No abstract

With the increasing popularity of electric vehicles (EVs), the demands for rechargeable and high-performance batteries like lithium-ion (Li-ion) batteries have soared. Li-ion battery systems require the use of a battery management system (BMS) to perform safely and efficiently. Accurate and reliable battery modeling is important for the BMS to function properly. Currently, many BMS applications use the equivalent circuit model due to its simplicity. However, with the development of a cloud BMS, machine learning battery models can be utilized, which can potentially improve the accuracy and reliability of the BMS. This work investigates the performance of four different machine learning models used to predict the thermal (temperature) and electrical (voltage) behaviors of Li-ion battery cells. A prismatic Li-ion battery cell with a capacity of 25 Ah was cycled under a constant current profile at three different ambient temperatures, and the surface temperature and voltage of the battery were measured. The four machine learning regression models-linear regression, k-nearest neighbors, random forest, and decision tree-were developed using the scikit-learn library in Python and validated with experimental data. The results of their performance were reported and compared using the R 2 metric.The decision tree-based model, with an R 2 score of 0.99, was determined to be the best model in this case study.

Automated assembly machines operate continuously to achieve high production rates. Continuous operation increases the potential for faults, with subsequent machine downtime. Early fault detection can reduce the amount of downtime. Traditional fault detection methods check for deviations from fixed threshold limits with multiple mechanical, optical and proximity sensors. The goal of this thesis was to develop and validate a machine vision inspection (MVI) system to detect and classify multiple faults using a single camera as a sensor. An industrial automated O-ring assembly machine that places O-rings on to continuously moving plastic carriers at a rate of over 100 assemblies per minute was modified to serve as the test apparatus. An Firstly, I would like express my sincere gratitude to my supervisor Dr. Brian W. Surgenor for his supervision of this project. He has provided to me an opportunity to learn both technical and professional aspects of engineering. I am very thankful to him for his encouragement, support and constant feedback throughout the course of my studies at Queen's University. He is a great teacher, supervisor and a nice person. Thank you Dr. Surgenor.

Liquid water management remains a primary challenge in developing next generation low temperature proton exchange membrane fuel cells. This work demonstrates the use of acoustic pressure waves superimposed on reactant channel air flow as an effective means to enhance liquid water removal from gas diffusion layer surfaces. Experiments were conducted for a range of acoustic vibration frequencies; 20 to 120 Hz with 20 Hz intervals. Water transport was visualized using a CCD camera mounted over a transparent ex-situ PEM fuel cell test channel. Cumulative water areas were measured along the flow channel along with two-phase flow pressure drop for water fluxes of 400, 600, and 800 μ /h and a superficial air velocity of 1.82 m/s. Results show that superimposing acoustic pressure waves on the air flow can reduce liquid water build up and, therefore, reduce two-phase flow pressure drops. Cumulative water area was reduced almost 85% with an acoustic vibration frequency of 80 Hz compared to the 0 Hz case. Additionally, at 80 Hz the lowest two-phase flow pressure drop was recorded. Finally, a comparison of energy usage is made between different acoustic vibration application methods.

No abstract