Mechanical Engineering Commons^™

Towards Real-Time Reinforcement Learning Control Of A Wave Energy Converter, Enrico Anderlini, Salman Husain, Gordon Parker, Mohammad Abusara, Giles Thomas

Michigan Tech Publications

The levellised cost of energy of wave energy converters (WECs) is not competitive with fossil fuel-powered stations yet. To improve the feasibility of wave energy, it is necessary to develop effective control strategies that maximise energy absorption in mild sea states, whilst limiting motions in high waves. Due to their model-based nature, state-of-the-art control schemes struggle to deal with model uncertainties, adapt to changes in the system dynamics with time, and provide real-time centralised control for large arrays of WECs. Here, an alternative solution is introduced to address these challenges, applying deep reinforcement learning (DRL) to the control of WECs …

Optimal Mission Planning Of Autonomous Mobile Agents For Applications In Microgrids, Sensor Networks, And Military Reconnaissance, Casey D. Majhor

Dissertations, Master's Theses and Master's Reports

As technology advances, the use of collaborative autonomous mobile systems for various applications will become evermore prevalent. One interesting application of these multi-agent systems is for autonomous mobile microgrids. These systems will play an increasingly important role in applications such as military special operations for mobile ad-hoc power infrastructures and for intelligence, surveillance, and reconnaissance missions. In performing these operations with these autonomous energy assets, there is a crucial need to optimize their functionality according to their specific application and mission. Challenges arise in determining mission characteristics such as how each resource should operate, when, where, and for how long. …

Modeling Of Thermal Dynamics In Chevrolet Volt Gen Ii Hybrid Electric Vehicle For Integrated Powertrain And Hvac Optimal Operation Through Connectivity, Nehal Doshi

Dissertations, Master's Theses and Master's Reports

Integrated thermal energy management across system level components in electric vehicles (EVs) and hybrid electric vehicles (HEVs) is currently an under explored space. The proliferation of connected vehicles and accompanying infrastructure in recent years provides additional motivation to explore opportunities in optimizing thermal energy management in EVs and HEVs with the help of this newly available connected vehicle data. This thesis aims to examine and analyze the potential to mitigate vehicle energy consumption and extend usable driving range through optimal control strategies which exploit physical system dynamics via controls integration of vehicle subsystems.

In this study, data-driven and physics-based models …

Electromagnetic Signal Feedback Control For Proximity Detection Systems, Adam K. Smith

Dissertations, Master's Theses and Master's Reports

Coal is the most abundant fossil fuel in the United States and remains an essential source of energy. While more than half of coal production comes from surface mining, nearly twice as many workers are employed by underground operations.

One of the key pieces of equipment used in underground coal mining is the continuous mining machine. These large and powerful machines are operated in confined spaces by remote control. Since 1984, 40 mine workers in the U. S. have been killed when struck or pinned by a continuous mining machine. It is estimated that a majority of these accidents could …

Simulation Of Human Ankle Trajectory During Stance Phase Of Gait, Leslie Castelino

Dissertations, Master's Theses and Master's Reports

A simulation was developed which mimics the human gait characteristics based on the input of an individual’s gait trajectory. This simulation also estimates the impedance of the human ankle based on the ground reaction forces measured by the force plate. This simulation will accept alterations of the following parameters: total body weight, weight of the shank, weight of the foot, trajectories of the shank and foot of the individual and orientation of the force plate, which would generate a new gait trajectory for the ankle during the stance phase of gait. The goal of this simulation was to validate the …