Senior Design Projects - Summer 2022 Showcase

Heart disease is a significant problem in the United States and worldwide. As the population increases and the average age rises, cardiovascular health solutions will only increase in demand. Unfortunately, current methods of monitoring the heart are expensive and require the patient to take time out of their day that they may not have to visit a medical professional. 

"Most power around the world is generated at a central location and distributed through transmission and distribution lines. Microgrids are a relatively new type of distributed generation, where there are many different generation facilities distributed across the territory. Microgrids typically serve a specific geographic location and have a utility connection. Any excess power generated by a microgrid is sent back to the utility to assist with the load. In oredr to ensure proper functioning of a microgrid, there must be a control center where all aspects of the microgrid are tracked and controlled. Before a microgrd is implemented, models must be created to ensure that it is going to have predictable funcionality. Our hardware-in-the-loop approach uses a Programmable Logic Controller (PLC) to control a simulated microgrid. The PLC accepts inputs from the model, and based on a set of predetermined scenarios, it will ouput a signal to produce a desired state on the grid. This product will be fully autonomous, providing increased reliability and safety for customers and engineers alike. The main objectives of this product are the afore mentioned safety, reliabilty, sustainability, and scalability."

Proton exchange membrane (PEM) fuel cell is a highly efficient and low emission electrochemical device that can be applied in many fields, including automobiles, renewable energy generation, and the military. The PEM fuel cell technology has made significant progress in increasing performance, reducing costs, and improving durability in recent years. However, the output performance and durability of PEM fuel cells are still insufficient for broad commercialization at this stage. The mechanisms causing performance degradation are various and complicated in these degradation processes, but it is widely recognized that analysis and prediction of the degradation behaviors are critical.

Besides the physical modeling of the PEM Fuel Cell, many studies developed data-driven models to predict the transient behaviors of PEM fuel cells. The data-driven model constructs the input-output relationship from an experimental dataset. A predictive approach based on an artificial neural network (ANN) could effectively predict the remaining useful life and short-term degradation of fuel cells, where an attention-based recurrent neural network (RNN) model that could accurately predict the output voltage degradation of PEM fuel cells based on original longterm dynamic loading cycle durability test data. Based on the literature review, machine learning was mainly used for the long-term degradation process prediction of PEM fuel cells. The cell performance degradation process was measured in the initial period (generally hundreds of hours). The data was used to predict the degradation process in the future time through machine learning.