Date of Award


Document Type

Masters Thesis

Degree Name


Organizational Unit

Daniel Felix Ritchie School of Engineering and Computer Science, Electrical and Computer Engineering

First Advisor

Rui Fan

Second Advisor

David W. Gao

Third Advisor

Mark E. Siemens


Machine learning, Multilayer perceptron, Support vector machine, Wind turbines


The inertia and damping coefficients are critical to understanding the workings of a wind turbine, especially when it is in a transient state. However, many manufacturers do not provide this information about their turbines, requiring people to estimate these values themselves. This research seeks to design a multilayer perceptron (MLP) that can accurately predict the inertia and damping coefficients using the power data from a turbine during a transient state. To do this, a model of a wind turbine was built in Matlab, and a simulation of a three-phase fault was used to collect realistic fault data to input into the turbine simulation. The model of the turbine was repeatedly run to generate simulated power data, where each run used a different inertia and damping coefficient. The generated data was used to train the MLP to accurately predict the coefficients. The MLP was able to predict the damping coefficient with an average prediction error of 0.159% and the inertia coefficient with an average prediction error of 0.176%. A sensitivity analysis was done on the MLP to test how noise in the power data and the size of the training data affected the magnitude of the prediction errors. To illustrate the efficacy of the MLP, a support vector machine (SVM) was designed and used to predict the inertia and damping coefficients using the same input data as was used in the MLP. The MLP outperformed the SVM in its predictions for the ideal case and for every case studied in the sensitivity analysis.

Publication Statement

Copyright is held by the author. User is responsible for all copyright compliance.

Rights Holder

Rebecca McCubbin


Received from ProQuest

File Format




File Size

51 pgs


Electrical engineering, Artificial intelligence