Engineering Commons^™

Data Driven Sensor Fusion For Cycle-Cycle Imep Estimation, Cooper Heyne Minehart

Dissertations, Master's Theses and Master's Reports

As the world searches for ways to reduce humanity’s impact on the environment, the automotive industry looks to extend the viable use of the gasoline engine by improving efficiency. One way to improve engine efficiency is through more effective control – effective control systems require a feedback signal. Indicated mean effective pressure (IMEP) is a useful feedback signal for automotive control but is costly to measure directly.

Successful machine learning based sensor fusion requires effective feature extraction and model creation. Through a multistage application of machine learning to both the feature extraction process and the IMEP estimation process we are …

Deep Learning Of Nonlinear Dynamical System, Aditya Wagh

Dissertations, Master's Theses and Master's Reports

A data-driven approach, such as neural networks, is an alternative to traditional parametric-model methods for nonlinear system identification. Recently, long Short- Term Memory (LSTM) neural networks have been studied to model nonlinear dynamical systems. However, many of these contributions are made considering that the input to the system is known or measurable, which often may not be the case. This thesis presents a method based on LSTM for output-only modeling, identification, and prediction of nonlinear systems. A numerical study is performed and discussed on Duffing systems with various cubic nonlinearity.

A Neural Network Approach To Estimate Buoy Mooring Line Sensor Deflection, Tom Price

Dissertations, Master's Theses and Master's Reports

Instrumented moorings are often used to measure characteristics, such as temperature and current, over the water column. However, the moorings deflect from the effects of currents and waves, which could lead to innacurate measurements. In this work, a computationally efficient method to compensate for mooring sensor position errors is developed. The two-step process first uses a hydrodynamic model of the buoy and mooring line system to create estimated mooring line deflections in a steady current. A neural network model is trained to approximate the hydrodynamic model’s mooring line displacement given the spatial location of the buoy and current profile measurements. …