22505 research outputs found
Sort by
Machinery Imbalance Failure Prediction Based on Pump – Motor Vibration Readings
Get PDFPredictive maintenance has emerged as a transformative solution in industrial operations, reducing unexpected machine failures and minimizing downtime. This study explores the application of machine learning in vibration analysis to detect imbalances in pump-motor units, a critical issue that accelerates equipment wear and increases maintenance costs. Traditional maintenance methods, such as scheduled inspections, often fail to identify faults early, leading to significant operational disruptions, particularly in utility, oil and gas sectors. By leveraging real-time vibration data and advanced machine learning techniques, this research aims to develop an efficient imbalance detection model that enhances maintenance efficiency and reliability. The study employs a structured methodology based on the CRISP-DM framework, covering data collection, preprocessing, modeling, and evaluation. The dataset includes vibration readings from multiple points on pump-motor units. Extensive preprocessing techniques were applied, including handling missing values, detecting outliers using Mahalanobis distance, and employing Principal Component Analysis (PCA) for dimensionality reduction. Feature engineering and selection methods, such as decision trees and statistical tests, were used to optimize the dataset for model training. Five machine learning algorithms—Logistic Regression, Linear Support Vector Machine (LSVM), Neural Networks, Decision Trees, and Random Forest—were tested across multiple scenarios to identify the most effective model. The dataset was split into three conditions: full dataset, dataset without outliers, and dataset with only outliers. The models were evaluated based on accuracy, recall, precision, and AUC (Area Under the Curve). Among the tested models, the Random Forest algorithm demonstrated the highest accuracy (99.3%) and recall (97.6%), making it the most reliable choice for detecting imbalances in pump-motor units. The results confirm that machine learning significantly improves imbalance detection, providing a proactive maintenance approach that reduces unexpected downtime, optimizes maintenance schedules, and extends equipment lifespan. The study also highlights the importance of data balancing techniques to address class imbalances and prevent bias in predictive models. Through advanced feature selection and sensitivity analysis, the most influential variables contributing to imbalance detection were identified, ensuring model interpretability and efficiency. The findings of this research contribute to the field of predictive maintenance by demonstrating the effectiveness of machine learning in real-world industrial applications. The integration of IoT-based vibration monitoring with machine learning can revolutionize equipment maintenance strategies, offering cost-effective and data-driven decision-making tools. Future work could explore the application of deep learning techniques and real-time deployment of the model for continuous monitoring in industrial settings
Visualizing the Dynamics of Neuroevolution with Genetic Distance Projections
Get PDFEvolutionary algorithms have shown substantial progress in recent years, especially in neural architecture search and neuroevolution applications. Despite their effectiveness, analyzing and understanding the evolutionary paths these algorithms traverse to reach solutions remains challenging. These algorithms often involve distributed computing strategies, which can include subpopulations or islands, and they explore massive or even unbounded search spaces in both continuous and non-continuous domains. Manually examining individual solutions to understand the evolutionary dynamics is often infeasible due to large population sizes, large genome sizes, and high generation counts. This work introduces a new methodology for visualizing neuroevolution population dynamics called genetic distance projections, along with a novel neural network-based method for generating these representations. This methodology is evaluated empirically and is found to perform better than other, more traditional methods in generating these representations. The usefulness of this methodology was validated with three different neuroevolution frameworks, including NEAT, EXAMM, and an experimental one, EXA-STAR. In addition, the debugging potential of this methodology is demonstrated on EXAMM
Mundane, ordinary and eerie undertones
Get PDFWhen people encounter fear and uncertainty, their mental and physical reactions can vary. Drawing from my personal experience and the ‘Uncanny Valley’ theory [2], I explore various materials and juxtapose ordinary elements with unsettling imagery. In this project, I focus on donuts, transforming them by adding surreal details to imbue them with eerie undertones. For example, in one of my works, a delicious-looking donut appears perfectly normal at first glance. When viewers have a close look at the donut, its surface is crawling with worms, creating an unsettling contrast between the familiar and the disturbing. By altering these familiar items, I seek to evoke a sense of unease and fascination, prompting viewers to reconsider the emotional weight of everyday objects
YOU! ME! DANCING!
Get PDFYOU! ME! DANCING! is a 3-piece photo installation consisting of photographs of myself and the Rochester area furry community. YOU! contains 145 medium format slides across two light panels exploring my relation to the masculine aspects of the Furry Fandom through staged studio portraits, intimate looks into furries in their natural habitats, and moments from local meetups. ME! uses large format sheet film layered in acrylic to highlight the change of character of wearing a fursuit, featuring my own custom fursuit. Lastly, DANCING!, is a visually inaccessible 80 image slideshow in which the pace and interval timed start of the slideshow makes the piece less about the individual image, but rather simulates the rush of new experiences I’ve experienced in the last two years. The work as a whole is a response to my own family archive dating back to the 1920\u27s that I recently scanned and organized, finding many familiar faces but not the supportive community I was hoping for. Through the use of lightboxes, a slide projector, and physical media, I have now amassed a new found family archive more centered on community, acceptance, and creative self-expression
Adaptive Reuse of Abandoned Schools
Get PDFThis thesis investigates the adaptive reuse of abandoned school buildings in economically declining communities, mainly focusing on how these transformations can contribute to sustainable community revitalization. The research highlights Columbus, Ohio, where school closures and grade realignments threaten to leave many school properties vacant, especially in minority neighborhoods. This adaptive reuse strategy presents an opportunity to address issues such as urban decay, resource efficiency, and social equity by repurposing these buildings into multifunctional community assets. The study adopts a multi-method approach, including literature reviews, case study analysis, and community needs assessments, to identify best practices and critical challenges in adaptive reuse, such as regulatory obstacles and financial constraints. The research proposes a tailored framework for reimaging school buildings as hubs for community services, affordable housing, and cultural centers by reviewing successful examples from diverse regions and gathering stakeholder data. Findings suggest that adaptive reuse preserves school structures’ architectural and cultural heritage and offers a cost-effective, environmentally friendly strategy that aligns with sustainability goals. The proposed framework provides a practical roadmap for policymakers, developers, and communities, aiming to support adaptive reuse initiatives that foster sustainable urban renewal. This study concludes that adaptive reuse, mainly when supported by effective policy and green design practices, can catalyze revitalizing economically challenged communities
Prediction of Diabetes Using Machine Learning
Get PDFThis research seeks to compare the overall health of diabetic patients with that of their healthy counterparts based on various heath indicators obtained from a large dataset comprising of pregnancies, glucose levels, blood pressure, skin thickness, insulin, BMI, diabetes pedigree function and age. Relative to the healthy group, increased average glucose level, higher BMI, and older age are identified in the diabetic participants. Most importantly, the results show that obesity is a significant risk factor for diabetes, and many diabetics have BMIs that are elevated above healthy levels. The data also points towards the fact that insulin resistance and prevalence of diabetes are related to each other, as exemplified by the range of insulin variation in type 2 diabetes subjects. Thus, the study also underscores the significance of family history and age in the development of diabetes, underlining the need for people with diabetes risk factors to undergo screening as soon as possible. The findings revealed an accuracy of close to 82% in diagnosing the condition from the dataset whose algorithms inform machine learning models that are already applied in clinical practice. These findings attest to the complex nature of the diseases and emphasize the importance of integrating various concepts and thinking in relation to diabetes risk factors to help ensure early detection and successful management of the conditions. In conclusion, this research enhances the literature on the application of health data analytics in enhancement of diabetes prevention and management
Examining Food Choice Determinants in NCAA Division III Athlete Participants Representing Multiple Sports
Get PDFObjective: To examine determinants of food choice among NCAA Division III athletes using the Athlete Food Choice Questionnaire (AFCQ), focusing on gender, sport type, and seasonal status. Participants: 72 NCAA Division III athletes from 13 sports at a private northeastern university participated in an online survey during Fall 2024. Methods: Participants completed the 32-item AFCQ assessing nine food choice factors. Independent t-tests and Pearson’s correlations were used to compare factor scores by gender, sport type, seasonal status, and team success. Results: Performance, Sensory Appeal, and Food Values and Beliefs emerged as the most influential factors in food choice, while Weight Control was least influential. Female athletes reported significantly higher scores for Emotional Influences, Usual Eating practices, Sensory Appeal, and Food Values and Beliefs compared to males. Male individual sport athletes reported higher scores in Nutritional Attributes, Food Health Awareness, and Weight Control compared to team sport athletes. Conclusions: The findings highlight notable differences in food choice determinants based on gender and sport context. The AFCQ proves to be a valuable tool in collegiate settings, emphasizing the need for nutrition education strategies tailored to the unique motivational and environmental factors influencing athlete eating behaviors
DOT-LINE — Furniture for Inspired Living
Get PDFDesign as a functional outlet results from research that revolves around the user experience. It is a fair definition that seems to acknowledge today\u27s standards of designing for the masses, prioritizing market-driven factors that include utility, manufacturability, and market demand. This approach aligns with contemporary design, but does it take ontological design out of the equation? Given that consumer consciousness determines what exists in the market, a design\u27s nonvisual and deeply conceptual aspects may go unnoticed. While market research allows designers to anticipate and shape consumer desires, it is also an opportunity to delve deeper into the user\u27s psyche, not for commercial gain, but to enhance well-being through emotional design. What emotions contribute to user welfare? And how can such a study be transmuted into a tangible user experience? This research explores how Art and Design interplay can materialize a product that carries more meaning beyond mere utility. The research about potential relational dynamics of art integration, interactivity, modularity, and intuitive design choices provides an in-depth look at how a product can be both a functional object and a signifier for creativity and self-expression in a living environment
Modelling and Load Frequency Control (LFC) Design of Microgrid Frame-worked As Technological Norm to Multi Energy System (MES)
No full textIn today\u27s world, the trend of using renewable energy sources as an alternative energy source is becoming more and more common due to various driving factors, such as energy scarcity (fossil fuel depletion, etc.) and environmental issues (carbon footprint). This trend is leading to a steady increase in the penetration of renewable energy sources (RESs) through microgrid (MG), which is formed from combination of various distribution energy sources (DERs). The inherent intermittent nature of RESs coupled with abrupt load changes can instigate sustained frequency fluctuations and can keep the frequency deviation out of the allowable range that leads to an increased uncertainty and instability in operation with possible collapse of the microgrid (MG) system. Hence, an independent MG operation needs to ensure disruption minimization to the energy supply and critical loads. Accordingly, a detailed and continuously improved control solution is required for stability and operation uncertainty reduction reasons. In this thesis, an advanced LFC scheme using a particle swarm optimization (PSO) optimized balanced reduced-order linear quadratic Gaussian/linear quadratic integrator (LQG/LQI) control scheme is proposed for autonomous microgrid frame-worked to accommodate a multi-energy system (MES), which integrates diverse energy resources and technologies, where this work has also targeted to build on multi-energy system (MES) requirements by introducing holistic approaches that provide 1) better, 2) accurate, and 3) comprehensive dynamic frequency response models for the microgrid components. The effectiveness of the proposed control scheme is validated through MATLAB®/SIMULINK simulations and comparative analysis with other control schemes under various scenarios, which range from distinct load disturbance to combined random disturbance input profiles of all RESs and RESs modeled with virtual inertia (VI). A proportional-integral-derivative (PID) particle swarm optimization (PSO)-tuned and an interval type 1 (IT1) fuzzy controller are the two other control schemes that are used for performance comparison analysis with the proposed controller. The simulation results demonstrated better frequency control performance for the proposed control scheme over the other two types of control schemes. The proposed advanced control scheme also guarantees fast settling time of frequency transients and improves dynamic response and exhibits high resilience to severe stochastic loads and active power disturbances for the subject microgrid
Crip Queer Storytelling: An Intersectional Analysis
Get PDFAbstract
Where are queer disabled characters, and how do they avoid tokenization? This particular approach will use the following criteria as its foundation:
1) The story has a character who is both disabled and queer. (This must be explicit in some way and not ambiguously coded within the text, or solely paratextual.)
2) The character is central to the narrative. (If the character were removed, would the story change significantly?)
3) The story can be affected by disability, but (with due respect to making space for such stories) the story isn’t solely/centrally about disability/overcoming ableism.
The hope with these criteria is to articulate instances of queer disabled representation that are nuanced and move beyond mere tokenization, or beyond characterization that is primarily defined by the character’s marginalized identities, with emphasis on intersectional possibilities in fiction. This exploration sits at the nexus of Creative Writing Studies, Queer Studies, and Disability Studies to consider representation complexly, examining a place of potential evolution/expansion in creative writing