering Center Laboratory Safety Project, Claudine Mock

All Graduate Reports and Creative Projects, Fall 2023 to Present

Laboratory accidents are common in teaching and research labs; these accidents can be injurious or even fatal. The consequences of each type of laboratory accident are different based on the activities performed and the hazardous materials used in each facility. However, the most common issue related to laboratory accidents is the lack of proper safety measures (e.g., poor handling of hazardous materials, not reporting incidents immediately, etc.). This project aimed to establish and strengthen best practices and procedures to ensure laboratory safety at the Utah State University Sustainable Waste-to-Bioproducts Engineering Center. To achieve this goal, different practices and measures were …

Survey And Analysis Of Safety Components And Costs In Construction Projects In Egypt, Emad E. Etman Prof., Haytham Sanad Prof., Asmaa Ibrahim Khater

Journal of Engineering Research

The difficulty of determining the factors that achieve safety on Egyptian construction sites as a result of multiple and different criteria and different relative weights of the criteria represents a challenge to achieve safety and a secure environment on construction sites. This issue has been of interest for many decades and continues to be a topic of discussion today because of construction project management is rapidly modernizing. The paper aims to identify the safety standards most commonly used on construction sites, and determine their relative weights as seen by the target audience and also estimate the cost of safety measures …

Kernel Ridge Regression In Predicting Railway Crossing Accidents, Ethan Villalobos, Constantine Tarawneh, Jia Chen, Evangelos E. Papalexakis, Ping Xu

Mechanical Engineering Faculty Publications

Expanding on the insights from our initial investigation into railway accident patterns, this paper delves deeper into the predictive capabilities of machine learning to forecast potential accident trends in railway crossings. Focusing on critical factors such as “Highway User Position” and “Equipment Involved,” we integrate Kernel Ridge Regression (KRR) models tailored to distinct clusters, as well as a global model for the entire dataset. These models, trained on historical data, discern patterns and correlations that might elude traditional statistical methods. Our findings are compelling: certain clusters, despite limited data points, showcase remarkably Root Mean Squared Error (RMSE) values between predictions …

Spectral Clustering In Railway Crossing Accidents Analysis, Ethan Villalobos, Hector Lugo Iii, Biqian Cheng, Miguel Gutierrez, Constantine Tarawneh, Ping Xu, Jia Chen, Evangelos E. Papalexakis

Mechanical Engineering Faculty Publications

This study employs graph mining and spectral clustering to analyze patterns in railway crossing accidents, utilizing a comprehensive dataset from the US Department of Transportation. By constructing a graph of implicit relationships between railway companies based on shared accident localities, we apply spectral clustering to identify distinct clusters of companies with similar accident patterns. This offers nuanced insight into the underlying structure of these incidents. Our results indicate that “Highway User Position” and “Equipment Involved” play pivotal roles in accident clustering, while temporal elements like “Date” and “Time” exert a diminished impact. This research not only sheds light on potential …

Feature Extraction From Vibration Signature Required From Railroad Bearing Onboard Condition Monitoring Sensor Modules, Kevin Quaye, Ping Xu, Dimah Dera, Heinrich D. Foltz, Constantine Tarawneh, Alberto Diaz

Mechanical Engineering Faculty Publications

From 2013 to 2022, 1671 derailments have been reported by the Federal Railroad Administration (FRA), 8.2% of which were due to journal bearing defects. The University Transportation Center for Railway Safety (UTCRS) designed an onboard monitoring system that tracks vibration waveforms over time to assess bearing health through three analysis levels. However, the speed of the bearing, a fundamental parameter for these analyses, is often acquired from Global Positioning System (GPS) data, which is typically not available at the sensor location. To solve this issue, this paper proposes to employ Machine Learning (ML) algorithms to extract the speed and other …

Planning And Executing The 2024 Annual Hackathon, Isabella Naomi Peterson

Construction Management

The Hackathon is an event that is put on every year by Cal Poly construction management students which highlights a prevalent safety issue in the construction industry. This is a one day event which focuses on re-designing, innovating, and improving an aspect on job sites that needs modification. The theme this year for the third annual Hackathon was redesigning the safety hard hat and helmet. This paper will explain how the Hackathon project came about this year, why the safety issue of hard hats was selected, the research conducted for this year’s Hackathon, steps of event planning, the execution of …

Exploring The Impact Of Personal Protective Equipment (Ppe) Quality On Construction Individuals, Daniel Seo

Construction Management

Personal Protective Equipment (PPE) is essential in protecting workers on construction sites. Construction sites are known to have various hazards that can lead to death or injury. While PPEs are designed to protect workers from these injuries, its usage and quality affects its capability. As PPE is distributed by construction companies, it is imperative to identify the determinants of quality PPE. These factors include psychological factors like perceived risk, comfort, and safety attitudes. Two surveys were conducted on seventeen (17) construction management industry individuals and twenty-one (21) construction management students to determine the preferences of PPE and their views regarding …

Two Heads Are Better Than One: Single Pilot Operation Threatens The Safety Of The Friendly Skies, Alexandria E. Rook

Arkansas Law Review

Boeing’s Maneuvering Characteristics Augmentation System (“MCAS”), an automated piloting system, is only supposed to handle aircraft operations in very specific circumstances. Despite devasting results with MCAS, Boeing has another automated piloting system on the horizon that poses even more grave risks: Single Pilot Operation (“SPO”). Boeing—along with Airbus—wants to replace one of the pilots in the cockpit of commercial airline flights with the new SPO technology it is developing. The FAA should not allow SPO technology to be implemented because it is premature, motivated by financial gain to the detriment of safety, and ignores the importance of professional judgment in …

Ensuring Resilience Against Stealthy Attacks On Cyber-Physical Systems, Paul Griffioen, Bruce H. Krogh, Bruno Sinopoli

Faculty Work Comprehensive List

This article provides a tool for analyzing mechanisms that aim to achieve resilience against stealthy, or undetectable, attacks on cyber-physical systems. We consider attackers who are able to corrupt all of the inputs and outputs of the system. To counter such attackers, a response scheme must be implemented that keeps the attacker from corrupting the inputs and outputs of the system for certain periods of time. To aid in the design of such a response scheme, our tool provides sufficient lengths for these periods of time in order to ensure safety with a particular probability. We provide an upper bound …

Longitudinal Spatial Trends In U.S. Pedestrian And Bicyclist Fatalities, Ossiris Rodriguez, Nicholas N. Ferenchak

Civil Engineering ETDs

Between 2009 and 2022 in the United States (U.S.), pedestrian fatalities increased 82.3% and bicyclist fatalities increased 70.8%. Several studies have researched crash characteristics such as the people and roadways involved in these crashes. But where are these fatalities occurring within our regions and what spatial characteristics of these locations could be influencing this trend? We analyzed pedestrian and bicyclist fatality data from the last two decades using NHTSA’s Fatality Analysis Reporting System (FARS) in relation to built-environment and socio-economic characteristics (such as street network density, transit access, poverty, and educational attainment) obtained from the U.S. Census and the U.S. …

Securing The Skies: Safety-Constrained Decentralized Multi-Uav Coordination With Deep Reinforcement Learning, Jean-Elie Pierre

Electrical and Computer Engineering ETDs

In the dynamic landscape of autonomous aerial systems, the integration of uncrewed aerial vehicles (UAVs) has sparked a paradigm shift, offering unprecedented opportunities and challenges in collaborative decision-making and navigation. This thesis explores the application of multi-agent reinforcement learning (MARL) for the planning and coordination of UAVs in complex environments.

The first part of this thesis provides an introduction to single-agent reinforcement learning and MARL. We provide examples of the use of MARL for countering uncrewed aerial systems (C-UAS). We formulate the Counter-UAS problem as a multiagent partially observable Markov decision process (MAPOMDP), and we propose Multi-AGent partial observable deep …

Safety Analysis In Ap-1000 Nuclear Power Plant Against Primary Loop Coolant Pump And Fuel Failures, Fabiano Gibson Daud Thulu, Hailemichael Guadie Mengsitu, Chifundo Tenthani, Paul Stone Macheso

International Journal of Nuclear Security

This study focused on the best-estimated thermal-hydraulic calculations performed regarding the AP-1000 nuclear power plant (NPP) under primary coolant loop pump and fuel failures. Primary coolant pump and fuel failure transients are important design-basis accidents in NPP safety assessments. This work examined the primary reactor’s safety margins of fuel and cladding peak temperature, primary and secondary loop pressure, hydrogen formation, and primary and secondary flow rates.The Adaptive System Thermal-Hydraulics program was used in the simulation and event progression analysis. The results showed that the peak fuel surface temperature was kept below the licensing design limit. No observation of corium was …

The National Center For Reliable Electric Power Transmission Test Facility, Anna Corbitt, Wesley G. Schwartz, Chris Farnell, Juan Carlos Balda, H. Alan Mantooth

Electrical Engineering and Computer Science Faculty Publications and Presentations

Globally, new technological solutions are being studied and developed by researchers in the field of power and energy systems. Before these solutions can be integrated into society as marketable products, thorough testing and validation of the design must be conducted. The National Center for Reliable Electric Power Transmission (NCREPT) is a unique high-power test facility located at the University of Arkansas, Fayetteville, AR, USA. NCREPT is a 12,000-square-foot laboratory space capable of testing power levels up to 6 MVA and offers testing at both the 480 V and 13.8 kV levels. NCREPT's capabilities expand outside of the scope of simply …

Modeling Pedestrian And Bicyclist Crash Exposure With Location-Based Service Data, Yunwoo Nam, Jason Hawkins, Don Butler, Nicholas Aldridge, Mohammad Elayan, Kwant Il (Jason) Yoo

Nebraska Department of Transportation: Research Reports

The rising popularity of non-motorized transportation has brought about safety risks. The inclusion of accurate traffic volume information is one of the key elements to produce robust outcomes when researching safety. The project investigates and enhances transportation safety for pedestrians and bicyclists, emphasizing the integration of Location-Based Services (LBS) data, particularly StreetLight data, to analyze traffic volume and associated risks. The calibration process demonstrates the significance of traffic volume as a key variable influencing prediction accuracy across pedestrian, bicyclist, and vehicle models. The crash analysis reveals a strong correlation between crash counts and traffic activity, with noteworthy findings emerging at …

Head Impact Measurement Using Piezoelectric Sensors, Huda Abdulla Alnuaimi

Theses

The importance of safety measures cannot be overstated, especially when it comes to protecting the human head. Head injuries can have severe, life-altering consequences, as the head is crucial for controlling the entire body. Unlike machines that store data, the human brain's capacity to retain thoughts and memories can be significantly affected by even a single injury. This thesis introduces a method for predicting the specific area of the head that might be injured during an impact. The prediction is based on the intensity and duration of the impact. The innovation of this thesis lies in the use of piezoelectric …

Assessing Past Airworthiness Directives And How Safety Management Systems May Benefit Aviation Product Design And Manufacturing, Damon Lercel, Manoj Patankar, Richard Steckel

Journal of Aviation/Aerospace Education & Research

The European Union Aviation Safety Agency (EASA) continues to promulgate Safety Management Systems (SMS) across aviation organizations when it recently issued SMS requirements for EASA certificated Part 145 maintenance, repair and overhaul (MRO) organizations and Part 21 Design & Manufacturing (D&M) organizations. Currently, the Federal Aviation Administration (FAA) has no such rule in place for these U.S.-based organizations, which may challenge those doing business in countries where EASA policies apply. Given that a majority of the United States’ D&M and MRO population is made up of smaller organizations, it is likely a U.S. SMS regulation will require justification of the …

The Elements Of Governance And Their Association With Aviation Safety Oversight Effectiveness, João Souza Dias Garcia

Doctoral Dissertations and Master's Theses

States and their respective national civil aviation authorities promote the improvement of the global civil aviation system by developing and enforcing safety regulations for aircraft design, operations, personnel training, infrastructure, and air traffic management, among other topics. For many years, the International Civil Aviation Organization (ICAO) has driven the continuous improvement of states’ safety oversight functions, supporting them in evaluating the effectiveness of these functions by conducting audits under the Organization’s Universal Safety Oversight Audit Program (USOAP). While the benefits of these assessments have been broadly recognized, scholarly literature on the factors commonly associated with safety oversight effectiveness across states …

Safety Investigation Of Crash Rates During Hurricane Evacuations, Amelia K. Lawson

Doctoral Dissertations and Master's Theses

This study aimed to investigate crash rates across four distinct periods—evacuation, re-entry, emergency, and non-emergency—during Hurricanes Matthew (2016), Irma (2017), and Michael (2018). A notable gap in existing research pertains to understanding crash rates during these critical phases of hurricane events. By addressing this gap, this research contributes to a deeper comprehension of evacuation transportation safety. The methodology employed ArcMap to construct an interactive map for data collection, encompassing key variables such as the number of crashes, traffic volumes, duration of each period under analysis, and roadway segment lengths for each hurricane. Evaluating the crash rate per million vehicular miles …

Integration Of Advanced Qualification Program Into Aviation Education, Jorge L. D. Albelo, Victor Fraticelli Rivera, Robert L. Thomas

Journal of Aviation Technology and Engineering

The Federal Aviation Administration places aviation safety as a top priority, continuously striving to improve safety standards within the National Airspace System. In 2004, the Federal Aviation Administration introduced the Advanced Qualification Program (AQP) as an alternative methodology for pilot training and evaluation. This study explores the impact of AQP-centered aviation education on student performance, particularly in the context of learning advanced jet transport systems. The AQP model, based on aligning training with operational aviation requirements, emphasizes cognitive skill training and evaluation. Theoretical foundations underpinning this study include Karp’s integrated aviation learning model, which seamlessly integrates various instructional approaches, fostering …

Evaluation Of Driveway Assistance Device (Dad) Systems In One-Lane Two-Way Work Zone, Mm Shakiul Haque, Aemal J. Khattak, Li Zhao

Mid-America Transportation Center: Final Reports and Technical Briefs

Lane closure on two-lane highways due to the presence of work zones negatively impacts traffic safety and operational efficiency. Additionally, traffic from access points (e.g., commercial and residential driveways, or minor side roads) within work zones make operations more complicated and inefficient. Deploying a driveway assistance device (DAD) system can enable more efficient traffic control for work zones with access points. While traffic agencies are becoming interested in DAD deployments, research on such systems is relatively sparse. This research was the first in-depth operational investigation of the DAD system under different signal strategies, traffic conditions, and work zone characteristics. This …

2023-2024 Annual Security And Fire Report – Sayre Campus, Southwestern Oklahoma State University

ANNUAL SECURITY & FIRE REPORTS

This is the 2023-2024 Annual Security and Fire Report of the Sayre Campus by Southwestern Oklahoma State University.

2023-2024 Annual Security And Fire Report – Weatherford Campus, Southwestern Oklahoma State University

ANNUAL SECURITY & FIRE REPORTS

This is the 2023-2024 Annual Security and Fire Report of the Weatherford Campus by Southwestern Oklahoma State University.