Master Theses & Projects (FEAS)

Permanent URI for this collectionhttps://ontariotechu.scholaris.ca/handle/10155/687

Browse

Now showing 1 - 20 of 491

Development of an AI-driven robotic manipulation framework
(2024-09-01) Liu, Xiaolong; Ren, Jing; Lang, Haoxiang
This paper introduces a manipulator control system that leverages state-of-the-art artificial intelligence (AI), advanced robotics, and the latest computer vision techniques to enable intuitive and universal robotic control across different robotic manipulators. The intuitive user command interpretation is deployed in the system using ChatGPT API. The vision capabilities of the system rely on YOLOv7 for object detection, Semi-Global Block Matching (SGBM) for object localization, and Principal Component Analysis (PCA) for object orientation. Moreover, MoveIt is utilized for motion planning, and the simulation environment is powered by Gazebo. These components are seamlessly coordinated by a custom state machine integrating into a ROS-based framework. This system allows users to control manipulators completing complex tasks by commands without expert knowledge of robotics. Additionally, a cross-platform kinematics solver architecture is introduced to assess inverse kinematics algorithms for manipulators. Compared to the traditional kinematics solver implemented as ROS plugins, this architecture integrates the sophisticated mathematical capabilities of Matlab with the feasibility of ROS.
Signal and power integrity analysis of bidirectional DC-DC converters for hybrid energy storage systems with EMI/EMC optimization
(2024-09-01) Ladhar, Manraj Singh; Williamson, Sheldon
Hybrid Energy Storage System (HESS) utilizes multiple energy storage architectures to achieve a broader range of characteristics in terms of power density, energy density and calendar life. A 500W bidirectional synchronous DC-DC converter design is implemented for the active topology of HESS. This thesis examines optimal design principles and practices essential for the printed circuit board (PCB) layout of switching regulators with fast dv/dt and di/dt edge rates to achieve electromagnetic interference (EMI) compliance standards. Furthermore, it focuses on comparative analysis and investigation of near-field noise emissions measured from three PCB designs each sharing the same schematic but different layout design rules and stackup configurations. Reflections, crosstalk, and transmission line management techniques along with power delivery network/system (PDN/PDS) design are implemented for enhanced signal and power integrity. 4-layer board designed with embedded interplane capacitance, controlled impedance traces, proper signal termination and crosstalk management exhibits lowest noise emissions. The experimental results show good consistency with electromagnetic field theory and simulations.
Design of a power, communications, and cable system for use with a robotic crawler for CANDU fuel channel inspection
(2024-09-01) Elvin, Bryce C.; Nokleby, Scott
Canadian Deuterium-Uranium Reactors (CANDU) are currently the only kind of power reactor used in Canada. These reactors supply a large quantity of the energy consumed in Canada. CANDU reactors require regular fuel channel inspection to ensure safety and performance. Fuel channel inspection is currently done one channel at a time which results in significant reactor downtime. The proposed system is a robotic crawler inspection system which can inspect the fuel channels while sealed inside the reactor. This allows for simultaneous inspection of multiple fuel channels using multiple copies of the system. The work in this thesis describes improvements to an existing inspection system. New hardware and software was created for the robotic crawler to improve the performance of different subsystems, as well as facilitate the complete separation of the system from the outside of the reactor. A new cable system was also designed to allow the crawler to have its power and communications system located inside the end-fitting of the fuel channel. The crawler was modified to function wirelessly from the operator, removing the need for wires to be led from the fuel channel to the operator’s device. A proof of concept prototype was created which demonstrates that the system can be operated remotely and that all subsystems can be placed inside of the fuel channel during inspection.
Unified data management in collaborative IoT systems
(2024-08-01) Ouda, Hossameldin; Elgazzar, Khalid
Data has become a central focus for industries and businesses in delivering services. Furthermore, efficient collaboration solutions for IoT systems are increasingly needed to optimize IoT data usage across various domains. This work provides a comparative analysis between data models for handling heterogeneous IoT data. The analysis shows that the document data model outperforms its competitors with a throughput rate of 597.2/sec and an average end-to-end execution time of 0.54 seconds in CRUD operations on IoT data. Furthermore, the work introduces a data unification framework that standardizes IoT device messages sent to the MQTT broker, eliminating the need to read extensive documentation. The framework includes a data interpreter approach that unifies heterogeneous IoT data into a well-defined JSON document the sensing information along with the metadata for the corresponding IoT device, storing it in data modelling collections. The results show an optimization of 88% in the IoT devices profile more than state-of-the-art solutions like Iotivity and SensorML. Also, Interoperability tests have been carried out in the area of smart intersections and their collaboration with weather and healthcare systems. The tests confirm the framework’s versatility and reliability thus proving its suitability for adoption by the developing community.
Development and experimental investigation of direct urea fuel cells
(2024-06-01) Meke, Ayse Sinem; Dincer, Ibrahim
This thesis study considers the development and experimental investigation of Direct Urea-Hydrogen Peroxide Fuel Cells (DUHPFC). The research focuses on preparing electrodes using nickel zinc iron oxide on stainless steel foil and evaluates single cells and stacks under varying conditions. Optimal single-cell performance is achieved at 65°C with 9 M KOH and 0.5 M urea, yielding a peak power density of 46.38 mW/cm². The stack shows improved performance at 65°C, with a power output of 0.307 kW. The single cell attains an open circuit voltage (OCV) of 0.72 V, while the stack reaches 8.8 V. The energy and exergy efficiencies are 58% and 24% at 5 M KOH for single cells, and 48% and 41% at 65°C for stack, respectively. The electrochemical impedance spectroscopy (EIS) shows impedance reduction from 30 ohm.cm² at 25°C to 15 ohm.cm² at 65°C, indicating enhanced ionic conductivity and reduced resistance. These findings provide insights for advancing DUHPFC technology.
"Sounding out solutions: current status of ocean noise pollution and management approaches to conserve cetacean with the focus on Canadian habitats."
(2024-03-01) Nassim, Nakissa; Jawad, Dima
As human activities continue to rise, the adverse consequences of ocean noise pollution on cetaceans (Cetacean is the general noun used to describe all 90 species of whales, dolphins, and porpoises), including stranding, masking, alterations in foraging behaviors, and mating disruptions, have become a significant concern for marine conservationists. Despite international recognition, the complex nature of sound propagation in aquatic environments and diverse contributing sources have left various aspects of ocean noise pollution needing to be fully comprehended. This research project delves into the multifaceted impacts of underwater noise on cetaceans, underscoring the imperative to implement effective mitigation measures promptly. Key strategies, such as planning, resource management, raising stakeholders’ awareness and engagement, adopting noise reduction technologies, and integrating them with existing ones, establishing Marine Protected Areas (MPAs), and initiatives to decrease ship speed and reroute ship lanes, play a pivotal role in alleviating ocean noise pollution. The project emphasizes the importance of a holistic approach to address the issue, suggesting integrating noise reduction strategies into all conservation plans for seas and oceans. Recognizing the significance of engagement from both the public and private sectors, a fundamental aspect of this approach involves raising awareness to foster a shared sense of responsibility toward marine life. Furthermore, it advocates for intensified research endeavors to further our understanding of the specific impacts of noise pollution on distinct cetacean groups, enabling the refinement of mitigation strategies accordingly. This project underscores the urgent and collective need for immediate action to tackle ocean noise pollution. By adaptive management, amalgamating technological advancements, regulatory measures, and public awareness and engagement initiatives, we can promote more sustainable coexistence between human activities and the marine environment, ensuring the safeguarding and conservation of cetacean species in our oceans.
Multiscale video transformers for video class agnostic segmentation in an autonomous driving setting
(2024-08-24) Cheshmi, Leila; Siam, Mennatullah
Semantic segmentation is a key technique in the perception of autonomous driving. Traditional semantic segmentation models, however, are constrained by the need for extensive annotated datasets and struggle with unknown classes not encountered during training. On the other hand, video class-agnostic segmentation aims to segment objects without relying on their semantic category. Motion cues could be used towards that goal to account for objects outside the closed set of training classes. This project proposes an innovative approach to video class-agnostic segmentation in autonomous driving using multiscale video transformers. We enhance the Video Class Agnostic Segmentation (VCAS) dataset by integrating richer annotations and tracking data from the TAO-VOS (BDD) dataset, thereby providing a comprehensive dataset for better generalization in complex driving scenarios. Our project involves designing a novel multi-scale video transformer-based architecture that foregoes optical flow, focusing instead on learning motion implicitly to identify objects in a class-agnostic manner. This architecture utilizes the Multiscale Encoder-Decoder Video Transformer (MED-VT) framework, which processes sequential data in a multiscale approach to capture both fine and coarse-grained information. Video transformers utilize encoder and decoder components, along with attention mechanisms, to efficiently process sequential data. Our approach takes an input clip and outputs the class-agnostic segmentation of moving objects in that clip. Features extracted from the raw input clip using a convolutional backbone are treated as tokens and provided to the multiscale transformer for pixel-wise classification. Additionally, we augment the currently available video class-agnostic segmentation datasets with TAO-VOS (BDD) datasets. We also label some missing objects in TAO-VOS (BDD) datasets with a standard semantic segmentation annotation tool in a few of the sequences. The outcomes of this project include a more diverse and comprehensive dataset and a superior video class-agnostic segmentation model with improved accuracy in mean intersection over union (mIoU). Our training on datasets focused on autonomous driving scenes demonstrated a significant improvement in mIoU compared to models trained on general-purpose video object segmentation datasets.
Energy planning with hydrogen deployment strategies within interconnected infrastructures using enhanced SWITCH model
(2024-07-01) Villalobos Herra, Elena; Gaber, Hossam
The water dimension is not adequately considered in energy models when planning for hydrogen technologies. To overcome this, three novel modules have been developed for the SWITCH energy model: one that considers water drinking systems, a second module that optimizes the size/location/type of hydrogen plants, and the buildings module to integrate buildings using hydrogen-based combined heat and power systems. The modules contribute to the research community by linking the water, hydrogen and power sectors in an energy model. The modules were tested in a case study for Durham Region, using data from 2022. The main results show that the zone of Oshawa is optimal for building a hydrogen electrolysis plant, but facing drastic changes in its power and water demands. Results also show hydrogen-based combined heat and power systems would not be economically feasible unless the price of hydrogen per kilogram is less than CAD$2.13, considering the 2022 parameters.
Modeling and analysis of all-season passenger car tire using finite element analysis
(2024-06-01) Fathi, Haniyeh; El-Sayegh, Zeinab; Ren, Jing
The performance of the ground vehicle is directly affected by its tire characteristics. Tires are the main components of the vehicle that resist all forces and moments generated during contact with the ground. Therefore, it is significant to better understand the effect of all tire characteristics on the tire-road interactions such as cornering maneuvers. In this research work, a 4-groove Continental Cross Contact LX Sport tire size 235/55 R19 101H is designed and modeled using the Finite Element Analysis (FEA) Technique. All tire layers are modeled separately with the corresponding reinforcement rubber layers with detailed geometry. The tire model is then validated using static and dynamic tests at various operating conditions. To achieve the accurate performance of the passenger car tire, the tread rubber is modeled under various temperatures and analyzed using hyper-viscoelastic models. The tire-road characteristics including rolling resistance, cornering characteristics, and traction are explained and investigated.
A hybrid approach for intersection management in V2X-enabled connected vehicles
(2024-08-01) Elmoghazy, Ammar; Elgazzar, Khalid; AlWidian, Sanaa
Autonomous Vehicles (AVs) have the potential to revolutionize transportation by enhancing safety, efficiency, and convenience. However, AVs face significant challenges in complex urban environments, particularly in accurately perceiving and navigating through intersections mainly due to occlusions. This thesis addresses these challenges by integrating Vehicle-to-Everything (V2X) communication with onboard sensors to improve AV perception and decision-making capabilities. In particular, this thesis proposes a hybrid centralized-decentralized management system, which maximizes the benefits of centralized control for strategic traffic management and the responsiveness of decentralized decision-making, using edge nodes as a traffic coordinators helps reduces the computational needs on the vehicle. Such a system leverages V2X data to enhance situational awareness, optimize traffic flow, and improve overall safety and efficiency in urban environments. The methodology involves using Simultaneous Localisation and Mapping - SLAM for mapping, particle filters for localization, and waypoint generation for planning and control. The hybrid system’s performance was evaluated through simulations and real-world experiments using scaled-down vehicles equipped with advanced sensing and communication technologies. Compared to purely centralized or decentralized approaches, the hybrid system achieved up to a 14% reduction in average travel times through intersections and a 20% improvement in overall traffic flow efficiency. This thesis contributes to the development of intelligent transportation systems by demonstrating the efficacy of hybrid intersection management in enhancing AV performance in urban environments.
A multistage-constant-current, temperature-controlled, health-conscious fast charging algorithm for lithium-ion batteries
(2024-08-01) Chetri, Chandan; Williamson, Sheldon
The economical operation and wider adaptability of an electric vehicle (EV) is highly governed by the energy storage system used in the vehicle. To enhance user convenience and compete with their gasoline counterparts, EVs need fast charging methods to achieve equivalent refueling times. However, fast charging can adversely affect the health and cycle life of the battery due to excessive temperature rise resulting in accelerated degradation of the battery chemistry. Especially in subzero conditions, the chemical reactions are much slower, resulting in increased internal impedance. This leads to a higher rate of temperature rise in battery temperature and eventually faster battery degradation. This thesis proposes a closed-loop Multistage-constant-current, Temperature-controlled (MCC-TC), Health-conscious Fast Charging strategy, which modulates the charging current considering the battery temperature as feedback. The experimental validation on an automotive grade battery cell depicts lower temperature rise and rate of temperature rise following the MCC-TC charging algorithm compared to the conventional Constant-Current Constant-Voltage (CC-CV) charging algorithm.
Developing a calibrated low fidelity model and an optimized sensor network using LIVE Digital Twin for pipelines in oil and gas industries
(2024-08-01) Bondoc, Andrew E.; Barari, Ahmad
Digital Twin (DT) solutions are at the forefront of intelligent prognostics and diagnostics of physical systems. The DT is the bidirectional communication between the physical and digital environments for better scheduling, manufacturing processes, health monitoring, etc. This communication is established with an optimized sensor network. LIVE Digital Twin (LIVE DT) is a novel methodology which addresses the lack of standardised DT solutions. This thesis employs LIVE DT to develop a calibrated Low Fidelity (LF) pipeline model. Three fault cases are rapidly simulated using the LF model to circumvent the need of expensive and dangerous physical experimentation. The developed data is used to develop an optimized sensor network for intelligent vibration monitoring of the pipeline. A machine learning algorithm is trained to detect the current fault experienced by the LF model. Furthermore, the presented methods and results can be scaled and customized to produce sensor networks for any physical system.
In-depth study and analysis of lithium-ion battery states using battery degradation data from electrochemical impedance spectroscopy
(2024-07-01) Anekal, Latha; Williamson, Sheldon
This thesis focuses on the study and analysis of lithium-ion battery (LIB) degradation mechanisms throughout the battery life. The performance of LIB deteriorates due to chemical and mechanical degradation that occurs during the battery operation affecting the health of the batteries. It is critical to understand degradation mechanisms for enhancing the performance, reliability, and safety of LIBs. This thesis studies the degradation mechanisms and degradation characterization techniques for designing an equivalent circuit model (ECM) of LIB. The thesis highlights the importance of considering the degradation effects into account for different LIB state estimations including state of charge (SOC), state of health (SOH), state of temperature (SOT), and state of power (SOP). The Electrochemical impedance spectroscopy (EIS) technique is a degradation diagnostic tool. The thesis covered the EIS principles, measurement techniques, and impedance data interpretation specific to LIB. A lithium nickel cobalt aluminium oxide cylindrical (NCA) battery is subjected to charge/discharge cycles to study the battery degradation mechanisms. The impedance spectrum from EIS tests is analyzed for ECM circuit parameterization. From the experimental data the degradation parameters are studied, and it is observed that the bulk resistance (𝑅􀯦), charge transfer resistance (𝑅􀯖􀯧 ), and mass transfer resistance (𝑅􀯪) showed an increasing trend with an increase in cycle life. Growth of the solid electrolyte interface (SEI) layer is observed after the 150th cycle with the evolution of two semi-circles in the Nyquist plots emphasizing the use of second-order ECM for LIB performance estimations. The changes in the double-layer capacitance of LIB are studied through the experimental results. The changes in the temperature behaviour of LIB through aging are highlighted and attributed to the changes in the degradation parameters. Furthermore, the thesis proposes an approach for estimating SOC using an adaptive extended Kalman filter (EKF) based on the parameters obtained from EIS. By updating the ECM parameters, the proposed SOC estimation technique can maintain accuracy throughout the battery life, as the ECM parameters are continuously updated based on feedback from the EIS data.
New frontiers in population-based multi-objective feature selection
(2024-04-01) Zanjani Miyandoab, Sevil; Rahnamayan, Shahryar; Makrehchi, Masoud
Feature selection is a persistent challenge aimed at minimizing the number of features while maximizing accuracy of classification, or any other machine learning and data mining task, by mitigating the curse of dimensionality. We frame feature selection as a multi-objective binary optimization task with the objectives of enhancing accuracy and reducing the feature count. Given that feature selection, along with binary optimization problems in general, is a NP-hard problem since the size of search space increases exponentially by the increase of the number of features, so especially in high-dimensional spaces, it can be very challenging. We propose three innovative approaches to tackle large-scale multi-objective feature selection. The first technique involves an augmentation to the diversity of the population in the well-established multi-objective scheme of the genetic algorithm, NSGA-II, which is achieved through the substitution of the worst individuals with new randomly generated individuals with a limited number of features in each generation. As the second method, a binary Compact NSGA-II (CNSGA-II) algorithm has been introduced for feature selection for the first time, which represents the population as a probability distribution not only to be more memory-efficient but also to accelerate finding a better candidate solution. Additionally, we present a novel binary multi-objective coordinate search (MOCS) algorithm, which, to the best of our knowledge, is the first of its kind, demonstrating effectiveness in solving multi-objective binary optimization problems. A comparative study on the proposed methods and NSGA-II showcases the promising performance of our methods in feature selection tasks involving large-scale datasets, surpassing the renowned NSGA-II algorithm. These methods are not limited to feature selection but can be applied to various binary optimization domains, including the Knapsack problem and training Binary Deep Neural Networks.
Experimental investigations of the thermodynamic properties of Nd-C and Ce-C binary systems for TRISO fuel applications
(2024-04-01) Varga, Ryan Mathew; Atkinson, Kirk; Piro, Markus; Fitzpatrick, Bernie
TRISO fuels are proposed for modular and niche nuclear power reactor technologies, expanding the global nuclear power inventory to meet increasing energy demands through small scale applications. Expansion is dependent upon the improvements to safety through thorough understanding of fission product behaviour, studied and analyzed here using experimental techniques and comparisons to existing literature. Significant knowledge gaps exist in the thermodynamic behaviour of neodymium carbide and cerium carbide fission products that play significant roles in the qualification of TRISO fuels. Thermodynamic investigations of neodymium and cerium carbide isotopic equivalent fission products were performed to improve the knowledge base of TRISO fuels. Various crucible tests, calibrant experimentation, sample generation and sample preparation techniques, and new thermodynamic measurements have been performed. Boron nitride crucibles worked most effectively, providing useful data for comparison to existing literature. Measurements of varying molar compositions of neodymium carbide and cerium carbide provided new data to expand upon predicted phase change boundaries, with experimental phase changes exhibiting comparatively higher transition temperatures.
A hybrid compensation-based misalignment tolerant wireless power transfer system for e-mobility
(2024-04-01) Shrestha, Niranjan; Williamson, Sheldon
The thesis focuses on developing a hybrid compensation with a phase shift control strategy, aiming for misalignment tolerant constant current/constant voltage (CC/CV) charging through a wireless power transfer (WPT) system for e-mobility. The thesis proposes a hybrid multi-resonant compensation network (LCC-LCC and LCC-S) for CC/CV charging during perfect alignment, controlled by the secondary side only. Additionally, the thesis introduces a phase shift control technique in the inverter to maintain the corresponding CC and CV charging mode during the misalignment up to 100 mm between primary and secondary coils. Initially, the theoretical analysis of the proposed system is described in detail. Then, simulation results for 3.7 kW and 270 W peak load were carried out in MATLAB Simulink. Lastly, experimental testing and validation were conducted for the proposed hybrid compensated system for 270 W peak load, applicable to the E-bike. The experimental results show good consistency with theoretical and simulation analysis.
Coupled radiation transport and mobile depletion for health physics and environmental impact applications
(2024-04-01) Sawatzky, Kevin; Atkinson, Kirk D.
The next generation of nuclear reactors pose a large challenge to existing computational methods. Caribou is a MOOSE-based health physics and environmental impact code under development at Ontario Tech which aims to address some of these challenges. This work developed a discrete ordinates radiation transport solver and a radionuclide trace species transport solver in the MOOSE framework for Caribou. This radiation transport solver is compared to several benchmark problems to determine its accuracy with and without ray effect mitigation measures, finding good agreement with all the problems tested. The trace species transport solver is then verified with the method of manufactured solutions. The coupled solvers are then used to analyze the formation of ⁴¹Ar in a containment volume due to ex-core neutron fields, and the photon fields from a ¹³⁷Cs plume. The conclusions of this work indicate that these methods are a valuable addition to Caribou’s suite of capabilities.
Design and development of an LLM-based framework for crime classification and prediction
(2024-04-01) Sarzaeim, Paria; Mahmoud, Qusay H.; Azim, Akramul
Large language models (LLMs), as a subset of generative AI, have been used in different domains, such as financial, medical, legal, and agricultural applications. However, adopting LLMs for smart policing applications remains unexplored. This thesis concentrates on developing a framework based on the transformative potential of the BART, BERT, and GPT models in this domain using methods such as zero-shot prompting, few-shot prompting, and fine-tuning. As a prototype, these methods were used to comprehensively assess the performance of LLMs in crime classification and prediction based on state-of-the-art datasets from two major cities: San Francisco and Los Angeles. The main objective is to illuminate the adaptability of LLMs and their capacity to revolutionize crime analysis practices. Additionally, a comparative analysis of the aforementioned methods on the GPT model and BART with machine learning (ML) techniques is provided. The experimental results demonstrate the feasibility of integrating LLMs into smart policing systems and show that GPT models are more suitable than traditional ML models for crime prediction in most experimental scenarios.
Design and development of a framework for predicting short price jumps in cryptocurrency market
(2024-04-01) Rajaei, Mohammadjavad; Mahmoud , Qusay H.
The cryptocurrency market's volatility offers significant profit opportunities despite its risks. This thesis aims to capitalize on these opportunities by designing and developing a framework to predict whether a coin will experience growth in the next trading candle. To achieve this, we constructed a robust framework that incorporated various input features. We conducted comprehensive analyses by leveraging six machine learning models. Our methodology involves training these models on historical daily data from the Binance Exchange. Subsequently, we evaluate their performance using diverse testing datasets from January 2022 to December 2023. Demonstrating notable precision, especially with a growth rate of 1%, the model has proven effective across various scenarios, consistently yielding profits. Regarding the backward testing results, the XGBoost model combined with the trading strategy made a profit in all three test datasets of Oct 2023, Jul to Sep 2023, and LSK/USDT achieved 24%, 47%, and 98% profits, respectively. This thesis underscores the potential for leveraging well-designed machine learning models to earn significant profits, even in bearish market conditions.
Modeling and testing of an improved 8x8 scaled electric combat vehicle
(2024-04-01) Kim, Junwoo; El-Gindy, Moustafa
The current 8x8 combat vehicle pertaining to multi-wheeled vehicles indicates a lack of effort in developing advanced multi-steering electric drive vehicle. Therefore, novel steering scenarios for an 8x8 scaled electric combat vehicle that features maintaining individual wheel’s steering and speed are developed in this thesis using a scaled 8x8 compat vehicle to introduce a future steering control system for the current combat vehicles. This thesis explains the mechanical improvement of the scaled vehicle compared to the previously developed model. In addition, validation of the scaled electric vehicle model in comparison with a full-size electric drive vehicle model in TruckSim is presented to prove the advantage of using the scaled vehicle in experimental test. Furthermore, development and validation of steering strategies including traditional, fixed 3rd axle, and all-wheel steering scenarios in the scaled vehicle in terms of both experiment and simulation results are conducted to enhance the limitations imposed by conventional vehicle’s steering control system. Active Steering Controller (ASC) is developed and simulated to overcome the limitations of the complete Ackermann steering condition when the scaled vehicle is driving at a relatively high speed. The outcome of this thesis research work is a novel future electric multi-drive and multi-steer combat vehicle.

Browse

Recent Submissions